Systems, methods and computer program products for postural control assessment

Abstract

A postural control assessment system, postural control assessment the system including: (a) a hardware communication channel, for providing to a processor sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; (b) at least one processor; and (c) at least one memory including computer program code. The at least one memory and the computer program code are configured, with the at least one processor, to cause the system to at least: (i) obtain timing information of a balance destabilizing event within the measurement time span; (ii) identify in the kinematic data kinematic fluctuation patterns of stability compensation movements following the balance destabilizing event; and (iii) process the kinematic fluctuation patterns to determine a postural instability condition of the individual.

Description

SYSTEMS, METHODS AND COMPUTER PROGRAM PRODUCTS FOR POSTURAE CONTROE ASSESSMENTFIELD

[0001] The invention related to systems, methods, and computer program products for assessing a postural instability condition of a person, and especially to systems, methods, and computer program products for assessing a postural instability condition (e.g., a cognitive state) of a person based on analysis of kinematic data of the person following a balance destabilizing event.BACKGROUND

[0002] Effective postural stability is crucial for carrying out daily activities, both in static and dynamic conditions (Haddad et al., 2013). Existing literature indicates that postural stability is controlled by both automatic and cognitively controlled processes (Takakusaki, 2017). Neural circuits in the cerebellum, brain stem, and spinal cord play a role in automatically regulating postural control, integrating multi-sensory information from visual, vestibular, and proprioceptive systems (Boisgontier et al., 2017). However, some studies suggest that maintaining stability requires cognitive processing, especially for more complex tasks (see for example, Boisgontier et al., 2013 and its cited sources). Even well-practiced tasks like upright stance can demand attention (Vuillerme et al., 2006), and challenging tasks like Romberg stance or tandem stance require attention as well (Hwang et al., 2013).

[0003] Some of the publications which can provide a background for the present disclosure include: a. Takakusaki K (2017) Functional neuroanatomy for posture and gait control. J Mov Disord 10(1): 1 b. Haddad JM, Rietdyk S, Claxton LJ, Huber J (2013) Task-dependent postural control throughout the lifespan. Exerc Sport Sci Rev 41(2): 123 c. Boisgontier MP, Cheval B, Chalavi S, van Ruitenbeek P, Leunissen I, Levin O, Swinnen SP (2017) Individual differences in brainstem and basalganglia structure predict postural control and balance loss in young and older adults. Neurobiol Aging 50:47-59 d. Fraizer EV, Mitra S (2008) Methodological and interpretive issues in posture-cognition dual-tasking in upright stance. Gait Posture 27(2):271- 279 e. Jacobs J, Horak F (2007) Cortical control of postural responses. J Neural Transm 114(10): 1339-1348 f. Kerr B, Condon SM, McDonald LA (1985) Cognitive spatial processing and the regulation of posture. J Exp Psychol Hum Percept Perform 11(5):617 g. Woollacott M, Shumway-Cook A (2002) Attention and the control of posture and gait: a review of an emerging area of research. Gait Posture 16(1):1— 14 h. Vuillerme N, Isableu B, Nougier V (2006) Attentional demands associated with the use of a light fingertip touch for postural control during quiet standing. Exp Brain Res 169(2):232-236. https: / / doi. org / 10. 1007 / s00221- 005- 0142-7 i. Hwang JH, Lee C-H, Chang HJ, Park D-S (2013) Sequential analysis of postural control resource allocation during a dual task test. Ann Rehabil Med 37(3):347 j. Lanzarin M, Parizzoto P, Libardoni TDC, Sinhorim L, Tavares G, Santos G (2015a) The influence of dual-tasking on postural control in young adults. Fisioter Pesquisa 22( 1 ):61— 68 k. Lanzarin M, Parizzoto P, Libardoni TDC, Sinhorim L, Tavares GMS, Santos GM (2015b) The influence of dual-tasking on postural control in young adults. Fisioterapia e Pesquisa 22( 1) :61— 68 l. Wollesen B, Voelcker-Rehage C, Regenbrecht T, Mattes K (2016) Influence of a visual-verbal Stroop test on standing and walking performance of older adults. Neuroscience 318:166-177m. Ruffieux J, Keller M, Lauber B, Taube W (2015) Changes in standing and walking performance under dual-task conditions across the lifespan. Sports Med 45(12): 1739-1758 n. Stins JF, Beek PJ (2012) A critical evaluation of the cognitive penetrability of posture. Exp Aging Res 38(2):208-219 o. Andrade LPD, Rinaldi NM, Coelho FGDM, Tanaka K, Stella F, Gobbi ETB (2014) Dual task and postural control in Alzheimer’s and Parkinson’s disease. Mot Rev De Educ Ffs 20(l):78-84. https: / / doi.org / 10.1590 / sl980- 6574201400 0100012 p. Brown FA, Shumway-Cook A, Woollacott MH (1999) Attentional demands and postural recovery: the effects of aging. J Gerontol Ser A Biomed Sci Med Sci 54(4):M165-M171 q. Shumway-Cook A, Woollacott M (2000) Attentional demands and postural control: the effect of sensory context. J Gerontol Biol Sci Med Sci 55(l):M10 r. Ghai S, Ghai I, Effenberg AO (2017) Effects of dual tasks and dualtask training on postural stability: a systematic review and metaanalysis. Clin Interv Aging 12:557 s. Andersson G, Hagman J, Talianzadeh R, Svedberg A, Larsen HC (2002) Effect of cognitive load on postural control. Brain Res Bull 58(1): 135-139 t. Shumway-Cook A, Woollacott M, Kerns KA, Baldwin M (1997) The effects of two types of cognitive tasks on postural stability in older adults with and without a history of falls. J Gerontol A Biol Sci Med Sci 52(4):M232-M240 u. Huxhold O, Li S-C, Schmiedek F, Lindenberger U (2006) Dualtasking postural control: aging and the effects of cognitive demand in conjunction with focus of attention. Brain Res Bull 69(3):294-305

[0004] In light of the cited prior art, there remains a need for novel systems, methods and computer program products for assessment of postural instability conditions.GENERAL DESCRIPTION

[0005] In the following disclosure, the disclosed systems, methods, and computer program products disclosed in the present disclosure utilize measurements which are indicative of the postural control of individuals to determine postural instability conditions of these individuals. While not necessarily so, the measurement of kinetic parameters of movements by such an individual may be held when that individual is preoccupied with performing another task (e.g., driving, reading, using a smartphone, using a computer, solving a problem, and so on). Performing a cognitive task alongside a postural task may reduce available attentional resources for postural control, potentially leading to reduced postural stability (Lanzarin et al., 2015a, b). This may be explained by the cross-domain resource competition hypothesis, which suggests that both postural stability and cognitive task performance draw from a limited pool of cognitive resources, leading to a decline in either or both tasks when performed concurrently (Wollesen et al., 2016). Furthermore, the complexity of the cognitive task may deplete attentional resources, particularly in older adults, leaving postural stability under-resourced (Rufeux et al., 2015).

[0006] The dual task paradigm has been used to explore the cognitive demand of postural control in both healthy and clinical populations (Stins and Beek, 2012). Some studies demonstrated decreased postural stability during dual tasking (Andrade et al., 2014; Brown et al., 1999), while others reported an improvement in postural stability (Shumway-Cook and Woollacott, 2000). A systematic review by Ghai and colleagues revealed that 50% of included studies found decreased postural stability during dual tasking and 30% reported an improvement in postural stability (Ghai et al., 2017). Thus, in at least some situations and for at least some groups of individuals, dual tasking leads to altered postural stability.

[0007] The inconsistencies in the literature regarding dual tasking's effects on postural stability may be attributed to the use of cognitive tasks with varying complexities and different balance tasks (Andersson et al., 2002). When postural demand on attentional resources is low, a simple cognitive task may not significantly affect postural stability, but a more demanding task might have an adverse impact (Shumway-Cook et al., 1997). Alternatively, postural stability during dual tasking may improve or deteriorate depending on the cognitive demand of the secondary task; asimple cognitive task might enhance stability by providing an external focus of attention, whereas a more complex task could lead to resource competition and reduced postural stability (U-shaped non-linear hypothesis) (Huxhold et al., 2006).

[0008] A measure known in the art to be an effective measure of Postural stability is postural sway. Postural sway refers to the involuntary movement or oscillation of the body's center of mass while maintaining an upright posture. It is an essential aspect of assessing a person's balance and stability. Various measures can be used to quantify postural sway. Here are some of the commonly used measures: a. Center of Pressure (COP) Excursion: The Center of Pressure represents the point of application of the ground reaction force beneath the feet. COP excursion measures the total distance covered by the COP in the medial- lateral (side-to-side) and anterior-posterior (front-to-back) directions during a specified period. It is often expressed in millimeters. b. COP Velocity: It is the speed at which the COP moves. It can be calculated as the total distance covered by the COP divided by the time taken to cover that distance. COP velocity is usually measured in millimeters per second (mm / s). c. COP Area: The COP area is the total area enclosed by the COP trajectory. It represents the overall sway range of the body during a specific time interval and is typically measured in square millimeters (mm2) or centimeters squared (cm2). d. Root Mean Square (RMS): RMS represents the average amplitude of postural sway movements. It calculates the root mean square deviation of the COP from the mean position. RMS values for both medial-lateral and anterior-posterior directions are often reported separately. e. Total Sway Path: This measure quantifies the total path length of the COP trajectory during the observation period. It reflects the cumulative distance covered by the COP and can be expressed in millimeters. f. Maximum Sway: Maximum sway indicates the highest displacement of the COP from the central position in both the medial-lateral and anterior- posterior directions. It is commonly expressed in millimeters.g. Sway Frequency: Sway frequency is the number of oscillations or movements of the COP within a given time frame, typically expressed in cycles per second or Hertz (Hz). h. Sway Power Spectral Density: This measure analyzes the frequency distribution of postural sway. By using a Fourier transform on the COP data, researchers can identify different frequency components of sway and quantify their power at each frequency band. i. Romberg Quotient: The Romberg quotient is used to assess postural stability under different sensory conditions (e.g., eyes open vs. eyes closed). It is calculated by dividing the COP sway area with eyes closed by the COP sway area with eyes open. A value greater than 1 suggests a higher reliance on visual information for balance. j. Ellipse Area: This measure quantifies the area of an ellipse fitted around the COP trajectory. It provides an estimation of the spatial dispersion of postural sway and is commonly used in dynamic posturography. k. These measures are typically obtained using force platforms, pressuresensitive mats, or other specialized equipment designed to record the movements of the COP. Researchers and clinicians use these measures to assess postural stability, identify balance impairments, and monitor changes in balance over time in various populations, such as athletes, elderly individuals, and patients with neurological disorders.

[0009] Corrective submovements are small corrective movements that occur during the execution of a larger movement, and they are thought to play a crucial role in motor learning and adaptation. The relationship between corrective submovements and cognition has been studied extensively in the context of motor control and learning. One line of research has investigated the role of cognitive processes such as attention, working memory, and decision-making in the generation and control of corrective submovements. For example, studies have shown that attentional load can affect the size and timing of corrective submovements during a reaching task (Plamondon & Alimi, 1997), and that working memory demands can influence the planning and execution of corrective submovements during a visuomotor adaptation task (Galea & Darian-Smith, 1994). Another line of research has focused on the relationship betweencorrective submovements and cognitive control processes such as inhibition and cognitive flexibility. For example, studies have shown that inhibition of an ongoing movement can lead to the generation of corrective submovements (Stinear & Byblow, 2003), and that cognitive flexibility can facilitate the adaptation of corrective submovements to changing task demands (Noble, Smout, & Byrne, 2018).

[0010] Beyond the scientific literature there are several patents dealing with the connection between corrective submovements and cognition. In these applications, Hochman (WO2022123568A1; US 11,141,113 B2) presented methods for analyzing corrective submovements as a means for monitoring a person's cognitive state during daily activities.

[0011] The following publications discuss interrelationship perturbation tasks and resulting corrective submovements, organized by year of publication: Jones and Hunter (1983) investigated the effects of perturbations on reaching movements. They found that sudden perturbations to the reaching hand resulted in corrective submovements that helped to bring the hand back to the target. Soechting and Lacquaniti (1983) conducted a study on the effects of sudden perturbations on the trajectory of reaching movements. They found that the corrective submovements produced were consistent with the predictions of the optimal feedback control model. Ghez and colleagues (1995) examined the role of visual feedback in the production of corrective submovements. They found that when visual feedback was removed, the magnitude and timing of corrective submovements were reduced. Scheidt and colleagues (2000) investigated the effects of perturbations on the adaptation of arm movements to novel force fields. They found that sudden perturbations could disrupt the adaptation process, but that corrective submovements helped to compensate for the perturbations and improve performance. Franklin and Wolpert (2008) proposed a computational model of corrective submovements that incorporated both sensory feedback and feedforward control. The model was able to reproduce many of the key features of corrective submovements observed in experimental studies. Shemmell and colleagues (2010) investigated the effects of perturbations on the coordination of muscle activity during reaching movements. They found that perturbations resulted in changes to the timing and magnitude of muscle activity, consistent with the production of corrective submovements. Kagerer and colleagues (2013) conducted a study on theeffects of perturbations on the coordination of hand and eye movements. They found that perturbations resulted in changes to the timing and direction of eye movements, as well as the production of corrective submovements in the hand. Mawase and colleagues (2014) investigated the effects of perturbations on the adaptation of grasping movements to novel object properties. They found that perturbations could disrupt the adaptation process, but that corrective submovements helped to compensate for the perturbations and improve performance.

[0012] Assessing the postural control of a person can be useful in many situations, such as when having inadequate postural control could put that person or others at risk, when the individual is operating machinery or performing tasks that require a sufficient degree of balance and spatial awareness, and so on. Likewise, an evaluation of postural control may offer critical insights for medical professionals. For instance, an individual's poor postural control might be indicative of a previously undiagnosed medical condition, such as a neurological disorder or musculoskeletal issue. Furthermore, postural control could act as an early warning system for certain conditions or situations, enabling timely intervention and potentially mitigating more severe outcomes. Inadequate postural control may also be indicative of a cognitive state of the person (e.g., confused, intoxicated, tired, and so on). Therefore, the ability to accurately and effectively assess an individual's postural control holds significant importance across a range of applications. Significantly, the systems, methods, and computer program products disclosed in the present disclosure may be used for determining a transient or short-term types of PIC (e.g., intoxication, fatigue) and / or a long-term types of PIC (such as diseases, chronic conditions, or neurological deterioration). Detecting long-term types of PIC may be based on single measurements of the individual (e.g., during a single ride of a vehicle), or on multiple measurements of the same individual over time (for example, by comparing how specific parameters determined during the execution of method 500, for example, change over weeks, months, and years). The systems, methods, and computer program products discussed below details techniques for assessing the postural control of a person using sensor- collected kinematic data indicative of the kinematics of one or more body parts of that person. It is noted that the invention may be applied to people in any body positions (e.g., lying, sitting, standing, squatting), in rest or during any activity (e.g., walking, running, jumping, cartwheeling).

[0013] An example scenario might be, for example, to detect motion sickness or other form of postural instability while the person is riding and / or driving a vehicle. This may be used, for example, to make sure that the driver can serve as a backup for the autonomous driving system, or in order to make sure that a passenger in the vehicle feels well and does not suffer from motion sickness. The analyzed kinematic data does not have to be collected when the person attempts to perform a purposeful task (such as, for example, driving the vehicle), but may be collected in any one of many scenarios (e.g., when the person is busy or idle, concentrated or distracted), when the person is subjected to a Balance Destabilizing Event (BDE) which causes the person a temporary loss of balance. Following such a BDE, posture control capabilities of the person are triggered, and data indicative of movements of the person when applying her posture control capabilities may be used in order to assess a state of that person (be it a cognitive state, or other types of state as discussed below). The collection of the kinematic data may be carried out by one or more sensors, measuring kinematic data indicative of movement of one or more body parts of the person directly (e.g., accelerometer worn by the person) or indirectly (e.g., sensors measuring kinematics of the steering wheel which is operated by that person). The systems and methods discussed below processed such kinematic data collected after the person experienced a BDE, e.g., by identifying and further processing a plurality of movements executed by the person (including very slight movements, such as submovements), whose unique characteristics indicate different states of the person (e.g., different levels of motion sickness).

[0014] Postural balance refers to the ability of a person to maintain an upright and stable posture while standing, sitting or moving. It involves coordination of various muscle groups and proper alignment of the body's center of gravity, which allows for efficient movement and reduces the risk of falls or injuries. Among other things, postural balance is important for maintaining good health and mobility, as well as for participating in activities that require physical stability and coordination. Factors that can impact postural balance include muscle strength, flexibility, joint range of motion, and sensory input from the eyes, ears, and other senses.

