Method, system, and wearable apparatus for assessing sleep quality of a subject

Abstract

Disclosed is a method (400) for assessing sleep quality of a subject. The method includes obtaining (402) electroencephalogram (EEG) data associated with the subject from one or more electrodes (104) coupled proximally to a cephalic region of the subject, during a wakefulness state. Further, the method includes determining (404) EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time. Furthermore, the method includes correlating (406) the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject. Moreover, the method includes determining (408) a deviation based on the correlation and generating (410) a sleep quality report corresponding to the subject based on the deviation. Furthermore, the method includes predicting (412), based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject.

Description

[0001] METHOD, SYSTEM, AND WEARABLE APPARATUS FOR ASSESSING SLEEP QUALITY OF A SUBJECT'

[0002] FIELD OF THE INVENTION

[0003]

[0