[0015] The cortical mechanism responsible for detecting postural errors involves a network of brain regions including the primary somatosensory cortex (SI), the primarymotor cortex (Ml), the cerebellum, and the parietal cortex. These regions work together to process sensory information from the body and compare it to stored motor plans, allowing for the detection of any discrepancies or errors in posture. The primary somatosensory cortex (SI) receives sensory information from the body, including proprioceptive information from the muscles and joints. This information is then sent to the primary motor cortex (Ml) and to the cerebellum, which use it to plan and execute movement. The parietal cortex is also involved in this process, as it is responsible for integrating sensory information from different sources and creating a cohesive representation of the body in space. When there is a discrepancy between an intended movement of the person and the actual movement, the parietal cortex sends a signal to the primary motor cortex (Ml) to correct the error. This process is known as feedback-based control, and it allows for the detection and correction of postural errors in real-time.

[0016] Error-Related Negativity (ERN) is a component of the Event- Related Potential (ERP) that is thought to be related to the detection of postural errors (in the case of a postural error it is referred to as “balance Nl”). The ERN is a negative deflection in the ERP that occurs shortly after an error is made, and it is thought to reflect the neural activity associated with the detection of an error and the subsequent correction. The exact neural mechanisms underlying the ERN are still not fully understood, but it is thought to involve the anterior cingulate cortex (ACC), which is a key component of the error-monitoring network. In conclusion, the cortical mechanism responsible for detecting postural errors involves a network of brain regions that work together to process sensory information, plan and execute movement, and detect and correct errors in real-time. The error-related negativity (ERN) is thought to reflect the neural activity associated with the detection of postural errors and the subsequent correction.

[0017] The brain uses a variety of mechanisms to correct posture errors. One of the primary mechanisms is the proprioceptive system, which is a network of sensors located throughout the body that provide the brain with information about the body's position and movement. When the body is in an inadequate posture, the proprioceptive system sends signals to the brain indicating that the body is out of alignment. The brain then activates the appropriate muscles to correct the posture error. Another mechanismused by the brain to correct posture errors is the vestibular system, which is a system of sensors located in the inner ear that provide the brain with information about balance and spatial orientation. When the body is off balance or tilted, the vestibular system sends signals to the brain, which activates muscles to correct the posture error. The brain also uses visual cues to help correct posture errors. When the body is not aligned with the surrounding environment, the brain uses visual information to adjust the body's position and alignment. Finally, the brain uses feedback from the body's muscles and joints to help correct posture errors. When a muscle is overworked or strained, the brain receives feedback from the muscle and adjusts the body's posture to relieve the strain. Overall, the brain uses a combination of proprioceptive, vestibular, visual, and muscle feedback to correct posture errors and maintain good posture.

[0018] This disclosure describes various systems, methods, and computer program products which can analyze kinematic data (such as corrective submovements) of a person who experiences a BDE. It is noted that while the physiological and neurological information provided above may assist the reader in getting a deeper understanding of some aspects of the invention, this information is not intended to limit the scope of the invention, and other aspects of the invention may be implemented whatever physiological or neurological processes happen in the person’s body in response to the BDE.

[0019] The outputs of such an analysis of kinematic data (e.g., of corrective submovements) of the person are an assessment of a state of the person, such as an assessment of a postural instability condition (PIC) of the person, an assessment of a cognitive state of the person, and so on. Such an assessment, in turn, can then be utilized to select a follow-up action to be taken, considering the detected state. The proposed analysis enables assessment of the PIC of the person (e.g., detecting fatigue, intoxication, or motion sickness) based on very slight submovements of one or more body parts of that person.

[0020] The system uses kinematic data collected by sensors located either on the person's body, in electronic devices that come in contact with that person, or which can otherwise detect movement of the person (e.g., camera or radar). This kinematic data may be collected in real-time and stored for later analysis, or be processed in realtime or close thereto, depending, for example, on the intended follow-up actions andtheir urgency. The collected kinematic data (possibly after preprocessing procedures) is then processed by a suitable model. Such models may be based, for example, on machine learning, on heuristic or rule-based algorithms, on combination of both, or on any other suitable algorithm. The systems and methods may infer the PIC of the person by analyzing the kinematic data corresponding to kinematic fluctuations and motion patterns that occur when the person experiences a BDE. For example, such kinematic fluctuations and motion patterns may include subtle changes in body angles, angular velocities, and angular accelerations that are not visible to the eye.

[0021] Within the context of the present disclosure, the phrase “postural instability condition” denotes a state of the individual characterized by the compromised ability of the individual to maintain or regain stable body posture or balance. Further details and examples are provided below. Within the context of the present disclosure, the phrase “cognitive assessment” refers to the process of evaluating an individual's cognitive abilities, such as memory, attention, language, perception, and problemsolving skills. It has been an important aspect of neuropsychology, especially in the diagnosis and treatment of neurocognitive disorders such as dementia, traumatic brain injury, and attention deficit hyperactivity disorder (ADHD). In recent years, with the advancement of technology and the widespread use of smartphones, there has been a surge in the development of computerized cognitive assessment applications (e.g., smartphone apps). Such apps aim to provide an efficient and accessible way to assess a person's cognitive state.

[0022] As discussed below in greater detail, there are a variety of different ways to calculate motion patterns (such as — but not limited to — submovements), which may include at least two steps. One of these steps includes identifying a beginning and an end of a primary movement. A second one of these steps includes identifying and / or labeling various speed derivatives (e.g., acceleration, jerk) which appear within the primary movement (from beginning to end, and sometime slightly after the end). In many cases the primary movement is a sharp movement in one direction, while in other cases the primary movement may be a continuous and very long movement. In the latter case, the movement along its entire length can be defined as a primary movement. At the end of the process various calculations are made on the speed derivatives.

[0023] It is noted that the directions of the stability compensation motions (e.g., submovements) are not necessarily in the same axis (or primarily along the same axis) as the thrust or impulse of the BDE. The measurement of the kinematic features and / or of the motion patterns, and the subsequent processing of the data may pertain to movement in directions other than that of the thrust, in one or more exes. Optionally, the relationship between the direction of a stability compensation motion to the direction of the thrust of the BDE may be part of the kinematic features and / or kinematic fluctuation patterns used in the processing for determining the PIC.

[0024] It is noted that optionally, the kinematic features (such as kinematic fluctuation patterns) of each motion pattern (e.g., submovement or other type of brief motion) are measured and analyzed independently, albeit using average values of multiple such motion patterns may also be used.

[0025] The processing of the kinematic data of the identified movements for determining the PIC of the person may be achieved using various computational and algorithmic approaches, such as using heuristic algorithms, machine learning algorithms, or combination of both. Referring to system 200 as well as to method 500, it is noted that the present invention may be implemented using various approaches, including but not limited to: machine learning techniques, heuristic algorithms, expert systems, statistical methods, fuzzy logic systems, or other suitable computational strategies. It is noted that different methods of machine learning and / or different methods of heuristic algorithms may be used in synergy, in order to identify unique features (such as unique kinematic fluctuation patterns) in the movements that correspond to differences between different PICs. That is, in the movements which are analyzed (especially after a BDE), the kinematic fluctuation patterns in each person have features which depend on the PIC of that person, wherein a person with different PICs (either different people or the same person in different times) demonstrate different kinematic fluctuation patterns which correspond to the PIC, and whose parameters could be identified and utilized in the determining of the PIC in the disclosed systems, methods, and computer program products. One way of collecting reference data (as well as training data for machine learning algorithms, if used) is to implement parametric manipulation of the postural instability condition, for example by giving different amounts of alcohol to the subjects or by inducing different levelsof fatigue in the subjects. The machine learning model (or neural networks) may than then run on the data. Such a model may be specifically guided to explore the many smaller movements (e.g., submovements) occurring within the primary movement, especially following balance destabilizing events (optionally of different magnitudes or characteristics).

[0026] As noted, different types of movements of the individual may be used in the processing of the kinematic data for determining the PIC of the individual. A broad definition of such movements may include movement adjustments (the deliberate or involuntary changes in the positioning and motion of the person's body (and especially of the measured body part, body parts, or other measured body portions of the body of that individual) in response to a loss of balance followed by a BDE. Submovements, e.g., as defined above, are one example of such movement adjustments which may be analyzed for determining the PIC, even though other types of movement adjustments may be analyzed as well (e.g., as discussed below). Corrective submovements are one example of such submovement which may be analyzed for determining the PIC, even though other types of submovements may be analyzed as well (e.g., as discussed below).

[0027] One example scenario in which such systems, methods, and computer program products may be used is for fleets managers (for any suitable type of vehicles, such as cars, trucks, scooters, heavy machinery) to verify, before permitting an individual to drive a vehicle of the fleet, whether the intended driver is capable of driving. The verification in such a case should be quick in order to be commercially viable (and in some cases, to be safe). Nevertheless, since the verification process in such a scenario takes place prior to the beginning of the drive (and thus, without being subjected to BDEs resulting from the motion of the drive), the balance destabilizing event may in such cases be triggered intentionally by the system (e.g., using video content). In another example, such systems, methods, and computer program products may be used is for fleets managers (for any suitable type of vehicles, such as cars, trucks, scooters, heavy machinery) to verify, during driving, that a person is available to keep driving the vehicle, or is ready to take control of the vehicle if needed to. In such cases, the system may optionally passively use BDEs occurring naturally during the driving, without using any resources for generating BDEs, and withoutunnecessarily interfering with the usual experience of the person or other passenger. Optionally, the determining of the PIC may be implemented more cheaply, accurately, require less computational power, and be more individual friendly than before. Furthermore, the collection of data may optionally be done without any dedicated sensors (e.g., using a preinstalled camera, steering wheels sensors, or any other sensors which are already being installed for other uses). It is nevertheless noted that dedicated sensors and / or dedicated user interfaces may also be implemented if needed.

[0028] According to an aspect of the invention, there is disclosed a postural control assessment system, postural control assessment the system including: (a) a hardware communication channel, for providing to a processor sensor -based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; (b) at least one processor; and (c) at least one memory including computer program code. The at least one memory and the computer program code are configured, with the at least one processor, to cause the system to at least: (i) obtain timing information of a balance destabilizing event within the measurement time span; (ii) identify in the kinematic data kinematic fluctuation patterns of stability compensation movements following the balance destabilizing event; and (iii) process the kinematic fluctuation patterns to determine a postural instability condition of the individual.

[0029] According to a further aspect of the invention, the system may further include at least one sensor selected from the group consisting of: a camera, an accelerometer, a RADAR, a touch screen, and a joystick, wherein the sensor-based kinematic data is based on data collected by the at least one sensor.

[0030] According to a further aspect of the invention, the balance destabilizing event may be a non-kinetic stimulus affecting at least one of visual perception and auditory perception of the individual.

[0031] According to a further aspect of the invention, the processor and the computer program code may be configured to determine the timing of the balance destabilizing event by analyzing the sensor-based kinematic data.

[0032] According to a further aspect of the invention, the processor and the computer program code may be configured to determine the timing of the balance destabilizing event by analyzing sensor data of a vehicle in which the individual is located.

[0033] According to a further aspect of the invention, the processor and the computer program code may be operable to determine a cognitive operational state of the individual by processing the kinematic fluctuation patterns.

[0034] According to a further aspect of the invention, the processor and the computer program code may be configured to: (i) identify in the kinematic data patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the user; (ii) identify within the patterns abnormal features reflecting abnormality of the patterns; and (iii) assess postural stability of the individual based on the identified abnormal features.

[0035] According to a further aspect of the invention, the processor and the computer program code may be further configured to selectively restrict operational conditions of a machine supervised by the individual based on the determined postural instability condition.

[0036] According to a further aspect of the invention, the system may be configured to manipulate at least one of the individual and an environment of the individual, for mitigating a physiological condition associated with the postural instability condition, based on the determining of the postural instability condition.

[0037] According to a further aspect of the invention, the processor and the computer program code may be configured to determine the postural instability condition at least partly based on decision model which is agnostic to historical performance information of the individual.

[0038] According to a further aspect of the invention, the processor and the computer program code may be configured to process the kinematic fluctuation patterns for determining the postural instability condition of the individual at least partly in response to a degree of correlation between an intensity of the BDE and an intensity of associated postural correction sub-movements.

[0039] According to an aspect of the invention, there is disclosed a vehicle, the vehicle including: (a) an engine operable to provide power for propelling the vehicle; (b) an individual controllable steering mechanism for controllably changing a propagation direction of the vehicle; (c) input user interface for detecting individual instructions for modifying a behavior of at least one module out of the engine and thesteering mechanism; (d) the postural control assessment system according to any one of the previous paragraphs; and (e) a Vehicle Control Authorization Module (VCAM) operable to selectively prevent controlling of performance of the at least one module by the input user interface based on the PIC determined by the postural control assessment system.

[0040] According to an aspect of the invention, there is disclosed a method for postural control assessment, the method including: (a) receiving, over at least one hardware communication channel, sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; (b) obtaining timing information of a balance destabilizing event within the measurement time span; (c) identifying in the kinematic data kinematic fluctuation patterns of stability compensation movements of the individual following the balance destabilizing event; and (d) processing the kinematic fluctuation patterns by implementing temporal data-pattern analysis to determine a postural instability condition (PIC) of the individual.

[0041] According to a further aspect of the invention, the balance destabilizing event may be a non-kinetic stimulus affecting at least one of visual perception and auditory perception of the individual.

[0042] According to a further aspect of the invention, the obtaining may include detecting the timing of the balance destabilizing event based on analysis of the sensor-based kinematic data.

[0043] According to a further aspect of the invention, the obtaining may include detecting the timing of the balance destabilizing event based on analysis of sensor data of a vehicle in which the individual is located.

[0044] According to a further aspect of the invention, the determining may include determining a cognitive operational state of the individual.

[0045] According to a further aspect of the invention, the determining may include determining that the individual is posturally instable.

[0046] According to a further aspect of the invention, the identifying may include identifying patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual, and identifying within the patternsabnormal features reflecting abnormality of the patterns; wherein the processing includes assessing postural stability of the individual based on the identified abnormal features.

[0047] According to a further aspect of the invention, the identifying may include identifying a pattern which reflects at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual; wherein the processing includes defining a multitude of brief intervals within a duration of the identified pattern, separately processing the kinematics motion of the at least one body part in each of the multitude of brief intervals, and assessing the postural stability of the individual based on the results of the plurality of brief-interval kinematic analysis processes.

[0048] According to a further aspect of the invention, the method may further include preventing operation by the individual of at least one system based on the determining of the postural instability condition.

[0049] According to a further aspect of the invention, the method may further include restricting operational conditions of a machine supervised by the individual based on the determining of the postural instability condition.

[0050] According to a further aspect of the invention, the method may further include triggering manipulation to at least one of the individual and an environment of the individual, for mitigating a physiological condition associated with the postural instability condition, based on the determining of the postural instability condition.

[0051] According to a further aspect of the invention, the determining of the postural instability condition may be based on decision model which is agnostic to historical performance information of the individual.

[0052] According to a further aspect of the invention, the processing of the kinematic fluctuation patterns to determine the postural instability condition of the individual may be responsive to a degree of correlation between an intensity of the BDE and an intensity of associated postural correction sub-movements.

[0053] According to a further aspect of the invention, the processing may include determining the PIC based on the behavior of a kinematic parameter of an individual movement over time.

[0054] According to a further aspect of the invention, the method may include detecting transient PICs selected from the group consisting of tiredness and intoxication.

[0055] According to an aspect of the invention there is disclosed a non-transitory computer-readable medium for assessing a postural instability condition of an individual, including instructions stored thereon, that when executed on a processor, perform the steps of: (a) receiving, over at least one hardware communication channel, sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; (c) obtaining timing information of a balance destabilizing event within the measurement time span; (c) identifying in the kinematic data kinematic fluctuation patterns of stability compensation movements of the individual following the balance destabilizing event; and (d) processing the kinematic fluctuation patterns by implementing temporal data- pattern analysis to determine a postural instability condition (PIC) of the individual.

[0056] According to a further aspect of the invention, the balance destabilizing event may be a non-kinetic stimulus affecting at least one of visual perception and auditory perception of the individual.

[0057] According to a further aspect of the invention, the instructions for obtaining may include detecting the timing of the balance destabilizing event based on analysis of the sensor-based kinematic data.

[0058] According to a further aspect of the invention, the instructions for obtaining may include instructions for detecting the timing of the balance destabilizing event based on analysis of sensor data of a vehicle in which the individual is located.

[0059] According to a further aspect of the invention, the instructions for determining may include instructions for determining a cognitive operational state of the individual.

[0060] According to a further aspect of the invention, the instructions for determining may include instructions for determining that the individual is posturally instable.

[0061] According to a further aspect of the invention, the instructions for identifying may include instructions for identifying patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual, and for identifying within the patterns abnormal features reflecting abnormality of thepatterns; wherein the processing may include assessing postural stability of the individual based on the identified abnormal features.

[0062] According to a further aspect of the invention, the instructions for identifying may include instructions for identifying a pattern which reflects at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual; wherein the instructions for processing may include instructions for defining a multitude of brief intervals within a duration of the identified pattern, instructions for separately processing the kinematics motion of the at least one body part in each of the multitude of brief intervals, and instructions for assessing the postural stability of the individual based on the results of the plurality of brief-interval kinematic analysis processes.

[0063] According to a further aspect of the invention, the computer-readable medium may further include instructions for preventing operation by the individual of at least one system based on the determining of the postural instability condition.

[0064] According to a further aspect of the invention, the computer-readable medium may further include instructions for restricting operational conditions of a machine supervised by the individual based on the determining of the postural instability condition.

[0065] According to a further aspect of the invention, the computer-readable medium may further include instructions for triggering manipulation to at least one of the individual and an environment of the individual, for mitigating a physiological condition associated with the postural instability condition, based on the determining of the postural instability condition.

[0066] According to a further aspect of the invention, the instructions for determining of the postural instability condition may be based on decision model which is agnostic to historical performance information of the individual.

[0067] According to a further aspect of the invention, the instructions for processing of the kinematic fluctuation patterns to determine the postural instability condition of the individual may be responsive to a degree of correlation between an intensity of the BDE and an intensity of associated postural correction sub-movements.

[0068] According to a further aspect of the invention, the instructions for processing may include instructions for determining the PIC based on the behavior of a kinematic parameter of an individual movement over time.BRIEF DESCRIPTION OF THE DRAWINGS

[0069] In order to understand the invention and to see how it may be carried out in practice, embodiments will now be described, by way of non-limiting examples only, with reference to the accompanying drawings, in which:

[0070] Figs. 1A and IB are functional block diagrams illustrating examples of postural control assessment systems, in accordance with the presently disclosed subject matter;

[0071] Fig. 2 illustrates an example of a postural control assessment system and an individual, in accordance with examples of the presently disclosed subject matter;

[0072] Fig. 3 is a flow chart illustrating a method for postural control assessment, in accordance with examples of the presently disclosed subject matter;

[0073] Fig. 4 illustrates a sub-method for identifying submovements of one or more body parts of the individual following the BDE based on processing of the kinematic data, in accordance with examples of the presently disclosed subject matter;

[0074] Figs. 5A and 5B include charts of kinematic data collected when the respective individual is in different PICs and at different degrees of stability, in accordance with examples of the presently disclosed subject matter; and

[0075] Fig. 6 illustrates four diagrams illustratively demonstrating different ways of defining a plurality of movement instances in the kinematic data.

[0076] Fig. 7 illustrates an example of kinematic data and analysis of motion patterns in that kinematic data, in accordance with examples of the presently disclosed subject matter.

[0077] It will be appreciated that for simplicity and clarity of illustration and description, certain elements in the figures may not have been drawn to scale. This could include the exaggeration of certain element dimensions relative to others.Additionally, corresponding or analogous elements may be identified using repeated reference numerals in the figures.DETAILED DESCRIPTION OF EMBODIMENTS

[0078] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the invention. While specific details are provided to enable a thorough understanding of the invention, those skilled in the art will appreciate that the invention may be practiced without these details. Additionally, well-known methods, procedures, and components are not described in detail to avoid obscuring the invention. Finally, any reference to a method, system, or non-transitory computer readable medium should be interpreted as including related aspects of the invention.

[0079] The terms “computer”, “processor”, and “controller” should be expansively construed to cover any kind of electronic device with data processing capabilities, including, by way of non-limiting example, a personal computer, a server, a computing system, a communication device, a processor (e.g. digital signal processor, DSP), a microcontroller, a field programmable gate array (FPGA), cloud computing server, an application specific integrated circuit (ASIC), a smartphone, an electronic control unit (ECU) of a vehicle, an and so on. Unless stated otherwise, the terms “computer”, “processor”, and “controller” may also include a combination of several modules (e.g., several central processing units, CPUs), which operate together toward a goal. Unless specifically stated otherwise, as apparent from the following discussions, it is appreciated that throughout the specification discussions utilizing terms such as "processing", "calculating", “computing”, "determining", "generating", “setting”, “configuring”, “selecting”, “defining”, or the like, include actions and / or processes of a computer that manipulate and / or transform data into other data. That data is represented as physical quantities, e.g., such as electronic or electromagnetic quantities, and / or said data representing physical objects.

[0080] It is appreciated that certain features of the presently disclosed subject matter, which are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, various features of the presently disclosed subject matter, which are, for brevity, described in the context of asingle embodiment, may also be provided separately or in any suitable subcombination. In embodiments of the presently disclosed subject matter one or more steps illustrated in the figures may be executed in a different order and / or one or more groups of steps may be executed simultaneously. The figures illustrate a general schematic of the system architecture in accordance with an embodiment of the presently disclosed subject matter. Each module in the figures can be made up of any combination of software, hardware and / or firmware that performs the functions as defined and explained herein. The modules in the figures may be centralized in one location or dispersed over more than one location.

[0081] Any reference in the specification to a method should be applied mutatis mutandis to a system capable of executing the method. Any reference in the specification to a method which can be executed by a computer should be applied mutatis mutandis to a non-transitory computer readable medium that stores instructions that once executed by a computer result in the execution of the method. All the details, variations, optional features, optional steps which are discussed with respect to a system are also applicable, mutatis mutandis, to such a corresponding method (and non-transitory computer readable medium, where applicable), and vice versa.

[0082] Fig. 1A is a functional block diagram illustrating an example of postural control assessment system 200 (also referred to as “system 200”), in accordance with the presently disclosed subject matter. System 200 is used to assess postural control of one or more subjects of the system for which sensor-based kinematic data is collected following a balance destabilizing event (DBE). System 200 may optionally be used for assessing a cognitive state of the subject (e.g., fatigue, intoxication), a physiological postural instability of the subject (e.g., due to dizziness, vertigo, epileptic seizure, motion sickness, or an impending seizure as indicated by the presence of a prodrome or aura), or both. System 200 may be used for assessing postural control in humans, animals, or both.

[0083] Postural control assessment system includes processor 220 for assessing sensor based kinematic data received via one or more communication channels 212 of system 200. The sensor based kinematic data is based on information collected by one or more sensors 210, and may include raw and / or processed sensor data. The sensorbased kinematic data may be received directly from the respective one or more sensors 210, but it may also be preprocessed by another system (e.g., by a computer installed in a vehicle in which system 200 operates, if applicable). The kinematic data received over the at least one communication channel 212 is indicative of kinematic parameters of at least one body part of the individual at different times (e.g., eyes, head, torso, hands, thighs, lungs). While not necessarily limited to such values, the kinematic data is especially indicative to the kinematic parameters of the at least one body part following a DBE. Communication channels 212 may be wired or wireless, depending for example on the nature of the sensors 210 and their proximity to a processor 220 of system 200. Optionally, communication channels 212 may provide for continuous communication with the sensors 210 (and / or with the pre-processing intermediary system, where applicable); alternatively (or additionally), ad-hoc communication may be used. Sensors 210 themselves may be part of system 200, or they may be external thereto, depending on the particular application of system 200. Regardless of the nature of sensors 210 or the communication channels 212 used to receive information from them, system 200 is designed to process and analyze the sensor based kinematic data, and to use that data to drive actionable insights and decisions. Optionally, communication channels 212 may be designed to enable the transfer of the sensor based kinematic data in real-time, ensuring that the information received is accurate and up to date. Optionally, system 200 may be designed to be flexible, allowing for the integration of additional sensors or modification of existing sensors as required. The communication channels can be customized to meet the needs of the application, and may be adapted to accommodate different types of sensors and data formats. It is noted that any suitable type of sensor 210 may be implemented for detecting kinematic information pertaining to one or more body parts of the individual. Some examples of types of sensors for sensor 210 which may be used to detect the kinematic parameters include: a. Inertial measurement units (IMUs): These sensors use accelerometers, gyroscopes, and magnetometers to measure the acceleration, angular velocity, and orientation of the body. b. Pressure sensors: These sensors are placed under the feet or on a platform to measure the distribution of weight across the body.c. Electromyography (EMG) sensors: These sensors measure the electrical activity of muscles to detect muscle activity and movement patterns. d. Opto-electronic sensors: These sensors use a combination of infrared and laser technology to measure the movement and position of body parts. e. Video-based sensors: These sensors use cameras to capture and analyze the movement of the body in three-dimensional space. f. Radar: can be used for monitoring the movement and positioning of the body (e.g., speed and direction of movement). g. Doppler sensor: can be used for measuring the speed and direction of movement using sound waves to detect changes in the movement of the body.

[0084] For example, system 200 may utilize (and optionally include) one or more sensors 210 selected from the group consisting of: a camera, an accelerometer, a gyroscope, a RADAR, a touch screen, a joystick, gyroscope, and magnetometer.

[0085] It is noted that processor 220 may further utilize data pertaining to the individual, such as body position (e.g., whether the individual is standing, or sitting), level of mobility (of the individual as a whole, or of one or more parts of the individual), and so on.

[0086] Reverting to processor 220 (which may include any combination of one or more of: hardware, firmware, and software components), it is noted that processor 220 is coupled to at least one memory module 250 which includes computer program code. The at least one memory module 250 may also store any other data required for the operation of processor 220 and / or of any other component of system 200, such as measurement data, analysis data, processing results, decisions, and so on. The at least one memory module 250 may store the computer program code and any optional additional data in any suitable technology, such as (but not limited to): volatile memory (e.g., random access memory or RAM), non-volatile memory (e.g., read-only memory or ROM, flash memory, magnetic storage devices), optical storage devices (e.g., CD- ROM, DVD), and emerging memory technologies (e.g., ferroelectric RAM, phasechange memory). The at least one memory module 250 and the computer program code are configured, with the at least one processor 220, to cause system 200 todetermine a cognitive state of the user based on motion patterns of a body potion of an examined user, as discussed below. Whenever processor 220 is discussed below as carrying any action or being operable to perform any action, the execution of such action may be based on a computer program code stored in the at least one memory module 250. Together with the at least one memory module, at least one processor 220 is configured to: a. Obtain timing information of a balance destabilizing event within the measurement time span. A balance destabilizing event (BDE) is an event which is expected to destabilize the subject, such as an abrupt impulse or thrust (e.g., abrupt movement of a vehicle used by the subject), sudden change in visual input presented to the subject (e.g., video), step detection of a steps meter, and so on. The timing information could indicate a beginning and / or the ending of the balance destabilizing event, its duration, timing of its peak movement, and so on. Optionally, the processor may obtain additional information pertaining to the BDE (such as magnitude, direction of thrust, etc.) which may be used in later computations by a processor, e.g., in its computation of the postural control of the subject, of the cognitive state of the subject, and / or of the physiological postural instability of the subject. Optionally, the processor may be configured to determine the timing of the balance destabilizing event by analyzing the sensor based kinematic data. Optionally, the processor may be configured to determine the timing of the balance destabilizing event by analyzing sensor data of a vehicle in which the individual is located, from a phone or another handheld device held by the individual, and so on. Optionally, the processor may obtain the timing information from a system which provides to the individual manmade data (such as video, scenarios created in the augmented reality, virtual reality data). b. Identify in the kinematic data a plurality of kinematic fluctuation patterns of stability-compensation movements following the balance destabilizing event. Further details regarding ways in which processor 220 may process the kinematic data to identify kinematic features of stability compensationmovements (e.g., kinematic fluctuation patterns of compensation submovements or other types of movements of the body part) are discussed below with respect to system 200 and to method 500. An example of a type of movements whose kinematic fluctuation patterns may be analyzed include stability compensation submovements, which are submovements of one or more body parts of the subject during a principal movement of the subject in which the subject (as managed by the brain of the subject) tries to compensate for its destabilization during the BDE (e.g., a sudden loss of balance). As discussed below in greater detail, the identification of kinematic features such as kinematic fluctuation patterns may be preceded by different stages of preprocessing of the kinematic data (by processor 220 or by other processing systems) which are intended to improve the kinematic data (e.g., remove noise, clutter) before the actual processing. c. Process the kinematic features (e.g., the kinematic fluctuation patterns) to determine a postural instability condition (PIC) of the individual. Within the context of the present disclosure, the phrase “postural instability condition” denotes a state of the individual characterized by the compromised ability of the individual to maintain or regain stable body posture or balance. This PIC may arise due to factors including, but not limited to, muscular fatigue, impaired cognitive or sensory function, neurological disorders, neurological events, or the influence of external substances. Some examples include fatigue, intoxication, and epileptic seizures. PICs of different durations may be determined (e.g., temporary, prolonged, and / or permanent). The determining of the PIC may be based on kinematic data following one BCE, but in some cases data of multiple BCEs may be used for the determining of the PIC. It is noted that in some scenarios (e.g., driving over an unpaved road or if triggered by the system), many BCEs may occur in a relatively short time. In some cases, a later BCE and at least a part of the response of the individual to that BCE may occur while the individual is still coping with the loss of balance resulting from a previous BCE.

[0087] Within the context of the present disclosure, the system may optionally be used to detect postural instability conditions which limit an ability of an individual to perform an activity which the individual is otherwise capable of performing (e.g., driving a car, operating a machine, babysitting a child, perceiving video context). Such PIC may include cognitive states such as (but not limited to): tiredness, drowsiness, fatigue, distraction, confusion, stress, anxiety, intoxication, acute physical condition, exhaustion, attention withdrawal, inattention, neurodegenerative disorders, movement-related ailments, synaptic dysfunction conditions, basal ganglia-related disorders, motor system pathologies, and other factors that could impair the cognitive abilities of the individual. It should be noted that a system or a method developed in accordance with the teaching of the present invention may optionally detect only some of these exemplary cognitive states, or even none (instead detecting other cognitive states or other types of PIC). The PICs which are detectable by the present invention are characterized by distinctive corresponding brain states of the individual, which cause the individual to act in a detectably distinct fashion (e.g., having distinct motor abilities).

[0088] Reverting to the one or more communication channels 212 of system 200, which are used for receiving sensor based kinematic data which is based on information collected by one or more sensors 210. The sensor based kinematic data may be received directly from the respective one or more sensors 210, but may also be preprocessed by another system (e.g., by a computer installed in the vehicle in which system 200 operates). The kinematic data received over the at least one communication channel 212 is indicative of kinematic parameters of at least one body part of the individual at different times following the BCE (e.g., eyes, hands, thighs, lungs). Communication channels 212 may be wired or wireless, e.g., depending on the nature of the sensors 210 and their proximity to a processor 220 of system 200. Optionally, communication channels 212 may provide for continuous communication with the sensors 210 (and / or with the pre-processing intermediary system); alternatively (or additionally), ad-hoc communication may be used.

[0089] Any of the one or more sensors 210 used may be part of system 200, or may be external thereto, depending on the particular application of system 200. Regardless of the nature of sensors 210 or the communication channels 212 used to receiveinformation from them, system 200 is designed to process and analyze the sensor based kinematic data, and to use that data to drive actionable insights and decisions. Optionally, communication channels 212 may be designed to enable the transfer of the sensor based kinematic data in real-time, ensuring that the information received is accurate and up to date. Optionally, system 200 may be designed to be flexible, allowing for the integration of additional sensors or modification of existing sensors as required. The communication channels can be customized to meet the needs of the application, and may be adapted to accommodate different types of sensors and data formats. The information received from the sensors can be analyzed and processed by the system in order to provide useful insights and inform decision-making. Overall, the system provides a powerful tool for monitoring and analyzing data from a range of different sources, allowing for more informed and efficient decision-making in a variety of applications. It is noted that any suitable type of sensor 210 may be implemented for detecting kinematic information pertaining to one or more body parts of the individual. For example, system 200 may utilize (and optionally include) one or more sensors 210 selected from the group consisting of: a camera, an accelerometer, a gyroscope, a RADAR, a touch screen, a joystick, gyroscope, and a magnetometer.

[0090] Reverting to processor 220, it is noted that processor 220 is operable to receive — over at least one hardware communication channel 212 — sensor based kinematic data, to process that kinematic data to identify various movements of the individual following one or more BCEs, and to determine a PIC of the individual based on analysis of the movements. Following the determining of the PIC, processor 220 may optionally proceed to take any suitable action, e.g., depending on the type of system or its objective. For example, processor 220 may proceed with any one or more of the following actions: a. Triggering a message to the individual, to another person or another system, indicative of the determined PIC (e.g., “intoxication detected”), on the meaning or the implications of the determined cognitive state (e.g., “please reduce your speed to under 40km / h”), and so on; b. Triggering an action which affects the individual or an environment of the individual (e.g., triggering emission of breathable materials for awakening the individual);c. Triggering an action which affects a machine operated by the individual or operable by the individual (e.g., slowing down of a car in which the individual travels, limiting the options in which the individual can control a computerized and / or mechanical system, up to preventing use of such a system by the individual), and so on.

[0091] Referring to the aforementioned kinematic data, this is a data being indicative of kinematic parameters of at least one body part of the individual at different times following the one or more BCE (and possibly at other times as well). Kinematic parameters are parameters which are indicative of movement of the respective body part, and may include, for example, locations at different times, velocities (e.g., vector, or absolute value), accelerations (e.g., vector, absolute values), higher degree derivatives, as well as relative locations, relative velocities, relative accelerations, or higher derivatives of relative parameters which pertain to the relationship between different body parts. It is noted that optionally, the kinematic data may pertain to the same one or more body parts which are used for controlling the vehicle or other machine operated by the individual, if any. However, processor 220 may optionally utilize for its decisions kinematic data which pertains to another body part. The kinematic data may be collected by one sensor or by a plurality of sensors of one or more types (e.g., two pressure sensors, or a camera and a touchscreen sensor). Optionally, dynamical quantities which are indicative of kinematic parameters may be measured, such as measurement of forces or pressures applied by one or more body parts of the individual on a sensor (directly or indirectly). For example, one or more force sensors (e.g., a load cell) and / or pressure sensors may be installed within a chair or a seat on which the individual sits (e.g., a car seat), and the kinematic movements of the individual may be measured by such sensors.

[0092] It is noted that the processing may focus on identifying movements and / or motion patterns of the individual that follow the at least one BCE, and may include differentiating and / or comparing between movements and / or motion patterns which occur before such one or more BCEs to movements and / or motion patterns which occur after such a BCE (all during the performance of the task by the individual). Further information pertaining to the use of movements and / or motion patterns information for determining PICs is provided below (e.g., as part of the discussion ofmethod 500 below). Such ways of implementing movements and / or motion patterns information for determining PICs as provided below may be incorporated to system 200, mutatis mutandis.

[0093] As discussed throughout this disclosure, the disclosed technologies for assessing a PIC of the individual, and for controlling access to various assets (e.g., vehicles, machines, computerized systems) based on such determination of PIC may be implemented in many different fields. In such cases, system 200 may optionally be associated with, connected with, included in, including of, or having another relationship with the system, vehicle, machine, or space whose control (and / or access thereto) depends on the determination of the PIC. For example, system 200 may be a vehicle which further includes: (a) an engine operable to provide power for propelling the vehicle, (b) an individual controllable steering mechanism for controllably changing a propagation direction of the vehicle, and (c) input user interface for obtaining individual instructions for modifying a behavior of at least one module out of the engine and the steering mechanism. Such user interface may be manual (e.g., steering wheel, pedals), computerized (e.g., cruise control, navigation software, driving mode such as sport, comfort, or economic), or any other suitable user interface. Processor 220 in such a case may be operable to selectively prevent controlling of performance of the at least one respective module (engine or steering mechanism) by the input user interface, based on the determined PIC.

[0094] System 200 may optionally be any individual controllable machine (e.g., printing press, crane, Remote Control Station (RCS) from which the individual remotely pilots an Unmanned Aerial Vehicle, robotic surgery systems, prosthetic limbs, exoskeletons, construction equipment, remotely operated underwater vehicles (ROVs), air traffic control systems, 3D printers, CNC machines, telepresence robots, agricultural machinery, laboratory equipment, power station controls, mining equipment, remote bomb disposal robots, rail transport control systems, amusement park rides, warehouse automation systems, textile machinery, food processing equipment, chemical plant control systems, and so on), as long as such machine includes an individual controllable mechanism for controlling operation of the respective machine (be it mechanical, electric, electronic, software, or any other suitable form of control mechanism), and an user interface for obtaining individualinstructions for controlling a behavior the aforementioned mechanism, where the controlling granted to the individual of the respective mechanism via the user interface is subject to processor decisions of the PIC (e.g., similar to the vehicle example, mutatis mutandis).

[0095] In another example, system 200 may be a safe which further includes: (a) a compartment in which valuables or other items may be stored, (b) a door or other latch for granting access to the compartment, (c) a lock which selectively disable opening of the door, (d) user interface for unlocking the lock, such as keypad or fingerprint detector. Processor 220 in such a case may be operable to selectively prevent unlocking (or, possibly, locking) of the safe by the user interface, based on the PIC determined by processor 220. Similar principles of operation may be applied, for example, for unlocking a smartphone, a computer, or access to any other computerized system, mutatis mutandis.

[0096] It is noted that while processor 220 was discussed above as a part of a larger system 200 (which also include communication channel 212 and possibly additional components), it is possible to plan, manufacture, sell, and promote processor 220 independently of such other components. For example, processor 220 may be offered as a standalone computer chip which may be later integrated into a system (e.g., a vehicle) which already include such additional components, or used with a set of sensors and / or user interface components which are selected by the client, based on the client’s needs. Furthermore, as discussed below in greater detail, it is possible to implement capabilities of processor 220 as a computer readable computer code, and install this code (e.g., from a tangible storage medium such as a memory stick or hard drive, or via an online connection) to such a “host system”. Such a computer executable code may include any functionality discussed above with respect to system 200 (and especially to processor 220), as well as any step or variations of method 500 discussed below.

[0097] Optionally, system 200 may include a PIC-gated access authorization module (e.g., as part of processor 220, or as an independent module) which is operable to selectively grant users control of a requested system based on the assessment of the postural instability condition. It is noted that the granting of the control of the requested system (e.g., vehicle, machine, computerized system) may be independent of thesuccess level of the individual at recovering from the BCE. That is, the individual may take a long time to recover from the BCE (e.g., due to interference, injury, etc.) and be granted access if the determined PIC is suitable for operating the requested system. On the other side, the individual may recover from the BCE relatively quickly, but the analysis of the corrective submovement of the individual during that successful recovery from the BCE may indicate that the individual is in a PIC which is not suitable for the operation of the requested system, and access would be denied.

[0098] For example, the PIC-gated access authorization module may be configured to: (a) permit control by the individual of the requested system in response to determination of the PIC which is based on kinematic data of a recovery of the individual from one or more BCEs, (b) repeating the stages of receiving, processing, and determining to determine a second PIC of the individual based on other kinematic data of a recovery of the individual from one or more other BCEs of similar magnitude (e.g., of similar thrust, impact), wherein the average recovery time from the one or more other BCEs is at least twice faster than the average recovery time from the at least one earlier BCEs, and (c) preventing control by the individual of the requested system in response to the determination of the second PIC.

[0099] As discussed in greater detail below, some or all of the processing by processor 220 (or other modules such as the aforementioned PIC-gated access authorization module) may be agnostic of individual history and / or private data. For example, optionally processor 220 may be configured to determine the PIC of the individual without accessing historical performance information of the individual.

[0100] As noted in this disclosure, the one or more sensors 210 may be dedicated for system 200, but may also be shared with another system. Especially, the sensors 210 may optionally be used by the individual to control a system to which access is selectively restricted by system 200. Optionally, sensors 210 may be further used to receive individual instructions for operating of a machine to which access is selectively granted by the system based on the determined PIC. For example, one or more of the at least one sensor 210 whose data is used by system processor 220 may be a sensor of an Electronic Throttle Control (ETC) or Drive-By-Wire (DBW) system of a car (e.g., an Accelerator Pedal Position (APP) sensor which send a signal to the Engine Control Module (ECM) or Powertrain Control Module (PCM) to indicate the driver'sdesired throttle opening may also be used to detect corrective submovement of the leg of the individual).

[0101] Fig. IB is a functional block diagram illustrating an example of system 200, in accordance with the presently disclosed subject matter. Optionally, processor 220 may include sensor interface module 221 for receiving the sensor based kinematic data over the at least one hardware communication channel 212 from the one or more sensors 210. Sensor interface module 221 may also be used for receiving and transmitting additional information between the one or more sensors 210 and other parts of processor 220, such as instructions, functional data, and so on. Optionally, sensor interface module 221 (or another component of processor 220 or system 200) may control the operation of one or more of the at least one sensor 210, fully or partly.

[0102] Optionally, processor 220 may include memory interface module 222 for receiving and / or transmitting data from the at least one memory module 250. Such data may include, for example, detection data, kinematic data, processing data, temporary files and storage, computer code instructions, and any other types of data, whether digital or analogue. Optionally, memory interface module 222 (or another component of processor 220 or system 200) may control the operation of one or more of the at least one memory module 250, fully or partly.

[0103] Optionally, processor 220 may include user interface controller 223 which is operable to monitor and / or control operation of an optional user output interface 230 and / or an optional user input interface 240. Especially, user interface controller 223 may be operable to trigger changes in the operations of any of the aforementioned user interfaces 230 and 240.

[0104] Optionally, processor 220 may include bus 224 or any other suitable means of internal communication, for facilitating communication between the different modules of processor 220.

[0105] Optionally, processor 220 may include motion analysis module 225, operable to execute any one or more of the following: process sensor-based kinematic data, characterizing motion patterns of the at least one body part, identify motions and / or patterns associated with loss of balance, identifying in the kinematic data kinematic fluctuation patterns of stability compensation movements of the individual that follow (and possibly result from the balance destabilizing event), identifying submovement,identifying corrective submovements, analyzing submovements, analyzing corrective submovements and so on. It is noted that processor 220 (e.g., motion analysis module225 of processor 220) may be operable to identify, processes, and analyze either movements of the individual which occur as direct result of the BDE (e.g., when the analyzed body part moves due to an impulse resulting from the BDE) and / or movements of the individual which occur as result of attempts of the individual to regain balance following the aforementioned initial movement.

[0106] Optionally, processor 220 may include cognitive state assessment module226 that is operable to process the kinematic fluctuation patterns by implementing temporal data-pattem analysis to determine a postural instability condition (PIC) of the individual and / or otherwise operable to determine a cognitive state of the user based on the any one or more of the aforementioned outputs of motion analysis module 225.

[0107] Optionally, processor 220 may include cognitive state-gated access authorization module 227, is operable to selectively grant users control of a requested system (e.g., a vehicle, a computer, a printing press) based on cognitive state assessment. Cognitive state-gated access authorization module 227 in such case may optionally be configured to: (a) permit control by the user of the requested system in response to determination of the cognitive state which is based on kinematic data collected during performance of the task by the user at a first success level, (b) repeat the steps of receiving, processing, and determining to determine a second cognitive state of the user based on other kinematic data collected during performance of a second task by the user at a second success level that is higher than the first success level; and (c) prevent control by the user of the requested system in response to the determination of the second cognitive state.

[0108] Processor 220 may include any combination of one or more of the aforementioned optional components (221, 222, 223, 224, 225, 226, and 227). Additionally, additional modules may be implemented to implement any other functionality, such as any functionality discussed below with respect to processor 220 and with respect to method 500.

[0109] Fig. 2 illustrates system 200 and an individual, in accordance with examples of the presently disclosed subject matter. In the illustrated example, the individual isdriving a vehicle, but it is noted that system 200 and the methods below may be implemented in any scenario in which the kinetic response of an individual to BCE may be measured. Optionally (e.g., as exemplified in the diagram), sensors 210 may be connected to the processor via wired or wireless means, directly or indirectly (e.g., via a server, communication bus, cloud, intermediary system, etc.), in any suitable way. The at least one or more sensors may be located in any one or more locations such as (but not limited to): on the body or clothing of the individual, otherwise carried, worn, or touched by the individual, integrated into a system within or next to which the individual is located, integrated into a system which is at least partly controlled by the individual, and so on.

[0110] In an example use of system 200, a vehicle is provided (e.g., a car, a motorcycle, a scooter, a truck, an ambulance, a police car, a plane, a ship, a boat, etc.), which includes: (a) an engine operable to provide power for propelling the vehicle, (b) an individual controllable steering mechanism for controllably changing a propagation direction of the vehicle, (c) an input user interface for detecting individual instructions for modifying a behavior of at least one module out of the engine and the steering mechanism (e.g., a steering wheel, a pedal, a control stick of an airplane), (d) postural control assessment system 200, and (d) a Vehicle Control Authorization Module (VC AM) operable to selectively prevent controlling of performance of the at least one module by the input user interface based on the PIC determined by the postural control assessment system. The VCAM may optionally be or include any combination of any one or more of the following: processor 220, one or more processor of the vehicle, a processor of a portable unit such as a smartphone or a dedicated remote-control unit, or any other suitable component. Examples of input user interface whose operation and / or affect may be controlled by the VCAM include: steering wheel, accelerator pedal, brake pedal, gear shift, turn signal lever, throttle, brake lever, clutch lever, gear shift lever, trim controls, ignition switch, navigation instruments, control column, rudder pedals, flap and spoiler controls, avionics panel, hydraulic controls, ballast controls of a submarine, turret controls of a tank, direction lever of a train, collective lever of a helicopter, and so on.

[0111] Fig. 3 is a flow chart illustrating method 500 for postural control assessment, in accordance with examples of the presently disclosed subject matter. Referring to theexamples set forth with respect to the previous drawings, method 500 may optionally be executed by system 200. Any variation, option, embodiment, or implementation discussed with respect to system 200 may be applied to method 500 (e.g., as a method step), mutatis mutandis. Likewise, any variation, option, embodiment, or implementation discussed with respect to method 500 may be applied to system 200, mutatis mutandis. Method 500 can be executed using any suitable hardware, software, or combination thereof, as may be desired by the individual. This flexibility allows the method to be adapted to a wide range of applications and individual preferences, without sacrificing its core functionality. Furthermore, the method can be easily integrated into existing systems and workflows, making it a highly versatile and user- friendly solution.

[0112] Step 510 of method 500 includes receiving (e.g., over at least one hardware communication channel) sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span. Referring to the examples set forth with respect to the previous drawings, the receiving of step 510 may be executed by processor 220, with the optional assistance of communication channel 212. Different aspects of kinematic data and its collection by one or more sensors are discussed above. The measurement time span may optionally be a predefined time span (e.g., 1 second, 10 seconds, 100 seconds, 10 minutes), e.g., if used to control access of the individual to a resource or when the frequency of BDEs could be estimated. The measurement time span may optionally depend on the number of BDEs for which kinematic data have been recorded (e.g., 10, 20, or 50; for example, optionally a threshold number of events must be analyzed for establishing a good assessment of the PIC). Any suitable option for determining the measurement time spans to suit the specific implementation may be used, and those are just a few examples.

[0113] Step 520 of method 500 includes obtaining timing information of a balance destabilizing event (BDE) within the measurement time span. It is noted that it is also possible to start the measurement time span with the detection of the BDE or shortly after it begins (e.g., if triggered by the system which executes the method), but since the kinematic data should be collected from very shortly after the BDE (e.g., less than a second, less than O.lsec, less than O.Olsec), the BDE is considered within themeasurement time span even if the actual collection of data starts less than a second after the BDE. Different types of timing information may be obtained with respect to the BDE, such as any one or more of the following: its beginning and / or ending time, its duration, its peak time, etc. The timing information may be received as a timestamp (e.g., 10:27:18.022AM), as a notification (e.g., aping), or in any other suitable fashion. Step 520 (or other steps of method 500) may also include receiving additional information which may be used in the determining of the PIC later in method 500, such as parameters relating to the BDE (e.g., accelerator data, kinematic information, magnitude, direction, type), parameters relating to the one or more sensors from which kinematic data is received or other one or more sensors (e.g., temperature sensor, GPS, accelerometer, gyroscope, magnetometer), and so on.

[0114] Referring to the balance destabilizing event, it is noted that any event which destabilizes the individual and whose occurrence and timing are obtainable may be used, whether it is a physical change directly affecting the individual (e.g., a thrust, shaking), stimulus which are perceivable by any one or more senses of the individual (e.g., visually disorienting lights, video, noise, or other sounds), whether originating naturally in the world or applied by a manmade system (e.g., TV monitor, virtual reality (VR) headset). The BDE may occur naturally (e.g., vehicle vibrations), initiated by another system (e.g., braking of an underground mass transit vehicle not anticipated by the system executing method 500), initiated by the respective system (e.g., providing relevant input to a VR headset), initiated by the individual (e.g., hitting the ground while running or walking, climbing stairs, jumping), initiated by another person (e.g., shove, serving a curving ball in a tennis game), or in any other suitable manner. Likewise, any suitable type of balance interrupting influence, stability compromising stimulus, balance impairing disturbance, balance compromising factor, instability inducing event, or balance impairing disturbance may serve as the BDE.

[0115] In some cases, the BDE may be a medium change. Changes in the medium can be changes in direction or speed or jumps of the person himself as a result of the influence of the medium (a person walking down the street during a snowstorm) or a change in direction or speed or jumps of the medium itself (a person sitting in a car). It is noted that in some cases, several BDEs (or medium changes) will occur at the same time (a change of direction together with a jump) or in close temporal proximity.In such a case, the method may pertain to only one of these BDEs (e.g., the first, the strongest), to a subgroup of such grouped or overlapping BDEs (e.g., the first, the strongest, those initiated by the system), or to all of them. The BDE may incorporate a kinematic stimulus of the individual (e.g., a thrust), a non-kinetic stimulus (e.g., affecting the visual perception and / or the auditory perception of the individual), or a combination of kinetic and non-kinetic stimuli. It is noted that the systems and methods disclosed herein may also be applied, mutatis mutandis, to loss of balance which does not result from any specific event, but it rather detectable from the movements or behavior of the individual, or others around him. For example, when someone is sliding on a smooth surface (e.g., wet floor, during inline skating), loss of balance may occur more readily, because maintaining balance on slippery surfaces requires different muscle coordination. The assessment of the PIC in method 500 may be based on information pertaining to the loss of balance in such conditions, to attempts of the individual of regaining the balance following loss of balance, or both.

[0116] Step 540 of method 500 includes identifying in the kinematic data kinematic features and / or kinematic fluctuation patterns of stability compensation movements following the balance destabilizing event. Such stability compensation movements may include corrective submovements as discussed above, but this is not necessarily so. The analyzed movements may not correspond directly to submovements as defined above, and different division of larger movement to smaller parts of analyzable movements may be implemented.

[0117] Step 540 may include identifying kinematic features and / or kinematic fluctuation patterns of stabilizing submovements, corrective submovements, or any other types of movements. For example, the individual may attempt to bring the respective body part whose kinematic parameters are measured to a certain position during the BDE (e.g., attempting to touch a multimedia screen while the car rattles). In such a case, the movement of the body part may include both movements relating to the intentional movement (e.g., corrective submovements relating to the proper execution of the intentional movement), and movements relating to the loss of balance and possibly recovery attempt. Step 540 may optionally include differentiating between different types of movements (e.g., such as those of the examples), but this is not necessarily so.

[0118] Step 540 may include identifying corrective submovements, which are the submovements that occur when the brain of the individual tries to compensate for the sudden loss of balance. It is noted that in the attempt to regain balance, there may be a sequence of many corrective submovement by the individual. The corrective submovement may occur either as result of the BDE (e.g., when the individual handles ongoing thrust applied continuously or in rapid succession) or after the BDE ended, when the individual attempts to restore balance (e.g., once the vehicle returns to straight uninterrupted forward motion). Method 500 (and especially step 540) may take both kinds of such submovements into consideration in the computations.

[0119] Corrective submovements may include, for example, subtle changes in body part angles, angular velocities, and angular accelerations — or their derivatives — that are not visible to the eye. The identifying of stage 540 may be focused on identifying movements (e.g., corrective submovements) following the one or more BDE, but may also include identifying movements (e.g., corrective submovements) prior to such BDE. Such data may be used, by way of nonlimiting example, for comparison or calibration of the post-BDE movements data. Optionally, the identifying of the movements in step 540 may include a preliminary substep of processing the kinematic data (directly, or a preprocessed version thereof) for identifying principal movements (e.g., spanning seconds) and the beginning and ending timing of such principal movement. This substep may then be followed by identifying movements (e.g., submovements) within the time of such larger movements. Some of the ways to carry out step 540 are explored in greater detail with respect to Fig. 4. Any one or more steps of sub-method 540’ may be incorporated, fully or partly, as part of step 540. It should be noted that the movements whose information is used in step 540 are very slight and movements are not visible to the eye. Such slight movements are therefore very different from voluntary movements made by people subject to BDE (e.g., the gross movement of moving one’s arms to shield sensitive body parts from impact of the ground when falling).

[0120] It is noted that step 540 may include defining the individual movements (also referred to as “motion segments”, “motion portions”, “motion instances”, “motion fragments”, depending on the specific implementation) by processing the kinematic data. Any suitable algorithm or technique for defining individual short movementswith the larger primary motion may be used. Depending on the specific implementation, the different movements identified in method 500 (and / or by processor 220) may be strictly non-overlapping movements (e.g., for any given identified movement which ends at time te(n), the following movement starts at ts(n+i)> te(n)), but this is not necessarily so, and overlapping movements (or “motion portions”, “motion instances”, “motion fragments”) may also be optionally identified, processed, and analyzed. The determination of when each individual movement starts and end may be implemented in any suitable manner, such as based on one of the many definitions used in the art for submovements and for corrective submovements; based on predefined heuristic parameters (e.g., crossing of zero by any specific derivative of the motion), based on analysis of usefulness of different decision rules on a training data of different individuals at different PICs, and so on.

[0121] The number of individual movement portions (or “movements”) defined in stage 540 may differ, depending on the specific implementations and its requirements. For example, the number of movements identified may be between 1-3 movements per second, between 2-10 movements per seconds, between 5-50 movements per seconds, and so on. The number of analyzed submovements depends on many factors. For example, number of analyzed submovements may depend on any one or more of the following: an intensity of the loss of posture, a position of the individual at the time of the loss of posture, and the segmentation method used during the operation of the model. It is noted that different movements may be defined in stage 540 to have substantially the same lengths or different lengths, depending on the implementation.

[0122] Some examples of characteristics of large motions that are typically analyzed in the process of using machine learning algorithms to analyze a person's postural balance in order to infer their cognitive state may include: (a) body sway (the amount of movement or instability in a person's body as they stand or walk), (b) step length and width, (c) gait speed (the speed at which a person walks or runs), (d) joint angles (the angles of the joints in a person's body as they move), (e) kinematics of the center of mass, (f) range of motion (the amount of movement or flexibility in a person's joints), and (g) postural stability (the ability of a person to maintain their balance while standing or moving (changes in posture, such as leaning forward or to the side, can be indicative of cognitive state, as they can indicate a lack of balance or stability). Themethods, systems, and computer program products disclosed herein are implemented for much finer movements. It is noted that the stability compensation movements and any other movement identifies, processed and / or analyzed at method 500 (e.g., at steps 540, 550) and by system 200 may occur during such larger movements, especially as a result of the BDE.

[0123] Some examples of large-scale features that are typically analyzed in the process of using machine learning algorithms to analyze a person's motion in order to infer their cognitive state include: (a) acceleration (the rate of change in the person’s velocity over time, often used to measure the intensity of a person's movement), (b) the speed or velocity at which a person is moving (can be used to determine their overall level of activity), (c) displacement (the distance traveled by a person over a given period of time, can be used to measure the overall extent of their movement), (d) the direction in which a person is moving (can be used to determine their intended movement path), (e) frequency (the number of times a person performs a specific movement or activity over a given period of time, can be used to determine the consistency of their motion), (f) duration (the length of time a person spends performing a specific movement or activity, can be used to measure the intensity of their motion), (g) rhythm (the pattern or flow of a person's motion, can be used to determine their level of coordination and control), (h) the amplitude, e.g., height or distance, of a person's motion (can be used to measure the intensity of their movement), (i) the speed of a person's motion (can provide information about their level of arousal or alertness), (j) smoothness of motion (can indicate level of coordination and balance); (k) rhythm of motion (can indicate level of attention and focus of the person), (1) variability of motion (can indicate level of cognitive flexibility), (m) duration of motion (can indicate level of endurance and stamina), (n) range of motion (can indicate level of mobility and flexibility), (o) body posture (can indicate level of relaxation or tension), and (p) gait (can indicate level of stability and balance). The systems, methods, and computer program products disclosed herein do not treat such gross movements or features as the direct subject of processing, but rather identify (or otherwise define or determine) many separate movements (e.g., submovements), as discussed in the context of method 500 and system 200. Each gross movement or motion may be subdivided into several, tens, or hundreds (or more) of individual movements, each of them is processed separately and / or in small subgroups.

[0124] It is noted that the processing of step 540 may be preceded by one or more steps of preprocessing the kinematic data before it is used for the following stages of the method (collectively denoted 530). For example, the obtained kinematic data (or derived parameters derived therefrom, as discussed with respect to sub-method 540’) may be preprocessed to remove noise and outliers. If data from multiple sensors is obtained (or if a single sensor provides multidimensional data), step 530 may also include synchronizing data from different sensors or reducing the number of dimensions in data provided by a single sensor. The preprocessing step 530 may also include feature extraction, which involves selecting relevant features from the raw data that are used for the analysis. The features may include, but are not limited to, body angles, angular velocities, and angular accelerations.

[0125] Step 550 of method 500 includes processing the kinematic features and / or the kinematic fluctuation patterns to determine a postural instability condition (PIC) of the individual. While not necessarily so, the determining of the PIC in step 550 may include determining a cognitive operational state of the individual. While not necessarily so, the determining of the PIC in step 550 may include determining that the individual is posturally instable (e.g., due to motion sickness or other physical PIC).

[0126] The processing of the kinematic features and / or kinematic fluctuation patterns in step 550 may include processing kinematic features and / or kinematic fluctuation patterns of one or more movements (including one or more stability-compensation movement) which occur after (and potentially in response to) one BDE or after a plurality of BDEs. If kinematic features and / or kinematic fluctuation patterns of movements of several BDEs are used, their information may be averaged, aggregated, or processed in any other suitable way.

[0127] It is noted that determining the PIC may yield various types of outputs, depending on the specific aims for which method 500 is used, on the specific capabilities and structure of the system which implemented method 500 (e.g., system 200), and so on. For example, in different implementations some of the different types of outputs which may be provided as a result of determining the PIC include any combination of any one or more of the following: a. A name, title, or description of the PIC (e.g., “nausea”, “intoxication”);b. A class of the PIC (e.g., “impaired cognitive state”, “impaired physiological rebalancing”); c. A level or degree of the PIC (e.g., estimation of alcohol blood concentration, equivalent of Standardized Field Sobriety Test (SFST) level, severeness of seizure); d. Level, degree, or characteristic of the ability of the individual to perform a specific task, a class of tasks, or a class of activities (e.g., “not authorized to drive a vehicle”, “having response time of x0.8 of her usual response time).

[0128] Optionally, step 550 may include identifying unique patterns of movements which are associated with abnormalities of the movement progression (e.g., associated by a computerized model used in method 500, e.g., for carrying out the processing of step 550). Such identifying of unique patterns may be implemented, for example, using machine learning computerized model or heuristic computerized model, or a combination thereof. Such a computerized model may be trained, for example, by parametric manipulation of the specific PIC or PICs of interest. More details about building or training computerized models based on parametric manipulation of PICs are provided throughout the present disclosure.

[0129] For example, training the model to recognize drunkenness may be achieved by letting subjects drink different amounts of alcohol, and training the computerized model to recognize unique movement features for different amounts. Alternatively, training the computerized model to recognize motion sickness may include inducing subjects to different levels of motion sickness and teaching the computerized model to recognize them. When the measurement is made during the induced BDE, there usually is an abnormality in the progress of the movement, which indicates that the brain of the respective subject is trying to brake the movement or stabilize it. For example, the rate of progress of the brain will be slower than usual or its acceleration will break earlier than usual. When the measurement is made after the DBE, attempts to compensate for loss of balance are usually manifested in the data, manifested in movement in an alternative direction to the direction of the change in the medium occurring as part of the BDE.

[0130] Optionally, method 500 may optionally include the following process as part of the identification of the PIC (e.g., the cognitive state). First (e.g., as part or step 540), the movement segment in which the loss of posture occurred is identified, followed by identifying critical features that indicate an attempt to stabilize the body along the movement segment and a little after it. The identification of the movement segment in which the loss of posture occurred can be done, for example, by a machine learning process in which a person is made to lose posture (for example, when the person is sitting in a vehicle, the vehicle turns or jumps) and then create a model of movement characteristics that indicate a loss of posture. Secondly, stage 540 may continue with identifying patterns within the body movement segments that indicate a change in the medium or in the body movement segments that occur immediately after the BDE (e.g., after the change in the medium) and that reflect an attempt to compensate for the BDE (patterns that indicate that the person is trying to stabilize himself). For example, rate of change in data received from the sensors such as rate of kinematic changes (e.g., accelerations changes or derivatives of acceleration changes) or rate of pressure or force changes, occurring within the segments of intertest. A machine learning model that identifies the relevant patterns (if implemented) can be trained by recording EEGs or EMGs and creating a coupling of EEG or EMG components associated with postural control with unique body movement components that appear just before, during and just after the EEG or EMG components. Alternatively, recording the movements of the intermediary (for example, record the movement of the vehicle) and look for unique body movement patterns occurring during or immediately after the intermediary movements. Alternatively, searching the body movement data and identifying abnormal patterns reflecting loss of balance or compensation for loss of balance.

[0131] Step 550 may include determining the PIC (e.g., the cognitive state) in response to a degree of correlation between an intensity of the BDE and an intensity of associated postural correction movements. The intensity of the BDE may be measured directly or indirectly (e.g., the intensity of the loss of posture as detected by the sensor). The intensity of the BDE could be represented for example by various kinematic and temporal parameters characterizing or otherwise indicative of an intensity of the BDE and / or of the loss of posture, such as rate, speed, amplitude, size, change of direction. The intensity of the associated postural correction movementsmay be measured directly or indirectly. The intensity of the associated postural correction movements could be represented for example by various kinematic and temporal parameters characterizing or otherwise indicative of an intensity of the associated postural correction movements, such as rate, speed, duration, amplitude, size, timing after the BDE, etc. An example for a determining the PIC based on such correlation between the intensity of a BDE to the intensities of the postural correction movements resulting from the response of the individual to the BDE is assigning an improved PIC (e.g., cognitive state) for better correlations, and reduced PIC for poorer correlations. For example, step 550 may include estimating a drunkenness level (or other performance inhibiting PIC) of a person having poor correlation between the intensity of BDE and the corresponding movements as more severe than the drunkenness level (or other performance inhibiting PIC) of a person having better correlation between the intensity of BDE and the corresponding movements. Any suitable form of determining correlation (between parameters of similar nature or not, e.g., amplitude-to-amplitude correlation vs. amplitude-to-timing correlation) may be used.

[0132] It is noted that step 550 may optionally take into account kinematic parameters relating to the one or more primary correction movement which the individual takes in response to experiencing the BDE, in addition to the parameters of the one or more posture correcting movements. In many types of standard movement, the velocity of motion (primary corrective motion or corrective movements) changes in a bell curve in which the acceleration of the movement is similar (albeit reversed) to the deceleration of the movement. For example, step 550 may include estimating a performance inhibiting PIC of an individual with a bell shape kinematic parameter behavior over time has having lower inhibition level (even as “normal” or better than normal) than the performance inhibiting PIC of an individual having kinematic parameter behavior differing significantly from a bell curve (which may be diagnosed in step 550, for example, as suffering from nausea). Optionally, stage 550 may include determining the PIC (e.g., a class of PIC, a level of PIC, performance inhibiting characteristics of the PIC) based on the behavior of a kinematic parameter of an individual’s movement over time (e.g., how similar is the changing of the kinematic parameter over time to a bell curve, or to other expected curves, associated with different PICs). The disclosed computation may be applied to stability compensationsubmovements or to any other type of movement. Once an indication for a BDE is obtained (whether by detecting it or being notified of it), the method continues with obtaining the kinematic data pertaining to the motion which follows the BDE and at least partly results from the BDE (characterized at least partly by kinematic fluctuation patterns as a result of the brain responding to the BDE), fragmenting such movement to a multitude of individual movements (e.g., “motion instances”) and analyzing the different motion instances (e.g., generating statistics of the patterns of the different movements) for determining the PIC of the individual.

[0133] The processing of the kinematic data of the identified movements for identifying the PIC may be achieved using various computational and algorithmic approaches, such as using heuristic algorithms, machine learning algorithms, or combination of both. It is noted that different methods of machine learning and / or different methods of heuristic algorithms may be used in synergy, in order to identify unique features in the movements that respond to differences between different PICS (e.g., different cognitive states). One way of collecting reference data (as well as training data for machine learning algorithms, if used) is to implement parametric manipulation of the cognitive state, for example by giving different amounts of alcohol to the subjects or by inducing different levels of fatigue in the subjects. The machine learning model (or neural networks) may then run on the data. Such a model may be specifically guided to explore the movements occurring within the primary movement, especially following changes to the response dynamics of the input user interface.

[0134] The determination of the postural instability condition of the individual at step 550 may be used in different ways, some of which were discussed above. One optional way of utilizing the determination of the postural instability condition of the individual is exemplified by the optional steps 570, 580, and 590. In decision box 570 method 500 continuous with determining whether the determined PIC limits the performance capabilities of the individual (e.g., with respect to a specific activity which the individual may commence or otherwise engage in), such as whether the individual is drunk, tired, intoxicated, experiencing a seizure, etc.

[0135] If the PIC determined in step 550 is determined to limit the performance capabilities of the individual, different remedial actions may be executed or triggered (e.g., for execution by another system) in step 580, such as those discussed above (e.g.,with respect to system 200). On the other hand, if the PIC determined in step 550 is determined not to limit the performance capabilities of the individual (at least not to a threshold-crossing degree), method 500 may continue with step 590 of facilitating individual control of a system whose control is conditioned on the PIC of the individual. Other actions may also be taken (e.g., informing the individual or another party about the findings of method 500). Other ways of following up may also be implemented. For example, the determining of the PIC may be followed by generating notification data indicative of the determined PIC. This may be useful, for example, when the individual (or another entity such as a supervisor, health care provider, family member, etc.) may simply be interested in knowing what the PIC (or a related parameter such as the cognitive state) of the individual is. For example, some people may want to use an app on their smartphone which implements method 500 (fully or partly) before entering into a negotiation, argument, decision-making process, or any other situation in which they want to be in their best.

[0136] Method 500 may optionally include a step of preventing operation by the individual of at least one system, based on the determining of the postural instability condition (i.e., preventing such control for certain outcomes of the determining of the PIC, e.g., drunkenness, intoxication, or a seizure, but not for all PICS, e.g., normal condition or mild tiredness).

[0137] Method 500 may optionally include a step of restricting operational conditions of a machine supervised by the individual, based on the determining of the postural instability condition (i.e., restricting such control for certain outcomes of the determining of the PIC, e.g., drunkenness, intoxication, or a seizure, but not for all PICS, e.g., normal condition or mild tiredness). Such a step may include, for example, restricting but not stopping an autonomously driven vehicle in response to determining motion sickness of the individual, taking into consideration the capability of the driver to act as a backup driver for the vehicle, or the condition which would aggravate a condition of the individual (e.g., worsen the motion sickness). Continuing the same example, such restrictions may pertain to permitted kinematic parameters of the vehicle, to types of roads on which the vehicle may travel, and so on.

[0138] Method 500 may optionally include triggering manipulation of to at least one of the individual and an environment of the individual, for mitigating a physiologicalcondition associated with the postural instability condition, based on the determining of the postural instability condition. Such a step may include, for example, applying different forms of stimulus to the individual, applying different types of medication or other chemical substances to the individual or her environment, setting parameters for an environment in which the individual is located (e.g., vehicle, elevator, room, street corner), and so on.

[0139] Referring to method 500 as a whole, it is noted that when there is an interest in using movements (e.g., submovements) in order to identify a PIC, different methods of machine learning may be used in synergistical fashion in order to identify unique features (e.g., unique kinematic fluctuation patterns) in the movements that correspond to fluctuations in the PIC. For example, this may be facilitated by a parametric manipulation of the PIC of various people, for example by giving different amounts of alcohol to the subjects or creating different levels of fatigue in the subjects. A machine learning model (or neural networks) may then be run on the data. The machine learning model should be guided to explore the many movements occurring within the primary movement.

[0140] Fig. 4 illustrates a sub-method 540’ for identifying movements (e.g., submovements) of one or more body parts of the individual following the BDE based on processing of the kinematic data, in accordance with examples of the presently disclosed subject matter. Sub-method 540’ is one way that may be used for implementing step 540, but other methods or processes may also be used.

[0141] Step 541 of method 540 includes obtaining values of at least one kinematic parameter of the individual for a continuous duration following the BDE. Such one or more kinematic parameters may be indicative, for example, of the position of the body part (e.g., with respect to the rest of the body, to sensor 210, to the vehicle or machine for which access is requested, and so on), of the orientation of the body part, of the velocity of the body part (scalar or vector), and so on. It is noted that the kinematic parameter may be related to the kinematics of the body part directly (e.g., a camera or a pressure sensor) or indirectly (e.g., internal joystick sensors which measure directly the angle of the joystick handle and which are indicative of the position of the hand of the individual indirectly, or even cursor position on the screen, which is another indirect indication of the location of the hand). Referring to an example in which theindividual operates an user interface (e.g., operating a cursor on a computer screen with a joystick or a mouse, or moving a steering wheel of a car), the obtained parameter may simply be cursor position data, joystick / mouse / wheel position sensor output data, or joystick internal sensors data (indicative of joystick orientation). The time following BDE for which sensor-based kinematic data is collected may vary to suit the specific implementation of method 500 or sub-method 540’. For example, kinematic data may be collected for a duration lasting between 1 second (or less) to 5 seconds, between 5 seconds to 20 seconds, between 20 seconds and 2 minutes, or any suitable longer duration. The duration for which kinematic data is collected may be predetermined, may be calculated based on collected kinematic data, on sensor data, or in any other suitable manner.

[0142] Optional step 542 includes processing the at least one kinematic parameter to generate values of a derived parameter for the continuous duration. For example, step 542 may include generating a trace of velocity values over time by calculating the first derivative (differentiating) of the position data obtained in step 541. Of course, in some cases such processing is not required (e.g., if the sensor 210 is operable to provide the velocity parameter directly).

[0143] Step 543 includes identifying a beginning (onset) of a principal movement based on the kinematic data and / or derived parameter. The identifying of step 543 may be implemented using any suitable type of processing, such as meeting a predefined criterion. For example, principal movement onset may be identified as the moment when a parameter (e.g., linear velocity, angular velocity) surpasses a predefined threshold (e.g., a pixels-per-second rate, or 5% of the peak angular velocity) and stays above for a predefined duration (e.g., 100 milliseconds).

[0144] Step 544 includes identifying an end (offset) of the principal movement based on the kinematic data and / or derived parameter. The identifying of step 544 may be implemented using any suitable type of processing, such as meeting a predefined criterion. For example, principal movement offset may be identified as the moment following the onset in which a parameter (e.g., linear velocity, angular velocity) does not vary by 5° for 0.4 seconds. The timing of the primary movement is then defined to be between the onset time and the offset time.

[0145] We use the term “principal movement” to refer to the entire motion from point A to point B (e.g., when a person moves his hand to grab a mug from a table, the entire movement between the starting position of the hand until it reaches the mug and stops is the principal movement). This so-called principal movement can be separated into two types of movements: (a) the primary movement which is the main motion that initiates and drives the body part towards its target position (location and orientation). This movement may include in many cases utilization of larger muscle (or muscle groups) to accomplish the intended task; and (b) smaller movements (e.g., corrective submovements), which are smaller, more refined adjustments made during the primary movement. These adjustments are controlled by the brain's continuous feedback system, which detects inaccuracies in the motion and corrects them to ensure that the intended motion is carried out (e.g., the hand successfully reaches the mug). Such smaller movements (e.g., corrective submovements) may include, for example, changes in speed, direction, or grip strength, and are crucial for fine-tuning and optimizing the overall movement. While not necessarily so, the corrective movements may include activating synergist muscles to assist the agonist muscle in performing the desired movement. Such synergist muscles help to support and fine-tune the motion, as well as prevent undesired or excessive movement in other directions. As discussed above, the plurality of smaller movements may be defined in many different ways, and are not necessarily limited to the corrective submovements as defined in the art.

[0146] It is noted that the accuracy of voluntary movements (e.g., voluntary primary movements) is limited by the speed-dependent noise present in the central nervous system (as reported by Woodworth in 1899, Fitts in 1954, and Schmidt et al. in 1979). This results in a trade-off between speed and accuracy known as Fitts's law. Essentially, the faster one tries to move, the less accurate the movement tends to be, a fact confirmed by the work of Fitts (1954), Wright and Meyer (1983), and Harris and Wolpert (1998). This limitation, and how we work around it, is the cornerstone of motor learning. To handle the noise and variability in rapid movements, the central nervous system monitors efference copy — copies of the motor command that allows the brain to predict the sensory consequences of actions — and sensory afference, the incoming nerve impulses that relay information from our senses. The central nervous system adjusts movements in response to errors or error predictions (i.e., theanticipation of errors), a mechanism described by Gordon and Ghez in 1987, Meyer et al. in 1988, Messier and Kalaska in 1999, and Desmurget and Grafton in 2000. The electrophysiological component known as ERN (Error-Related Negativity), which reflects error control in the brain, is present at the start of the movement corrections.

[0147] The methods, systems, and computer program products disclosed herein enable us to learn about the cognitive state and / or physiological state of an individual through analysis of movement adjustments from the moment a situation of loss of balance occurs. Movement adjustments can be continuous (e.g., changing the duration of an agonist muscle movement or controlling the activation of the antagonist muscle) or discrete, through corrective movements. Larger movements can consist of an initial primary movement followed by corrective movements if the primary movement is too large or small. These movements can be concurrent with the primary movement (e.g., an overlapping submovement) or made after it (e.g., a delayed submovement).

[0148] Step 545 includes defining a plurality of movements (e.g., submovements or other movements such as those discussed above) within the principal movement duration. Step 545 may include, for example, dividing each principal movement into a primary movement and many submovements. By way of example, such division may be achieved by analyzing the third derivative of position (commonly referred to as “jerk”) and locating all zero crossings between onset and offset of the principal movement. The number of zero crossings is halved to find the total number of movements (velocity peaks). Subtracting the primary movement from this count gives the number of submovements. The overlap of submovements with the primary movement may be estimated based on the method by Tunik et al. (2009). Other parameters which may also be detected in step 545 include, for example, peak velocity and peak acceleration of the primary movement, and the time until the first submovement. These parameters may be determined from the velocity and acceleration trace. Principal movement amplitude may be defined as the angular displacement between the starting angle and the maximum displacement in the trial. As mentioned above, many other techniques of defining movements may be implemented (e.g., based on heuristic rules, on analysis of training data, on computer learning, on deep neural networks, and so on).

[0149] It is noted that postural control is sensitive to different postural instability conditions, examples for which are provided in greater detail below, such as different mental states, dual task, headache, fatigue, drunkenness, and motion sickness. With respect to dual tasking (e.g., measuring postural activity of the individual while that individual is preoccupied in another activity), it is noted that method 500 (and likewise system 200, mutatis mutandis) may include assessing a postural instability condition which is indicative of a parameter pertaining to the other task performed by the individual. Such a parameter may include: level of engagement with the other task (e.g., if the individual watches a video content, the level of preoccupation of the individual in the video content will affect the response of the individual to a BDE, and therefore assessment of the latter is indicative of the former), level of complexity of the other task (e.g., solving a more difficult puzzle may affect the postural control of the individual differently than solving a simpler puzzle), movement related parameters of the task (for example, is the other activity enhances postural control or worsen it), and so on. For example, method 500 (and likewise system 200, mutatis mutandis) may be used in a use case in which the postural instability condition (e.g., mental state) us assessed when that individual is busy with another task, such that the more the individual pays attention to the occupation, their postural control will change. For example, if an advertisement is shown to a passenger in a car, it is possible to assess how interesting is the advertisement to the individual passed on the postural response of the individual to a BDE, e.g., as discussed with respect to method 500.

[0150] Fig. 5A includes four charts of kinematic data collected when the respective individual is in different PICs and at different degrees of stability, in accordance with examples of the presently disclosed subject matter. Each of the diagrams 401, 402, 411, and 412 shows measurements of two piezoelectric sensors located under a driver's seat on which the respective individual is sitting, measuring displacement of thighs of the respective individual while driving. The measurement of both sensors is sufficiently similar such that kinematic information captured by each of the respective pair of sensors may be sufficient to determine the PIC of the individual, even though implementing more than one sensor may yield more accurate results, especially in transitional or intermediate PICs (e.g., mild intoxication or mild fatigue). The abscissa (x-axis) of each diagram shows passing time in seconds, and the ordinate (y-axis) is indicative of change in pressure applied to the sensor, in arbitrary units (the graphsactually represent change in the electrical voltage of the piezoelectric sensors when the individual moves while sitting on a seat in which the sensors are placed, thereby changing the pressure that activates the sensors). It should be noted that the times of each diagrams are different because the illustrated measurements were acquired at selected temporal windows starting at different times from the beginning of each respective measurement. In the illustrated example, the BDE is not a planned BDE, but rather are BDEs determined upon detection of a sharp change in direction of the vehicle by the accelerometers, which causes the driver to jerk along with the vehicle. The driver then stabilizes himself. In the illustrated case, the BDE resulted from sharp turning of the car.

[0151] Dot product of vectors was calculated per time point, giving a scalar output: dot productt^t+1= accXt* accXt+1+ accYt* accYt+1+ accZt* accZt+1

[0152] The magnitude of a vector was calculated as the square root of the sum of the squares of its components. magnitudet= accX2+ accY2+ accZf magnitudet+1= accX2+1+ accY2+1+ accZ2+1

[0153] Cosine of the angle between vectors representing the change in the vehicle orientation between consecutive time steps.

[0154] The time of the BDE (indicated by a vertical black dashed line denoted “BDE” in diagrams 411 and 412) was determined when> 100, indicating a sharp change in the vehicle's direction from time t to time t + 1. In these two diagrams, to the left of the dashed BDE line: the time duration Atturnin which the driver performed the turn, indicating loss of stabilization. To the right of the BDE line: the time duration tmotionfixationin which the driver returned to straight driving, indicates the stabilization of the motion.

[0155] The two top diagrams illustrate the displacement of the body part for a sober individual (diagram 401) and for intoxicated individual (diagram 402) when the respective individual is subject to no acceleration (i.e., in stable conditions). The twobottom diagrams illustrate the displacement of the body part for a sober individual (diagram 411) and for intoxicated individual (diagram 412) when the respective individual is subject to unexpected acceleration during a BDE. As can be seen, in both cases (401 vs 411 and 402 vs 412), the occurrence of the BDE results in motion by the individual, partly by the acceleration of the vehicle transferred to the individual in the vehicle, and partly by attempts of the individual to stabilize oneself.

[0156] From diagrams 401 and 402 it can be inferred that there is no sufficient difference between sober and intoxicated (e.g., drunk) drivers while no displacement is obtained. In addition, for both cognitive states the AAmp < IV. However, with respect to diagrams 411 and 412, it can be seen that the amplitude of motion during stabilization loss while drunk (Ampmotion(drunk) is approximately twice that of when sober (2 ■ Ampmotion(sober) . During Motion Stabilization: the amplitude while drunk shows a decreasing trend. However,first stabilizes, then decreases, and finally increases -eventually doubling its value.

[0157] Fig. 5B includes four charts of kinematic data collected when the respective individual is in different PICs and at different degrees of stability, in accordance with examples of the presently disclosed subject matter. Each of the diagrams 421, 422, 431, and 432 shows derivates of measurements of a piezoelectric sensor located under a driver's seat on which the respective individual is sitting, measuring acceleration of thighs of the respective individual while driving. The abscissa (x-axis) of each diagram shows passing time in seconds, and the ordinate (y-axis) indicates acceleration in arbitrary units. It should be noted that the times of each diagrams are different because the illustrated measurements were acquired at selected temporal windows starting at different times from the beginning of each respective measurement. In the illustrated example, the BDE is not a planned BDE, but rather are BDEs determined upon detection of a sharp change in direction of the vehicle by the accelerometers, which causes the driver to jerk along with the vehicle. The driver then stabilizes himself. In the illustrated case, the BDE resulted from sharp turning of the car.

[0158] Dot product of vectors was calculated per time point, giving a scalar output: dot productt^t+1= accXt* accXt+1+ accYt* accYt+1+ accZt* accZt+1

[0159] The magnitude of a vector was calculated as the square root of the sum of the squares of its components.

[0160] Cosine of the angle between vectors representing the change in the vehicle orientation between consecutive time steps.

[0161] The third derivative of Voltage (measured by the piezoelectric seat sensor) with respect to time indicates the rate of change of an object's acceleration over time.

[0162] The time of the BDE (indicated by a vertical black dashed line denoted “BDE” in diagrams 431 and 432) was determined when> 100, indicating a sharp change in the vehicle's direction from time t to time t + 1. In these two diagrams, to the left of the dashed BDE line: the time duration Atturnin which the driver performed the turn, indicating loss of stabilization. To the right of the BDE line: the time duration tmotionfixationin which the driver returned to straight driving, indicates the stabilization of the motion.

[0163] The two top diagrams illustrate the acceleration of the thigh for a sober individual (diagram 421) and for intoxicated individual (diagram 422) when the respective individual is subject to no acceleration (i.e., in stable conditions; straight driving was obtained< 50°). The two bottom diagrams illustrate the acceleration of the thigh for a sober individual (diagram 431) and for intoxicated individual (diagram 432) when the respective individual is subject to unexpected acceleration during a BDE. As can be seen, in both cases (421 vs 431 and 422 vs 432), the occurrence of the BDE results in motion by the individual, partly by the acceleration of the vehicle transferred to the individual in the vehicle, and partly by attempts of the individual to stabilize oneself.

[0164] From diagrams 421 and 422 it can be inferred that there is no sufficient difference between sober and intoxicated (e.g., drunk) drivers while no acceleration is obtained. However, with respect to diagrams 431 and 432, during the turn drunk derivative indicates a high rate of change in the vibration acceleration, compared to a more smoothed rate of the sober derivative. During motion stabilization, following the BDE, the amplitude of the sober peak (Ampmotionis approximatelytwice that of drunk peak (2 ■ Ampmotiondrunk') . )

[0165] Referring to step 540 of method 500 and to sub-method 540’, it is noted that the identifying in any of these cases may optionally include identifying patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual, and identifying within the patterns abnormal features reflecting abnormality of the patterns. The processing of the pattern data in such a case may include assessing postural stability of the individual based on the identified abnormal features. That is, any person might lose balance and attempt to compensate for such loss of balance, so detecting patterns indicating loss of balance or attempted recovery is to be expected. However, people who suffer from altered cognitive states or other altered PICs demonstrate different patterns in coping and recovering from lost balance. Detecting which such patterns are normal and which are abnormal may be done, for example, based on previously collected and analyzed reference data which includes measurements of patterns in people experiencing different PIC (e.g., experiencing different cognitive states). For example, both sober and drunk people may be subjected to different levels of destabilizing stimuli, and the response patterns of the different groups of people may be collected and processed for generating reference data which is later used in method 500 and / or 540’ for analyzing the PIC of the specific individual.

[0166] Optionally, method 500 (and / or sub-method 540’) may include identifying, differentiating, and processing overlapping movements (e.g., as exemplified with respect to Fig. 6 below). The calculation of overlapping movements is of particular importance when trying to use them to identify the cognitive state of the individual when she loses her posture. In some cases, the involuntary movement in which the posture is lost can be considered as primary movement. In such a situation, it is possible to look for characteristics of overlapping movements that reflect an attempt to correct or stop the unwanted movement, within the movement that represents theloss of posture. Another example of overlapping movements which may be identified, differentiated, and used in the processing includes movements which did not yet concluded, and after a kinematic peak of the movement (e.g., post peak decline in velocity, acceleration, etc.) a second kinematic boost is initiated by the brain. For example, if when a velocity of a movement of a body part of the individual is past its peak and slowing down the brain determines that it has not yet reached its target, it may accelerate the movement again.

[0167] Reverting to method 500 in general, it is noted that the timing information of the BDE may be obtained in different ways. For example, method 500 may optionally include step 502 of identifying a BDE using sensor data. Such a sensor may be the same sensor used for the collection of the kinematic data (e.g., a camera or an accelerometer), or any other sensor. Message 500 also includes the optional step 504, which includes triggering the BDE. Search triggering may include triggering an activation of a motor, a media output interface, or instructing another system to initiate BDE in any suitable manner. Method 500 may also include receiving information pertaining to the BDE from another system, whether a system initiating the BDE or a system which identifies or being notified of the BDE format yet another system. Recognition of the BDE maybe done directly (e.g., by an accelerometer directly sensing the motion the individual is subject to) or indirectly (e.g., by a camera and an image processing software, recognizing effects on of acceleration on inanimate objects in the vicinity of the individual). Optionally, the obtaining of step 520 may include detecting the timing of the BDE based on analysis of the sensor-based kinematic data. Optionally, the obtaining of step 520 may include detecting the timing of the BDE based on analysis of sensor data of a vehicle in which the individual is located. Optionally, the obtaining of step 520 may include obtaining the timing information from a virtual reality (VR) system or augmented reality system which the individual operates (or otherwise subjected to), based on scenarios created in the augmented or virtual reality system (whether intentionally intended to generate a BDE for testing the system, inadvertently creating a BDE, starting a scenario suspected as a BDE, or for any other reason.). Optionally, the obtaining of step 520 may include obtaining the timing information generated from analysis of video or sound content (e.g., for determining if a movie scene is a BDE, at least for some people, such as triggering epileptic seizures). More generally, it is noted that optionally, one or more of the atleast one BDE used for determining the PIC may be a non-kinetic stimulus affecting at least one of the visual perception and the auditory perception of the individual (e.g., one or more photos, videos, lighting patterns, sounds, noises, and so on).

[0168] Fig. 6 illustrates four diagrams illustratively demonstrating different ways of defining a plurality of movement instances 310 in the kinematic data of diagram 412, in accordance with examples of the presently disclosed subject matter. In diagram 412A, the kinematic motion is divided into multiple stability-compensation movement spans 310 of equal length of about 50-100ms each. In diagram 412B, the multiple stability-compensation movement spans 310 are of different lengths, and are determined based on analysis of the sensor-originated kinematic data. In diagram 412C, some of the multiple stability-compensation movement spans 310 are partly or fully overlapping with one another. In diagram 412D, the multiple stabilitycompensation movement spans 310 are much shorter, exemplifying the ability to implement the systems, methods, and computer products disclosed herein in many different ways. It should be noted that these are just a few examples not intended to exhaust all the ways in which stability-compensation movements may be identified. While not necessarily so, different movements 310 (e.g., different stability compensation movements) may be characterized in that they demonstrate different accelerations, different accelerative-patterns and / or accelerative-features, and so on. Optionally, the different movements may be identified and / or defined specifically to have different accelerations, different accelerative-patterns and / or accelerative- features, and so on.

[0169] One of the significant challenges which the disclosed systems, methods, and computer program products discussed herein are able to face is identifying the intermediary changes that call for significant posture corrections. That is, those intermediary changes that require significant intervention of the cerebral postural control system. The analysis of the different such intermediate changes (i.e., all of the complex pattern of the plurality of stability compensation movements) renders the information obtained from the activity of the cerebral postural control system meaningful for the assessment of the PIC of the individual (e.g., their cognitive state).

[0170] Referring to method 500 as a whole, optionally one or more sensors may capture movements of multiple body parts occurring in response to the same BDE(especially stability compensation submovements, and possibly other types of movements as well). The processing of stage 550 in such case may take into account the kinematic features and / or kinematic fluctuation patterns of stability compensation movements of different body parts resulting from the same BDE for the determining of the PIC. Such processing may analyze the kinematic features and / or kinematic fluctuation patterns of each movement independently (e.g., at least N>1 body parts should demonstrate specific kinematic features and / or kinematic fluctuation patterns for the determining of specific PIC) or in relation to one another (e.g., the timing differences between corrective submovements in different body parts, the relative amount of corrective submovements in different body parts in response to the same BDE, and so on). For example, one or more pressure sensors in a car seat may measure movements (e.g., submovements) of the torso of the individual while a camera or a radar simultaneously measures movements of the head and / or arms and / or hands, and the relationship between the kinematic features and / or kinematic fluctuation patterns of corrective movements of one or more subgroups of different body may serve in the determining of the PIC. Optionally, such processing based on kinematic features and / or kinematic fluctuation patterns of movements of different body parts measured by one or more sensors of one or more types of sensors may enable a computerized model used for method 500 to determine PICs in an improved manner. For example, continuing the same example, possibly the system executing method 500 in the latter example (e.g., system 200) may perform differently (arguably worse) in times when the camera does not work or cannot properly detect movements of the arms to complete the data pertaining to the movements of the torso provided by the pressure sensors.

[0171] It is possible that different body parts will move in opposite directions. One side of the body slows and the other moves faster to the other side. For example, each hip can react differently, or the upper body and lower body can react differently, or head and neck versus lower body. In cases where data is received from different body parts, for example when measuring with a camera or radar, a calculation of the combination of the various movements should be made.

[0172] Referring to system 200 and to method 500, it is noted that optionally, the determining of the PIC of the individual may be based on decision model which is agnostic to historical performance information of the individual. That means in suchcases there is no need to save sensitive personal data of the individual, and that the respective system or method could also be used for anonymous users, unregistered users, casual users, guest users, drop-in users, one-time users, etc. While not necessarily so, other steps of the respective method (as well as processing capabilities of system 200) may also be agnostic to historical performance information of the individual, or to other data about the individual. For example, the processing of the kinematic data to identify movements (e.g., submovements) of one or more body parts of the individual following the BDE may also be agnostic to historical performance information of the individual, or to other data about the individual. In addition or instead, the processing of the kinematic patterns of the identified movements to determine kinematic patterns indicative of recognized PICs may also be agnostic to historical performance information of the individual, or to other data about the individual. It is noted that user-agnostic operation is just one alternative, and that in other implementations different levels of individual information may be used for different aspects of the processing. Such individual information may range from very general (e.g., age and gender) to the very specific (e.g., prior recordings of kinematic data of the same individual). In some implementations, tailoring the disclosed technology to specific users may be especially beneficial (for example, when specific individuals are tasked with making very significant decisions). Optionally, the determining of the PIC is based on decision model which is agnostic to historical performance information of the individual. Optionally, the processing of the kinematic features and / or kinematic fluctuation patterns of the stability compensation movement is based on decision model which is agnostic to historical performance information of the individual. The decision model may be a statistical model, a heuristic model, a machine-learning model, etc. The decision model may be implemented by any suitable type of computerized model, such as the ones discussed above. Referring to the option of utilizing machine learning in system 200 and / or for the execution of method 500, it is noted that machine learning algorithms may be used for analyzing the kinematic data and / or the preprocessed data and to infer from it a person's PIC (e.g., cognitive state, physiological PIC). The algorithm may include supervised or unsupervised learning methods, such as decision trees, random forests, neural networks, or support vector machines. Such a machine learning algorithm may be trained on a dataset oflabeled data that includes information about the person's PIC and their corresponding body movements following BDEs.

[0173] Referring to method 500 as a whole, it is noted that the respective method may be executed by executing by one or more processors the steps of the respective method which are stored as a computer readable code on a non-transitory computer- readable medium.

[0174] According to an aspect of the invention, there is disclosed a non-transitory computer-readable medium for assessing a PIC of an individual, comprising instructions stored thereon, that when executed on a processor, perform the steps of method 500 (in any one or more of its variations discussed above). According to an aspect of the invention, disclosed is a program storage device readable by machine, tangibly embodying a program of instructions executable by the machine to perform a method for assessing a PIC of an individual comprising the steps of any one or more variations of method 500.

[0175] Referring to method 500 as a whole, and to any of its variations, it is noted that the respective method may be executed by executing by one or more processors the steps of the respective method which are stored as a computer readable code on a non-transitory computer-readable medium.

[0176] The aforementioned computer program may be stored internally on a non- transitory computer readable medium. All or some of the computer programs may be provided on computer readable media permanently, removably or remotely coupled to an information processing system. The computer readable media may include, for example and without limitation, any number of the following: magnetic storage media including disk and tape storage media; optical storage media such as compact disk media (e.g., CD-ROM, CD-R, etc.) and digital video disk storage media; nonvolatile memory storage media including semiconductor-based memory units such as FLASH memory, EEPROM, EPROM, ROM; ferromagnetic digital memories; MRAM; volatile storage media including registers, buffers or caches, main memory, RAM, etc.

[0177] A computer process typically includes an executing (running) program or portion of a program, current program values and state information, and the resources used by the operating system to manage the execution of the process. An operating system (OS) is the software that manages the sharing of the resources of a computerand provides programmers with an interface used to access those resources. An operating system processes system data and user input, and responds by allocating and managing tasks and internal system resources as a service to users and programs of the system.

[0178] For example, according to an aspect of the invention there is disclosed a non- transitory computer-readable medium for assessing a postural instability condition of an individual, including instructions stored thereon, that when executed on a processor, perform the steps of: (a) receiving, over at least one hardware communication channel, sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; (c) obtaining timing information of a balance destabilizing event within the measurement time span; (c) identifying in the kinematic data kinematic fluctuation patterns of stability compensation movements of the individual following the balance destabilizing event; and (d) processing the kinematic fluctuation patterns by implementing temporal data- pattern analysis to determine a postural instability condition (PIC) of the individual. Any variation of method 500 may be implemented in this code using suitable instructions.

[0179] As mentioned above, any variation, option, embodiment, or implementation discussed with respect to method 500 may be applied to system 200 and to the aforementioned computer program product, mutatis mutandis. For example, optionally, processor 220 may be is configured to: (i) identify in the kinematic data patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual; (ii) identify within the patterns abnormal features reflecting abnormality of the patterns; and (iii) assess postural stability of the individual based on the identified abnormal features. For example, processor 220 may be further configured to selectively restrict operational conditions of a machine supervised by the individual based on the determined postural instability condition (e.g., limiting but not stopping autonomous driving based on motion sickness or more generally on the capability of the driver to act as a backup driver based on the determined PIC). For example, system 200 may include one or more components configured to manipulate at least one of the individual and an environment of the individual (e.g., based on instructions triggered by processor 220), for mitigating aphysiological condition associated with the postural instability condition, based on the determining of the postural instability condition.Extraction of movement data from kinematic data

[0180] As discussed above, there are many possible ways to extract movement data and features from the kinematic data collected by the sensor. In the following paragraphs, a nonlimiting example of a process for extracting movement data from kinematic data is disclosed. In the disclosed process, movements are extracted from the position and / or velocity traces of the movement segment in focus (i.e., within a duration of time) by calculation of higher-order derivatives, including acceleration, jerk, and snap. For example, such high-order derivatives may be obtained for each segment by numerical differentiation. There are different methodologies for analyzing movements. Below is one of the more common methodologies (Novak et al., 2000).

[0181] The movement segments are analyzed for their timing of movement onset, peak velocity, and end. The onset is determined as the moment when the velocity surpasses a 10% threshold of the peak velocity. Typically, the time of peak velocity is established by identifying when acceleration first reaches zero after crossing from positive to negative. However, there are instances where the acceleration trace shows an inflection point prior to the zero crossing, indicating a secondary acceleration pulse. In such cases, the time of peak velocity is estimated based on the acceleration inflection (found at the jerk zero crossing) rather than the acceleration zero crossing. This estimate is typically 5 to 10 milliseconds ahead of the actual peak velocity time, where the first acceleration pulse would have crossed zero if not disrupted by the second pulse.

[0182] The end of the movement is identified through two methods, depending on the desired application. Firstly, similar to the movement onset, the end is defined as the moment when velocity drops below a 10% threshold of the peak velocity to maintain the symmetry of the movement. The second definition is the point when velocity drops below ±10°-s1and remains there for a minimum of 30 milliseconds. This second method is utilized in analyzing movement regularity and irregularities. Irregular movements are recognized by noticeable inflections in the acceleration during the latter half of the movement. These inflections are found by counting thezero crossings of acceleration's derivative (jerk) and its derivative (snap). Trials with more than one jerk or snap zero crossing in a specific time window during the latter half of the movement are considered irregular. An example timing for this time window begins 12 milliseconds after peak velocity and ends 2 milliseconds after velocity drops below the 10°-s1threshold and settles to zero. The 2 milliseconds were added to take into account the snap zero crossings related to sudden final decelerations. It is noted that different timings may be used.

[0183] Fig. 7 illustrates an example of kinematic data and analysis of motion patterns in that kinematic data, in accordance with examples of the presently disclosed subject matter. Such analysis may include, for example, various segmentation techniques, such as (but not limited to) techniques which are based on the differentiation of the submovements. In Fig. 10, the measured / sensed motion pattern MP(t) is shown represented by a curve Cl corresponding to direction changes of a continuous hand motion. Curve C2 represents motion acceleration changes. While the processing of the motion pattern by system 200 and / or in method 500 does not necessarily involves identifying, distinguishing, or processing submovements in the motion patterns of the respective body portion, the following discussion explains the specific motion of the hand of the user in such terms, for clarity. Segment A of the curve Cl presents initiation of goal-directed movement; segment B presents undershoot corrective submovement immediately after pick acceleration; segment C corresponds to overshoot corrective submovement immediately after pick acceleration; segment D presents undershoot corrective submovement immediately before movement termination; segment E presents overshoot corrective submovement immediately before movement termination; and segment F presents termination of the goal-directed movement. Segments A, B, C, D, E, and F are just one of the possible many ways to analyze the kinematics of the hand during the motion.

[0184] The characteristics and prevalence of submovements can result from different task constraints. As previously mentioned, in the context of the current application, the relevant motion patterns may be interpreted as corrective adjustments resulting from changes of the response dynamic of the input user interface during the performance of the task, possibly resulting from the aforementioned mechanisms in the brain of the user.

[0185] However, there are other motion pattern interpretations and even other submovements interpretations. For example, submovements may be interpreted as a property of movement control. More specifically, submovements may be movement primitives used as building blocks of normal movements, thus having no direct relation to accuracy requirements. Also, many submovements may represent irregular velocity fluctuations, emerging due to noise in the kinematic output (i.e., muscle elasticity, coactivation, non-smooth activation of motor units, and noise in the neural circuitry involved in movement control).

[0186] Thus, it might be difficult to distinguish corrective and non-corrective submovements based on kinematic analyses. Corrective and non-corrective submovements have similar kinematic characters, reflected by velocity profile modulations, usually measured by zero crossings of the first three or four displacement derivatives. The distinction may be based on fitting movement trajectory with series of bell-shaped functions of scaled duration and amplitude. However, submovements extracted according to these methodologies can be either corrective or non-corrective. According to some other approaches, if the submovement brings the trajectory closer to the target it is a corrective one. However, noisy motions (e.g., noisy target-aimed motions) may have the same or similar characteristics as a series of corrective submovements. According to yet further approaches, motion termination may cause submovements because it requires dissipation of movement mechanical energy and stabilization of the arm at the target. In discrete movements, motion termination results in complete halt of both velocity and acceleration. However, in continuous movements that reverse without residing on target, only the velocity, and not acceleration, is abolished at the target. The stabilization of the limb at the target in discrete motions may cause submovements, absent in continuous movements. Accordingly, submovements revealed with the lower derivatives (gross submovements) are often caused by motion termination in discrete motions but not in continuous motions. Conversely, submovements revealed with higher derivatives of motion (fine submovements) might be more related with corrective maneuvers associated with higher accuracy demands and occur in both discrete and continuous motions. However, during cyclical movements, incidence of fine submovements depends on cyclic frequency (frequency of periodic movement) and not on accuracy demands. Hence, slow movements may be prone to irregularities observed as finesubmovements, and since highly accurate motions are also slower, these movements are characterized by non-corrective fine submovements.

[0187] Alternatively or additionally, the motion command data being measured / sensed may include a force (or any derivative thereof such as pressure) applied by the body part (e.g. on a certain device) when performing the action. In general, the force applied when erroneous action is performed is different from the force applied when a non-erroneous action is performed. The applied force can be measured on the individual's body part which is applying the force or on the device on which the force is being applied. Similar to the acceleration and the derivative of acceleration / deceleration in relation to time, the rate of change in the applied force can be calculated and used as an indication of an erroneous action.

[0188] The motion command data being measured / sensed may also include time to lift parameter being measured as a time interval before the body part is lifted from a certain device on which the action is applied, or a time interval before the pressure applied on the device is alleviated, or a time interval before an electric circle closed by the action, opens again. For example, a time to lift period can be measured from the moment of initial contact of a body part with the device until the body part is lifted from the device. In general lifting time shortens when the action is a result of an erroneous command as compared to an action which results from a non-erroneous command.

[0189] The sampling frequency used in measurements of error detection-related kinematics and other information related to the measurement of motion command data is preferably above 50 Hz and, preferably, above 100 Hz.Examples of postural instability condition

[0190] As mentioned above, PICs may have physiological and / or cognitive aspects. A person's cognitive operational state refers to the way in which their mind is functioning at a particular moment in time. This includes their level of attention, perception, memory, problem- solving abilities, and other mental processes that are necessary for effective decision-making and goal-directed behavior. There are several factors that can influence a person's cognitive operational state, including their level of physical and emotional well-being, the complexity of the task at hand, and the levelof external distractions present. For example, if a person is feeling stressed or anxious, they may struggle to focus and process information effectively, leading to a lower cognitive operational state. On the other hand, if a person is well-rested and emotionally stable, they may be able to maintain a higher cognitive operational state, allowing them to perform tasks more efficiently and effectively. In general, a person's cognitive operational state is an important factor in their overall cognitive performance, as it determines the extent to which they are able to process and retain information, make decisions, and execute actions. It is also a key factor in determining how effectively a person is able to adapt to new situations and challenges, as well as their ability to learn and grow. Therefore, detecting the cognitive state (or other type of PIC) based on analysis of movements features which are affected by the cognitive state facilitates assessment of the ability of the individual to process and retain information, make decisions, execute actions, and so on.

[0191] Some of the factors which may alter an individual cognitive operational state include: a. Stress: Stress can have a significant impact on cognitive functioning. When a person is under stress, their brain becomes flooded with stress hormones such as cortisol, which can interfere with their ability to focus, concentrate, and think clearly. b. Sleep: Lack of sleep can impair cognitive functioning and make it difficult for a person to perform at their best. c. Nutrition: Poor nutrition can affect cognitive functioning, as the brain needs certain nutrients to function optimally. d. Illness: Illness or injury can affect cognitive functioning, as the body's resources are focused on healing rather than cognitive tasks. e. Age: As a person gets older, their cognitive functioning can decline naturally. f. Substance use: Substance abuse, such as alcohol or drugs, can impair cognitive functioning and alter a person's cognitive operational state.g. Mental health: Mental health conditions such as depression, anxiety, or schizophrenia can affect cognitive functioning and alter a person's cognitive operational state. h. Motion sickness: Motion sickness is a condition that occurs when the body's sense of balance and motion are disrupted. It is often caused by activities such as riding in a car, boat, or airplane, or playing video games or virtual reality experiences. During motion sickness, the body may feel dizzy, nauseous, or lightheaded. The individual may also experience sweating, fatigue, and a loss of appetite. These symptoms occur because the brain is receiving conflicting signals from the eyes and the inner ear, which can cause confusion and discomfort. There are several factors that can increase the likelihood of motion sickness, such as: The intensity of the motion, The duration of the motion, The person's level of anxiety or stress, The person's physical condition (such as being dehydrated or hungry), The person's age (children and elderly people are more prone to motion sickness).

[0192] As aforementioned, altered cognitive operational state (or otherwise altered PIC) may have significant effect on the postural balance detection or correction. Altered cognitive operational state, such as changes in attention, memory, or perception, can negatively impact postural balance. When an individual's cognitive abilities are impaired, they may be less able to accurately perceive and respond to changes in their surroundings, leading to an increased risk of falls and accidents. Additionally, cognitive difficulties can make it harder for an individual to maintain their balance while performing tasks that require mental focus, such as navigating through a crowded environment or performing a complex physical activity. Overall, altered cognitive operational state can significantly hinder an individual's ability to maintain proper postural balance and stability. Several factors related to postural balance are affected by altered cognitive state. Here is an example of some: a. Stability: A person's ability to maintain their balance and remain upright can be a good indicator of their operational state. If they are able to maintain their balance easily, it may suggest that they are in a good operational state. However, if they are struggling to maintain their balanceor are frequently losing their balance, it may suggest that they are in a poor operational state. b. Postural sway: The amount of sway or movement in a person's posture can also be an indicator of their operational state. If they are standing with minimal sway and are able to maintain a stable posture, it may suggest that they are in a good operational state. However, if they are swaying excessively or have difficulty maintaining a stable posture, it may suggest that they are in a poor operational state. c. Response time: The speed at which a person responds to perturbations (sudden movements or changes in their environment) can also be an indicator of their operational state. If they are able to quickly and effectively respond to perturbations, it may suggest that they are in a good operational state. However, if they have a slower response time or struggle to respond effectively, it may suggest that they are in a poor operational state.

[0193] While the embodiments described above are provided as examples, it should be understood that various modifications and substitutions may be made without departing from the scope of the invention as defined in the appended claims.

Claims

CLAIMSWhat is claimed is:

1. A postural control assessment system, the system comprising: a hardware communication channel, for providing to a processor sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; at least one processor; and at least one memory including computer program code, where the at least one memory and the computer program code are configured, with the at least one processor, to cause the system to at least: obtain timing information of a balance destabilizing event within the measurement time span; identify in the kinematic data kinematic fluctuation patterns of stability compensation movements following the balance destabilizing event; and process the kinematic fluctuation patterns to determine a postural instability condition of the individual.

2. The system according to claim 1, further comprising at least one sensor selected from the group consisting of: a camera, an accelerometer, a RADAR, a touch screen, and a joystick, wherein the sensor-based kinematic data is based on data collected by the at least one sensor.

3. The system according to any one of claims 1 and 2, wherein the balance destabilizing event is a non-kinetic stimulus affecting at least one of visual perception and auditory perception of the individual.

4. The system according to any one of claims 1-3, wherein the processor and the computer program code are configured to determine the timing of the balance destabilizing event by analyzing the sensor-based kinematic data.

5. The system according to any one of claims 1-4, wherein the processor and the computer program code are configured to determine the timing of the balancedestabilizing event by analyzing sensor data of a vehicle in which the individual is located.

6. The system according to any one of claims 1-5, wherein the processor and the computer program code are operable to determine a cognitive operational state of the individual by processing the kinematic fluctuation patterns.

7. The system according to any one of claims 1-6, wherein the processor and the computer program code are configured to: identify in the kinematic data patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the user; identify within the patterns abnormal features reflecting abnormality of the patterns; and assess postural stability of the individual based on the identified abnormal features.

8. The system according to any one of claims 1-7, wherein the processor and the computer program code are further configured to selectively restrict operational conditions of a machine supervised by the individual based on the determined postural instability condition.

9. The system according to any one of claims 1-8, further configured to manipulate at least one of the individual and an environment of the individual, for mitigating a physiological condition associated with the postural instability condition, based on the determining of the postural instability condition.

10. The system according to any one of claims 1-9, wherein the processor and the computer program code are configured to determine the postural instability condition at least partly based on decision model which is agnostic to historical performance information of the individual.

11. The system according to any one of claims 1-10, wherein the processor and the computer program code are configured to process the kinematic fluctuation patterns for determining the postural instability condition of the individual at least partly in response to a degree of correlation between an intensity of the BDE and an intensity of associated postural correction sub-movements.

12. A vehicle, comprising: an engine operable to provide power for propelling the vehicle; an individual controllable steering mechanism for controllably changing a propagation direction of the vehicle; input user interface for detecting individual instructions for modifying a behavior of at least one module out of the engine and the steering mechanism; the postural control assessment system according to any one of claims 1- 11 ; and a Vehicle Control Authorization Module (VC AM) operable to selectively prevent controlling of performance of the at least one module by the input user interface based on the PIC determined by the postural control assessment system.

13. A method for postural control assessment, the method comprising: receiving, over at least one hardware communication channel, sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; obtaining timing information of a balance destabilizing event within the measurement time span; identifying in the kinematic data kinematic fluctuation patterns of stability compensation movements of the individual following the balance destabilizing event; and processing the kinematic fluctuation patterns by implementing temporal data-pattem analysis to determine a postural instability condition (PIC) of the individual.

14. The method according to claim 13, wherein the balance destabilizing event is a non- kinetic stimulus affecting at least one of visual perception and auditory perception of the individual.

15. The method according to any one of claims 13 and 14, wherein the obtaining comprises detecting the timing of the balance destabilizing event based on analysis of the sensor-based kinematic data.

16. The method according to any one of claims 13-15, wherein the obtaining comprises detecting the timing of the balance destabilizing event based on analysis of sensor data of a vehicle in which the individual is located.

17. The method according to any one of claims 13-16, wherein the determining comprises determining a cognitive operational state of the individual.

18. The method according to any one of claims 13-17, wherein the determining comprises determining that the individual is posturally instable.

19. The method according to any one of claims 13-18, wherein the identifying comprises identifying patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual, and identifying within the patterns abnormal features reflecting abnormality of the patterns; wherein the processing comprises assessing postural stability of the individual based on the identified abnormal features.

20. The method according to any one of claims 13-19, wherein the identifying comprises identifying a pattern which reflects at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual; wherein the processing comprises defining a multitude of brief intervals within a duration of the identified pattern, separately processing the kinematics motion of the at least one body part in each of the multitude of brief intervals, and assessing the postural stability of the individual based on the results of the plurality of brief-interval kinematic analysis processes.

21. The method according to any one of claims 13-20, further comprising preventing operation by the individual of at least one system based on the determining of the postural instability condition.

22. The method according to any one of claims 13-21, further comprising restricting operational conditions of a machine supervised by the individual based on the determining of the postural instability condition.

23. The method according to any one of claims 13-22, further comprising triggering manipulation to at least one of the individual and an environment of the individual,for mitigating a physiological condition associated with the postural instability condition, based on the determining of the postural instability condition.

24. The method according to any one of claims 13-23, wherein the determining of the postural instability condition is based on decision model which is agnostic to historical performance information of the individual.

25. The method according to any one of claims 13-24, wherein the processing of the kinematic fluctuation patterns to determine the postural instability condition of the individual is responsive to a degree of correlation between an intensity of the BDE and an intensity of associated postural correction sub-movements.

26. A non-transitory computer-readable medium for assessing a postural instability condition of an individual, comprising instructions stored thereon, that when executed on a processor, perform the steps of: receiving, over at least one hardware communication channel, sensor-based kinematic data indicative of kinematic parameters of at least one body part of an individual at different times within a measurement time span; obtaining timing information of a balance destabilizing event within the measurement time span; identifying in the kinematic data kinematic fluctuation patterns of stability compensation movements of the individual following the balance destabilizing event; and processing the kinematic fluctuation patterns by implementing temporal data-pattem analysis to determine a postural instability condition (PIC) of the individual.

27. The computer-readable medium according to claim 26, wherein the balance destabilizing event is a non-kinetic stimulus affecting at least one of visual perception and auditory perception of the individual.

28. The computer-readable medium according to any one of claims 26 and 27, wherein the instructions for obtaining comprise instructions for detecting the timing of the balance destabilizing event based on analysis of the sensor-based kinematic data.

29. The computer-readable medium according to any one of claims 26-28, wherein the instructions for obtaining comprise instructions for detecting the timing of the balance destabilizing event based on analysis of sensor data of a vehicle in which the individual is located.

30. The computer-readable medium according to any one of claims 26-29, wherein the instructions for determining comprise instructions for determining a cognitive operational state of the individual.

31. The computer-readable medium according to any one of claims 26-30, wherein the instructions for determining comprise instructions for determining that the individual is posturally instable.

32. The computer-readable medium according to any one of claims 26-31, wherein the instructions for identifying comprise instructions for identifying patterns which reflect at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual, and for identifying within the patterns abnormal features reflecting abnormality of the patterns; wherein the instructions for processing comprise instructions for assessing postural stability of the individual based on the identified abnormal features.

33. The computer-readable medium according to any one of claims 26-32, wherein the instructions for identifying comprise instructions for identifying a pattern which reflects at least one of: (a) a loss of balance and (b) compensation for loss of balance by the individual; wherein the instructions for processing comprise instructions for defining a multitude of brief intervals within a duration of the identified pattern, instructions for separately processing the kinematics motion of the at least one body part in each of the multitude of brief intervals, and instructions for assessing the postural stability of the individual based on the results of the plurality of briefinterval kinematic analysis processes.

34. The computer-readable medium according to any one of claims 26-33, further comprising instructions for preventing operation by the individual of at least one system based on the determining of the postural instability condition.

35. The computer-readable medium according to any one of claims 26-34, further comprising instructions for restricting operational conditions of a machine supervised by the individual based on the determining of the postural instability condition.

36. The computer-readable medium according to any one of claims 26-35, further comprising instructions for triggering manipulation to at least one of the individual and an environment of the individual, for mitigating a physiological condition associated with the postural instability condition, based on the determining of the postural instability condition.

37. The computer-readable medium according to any one of claims 26-36, wherein the instructions for determining of the postural instability condition are based on decision model which is agnostic to historical performance information of the individual.

38. The computer-readable medium according to any one of claims 26-37, wherein the instructions for processing of the kinematic fluctuation patterns to determine the postural instability condition of the individual are responsive to a degree of correlation between an intensity of the BDE and an intensity of associated postural correction sub-movements.

Images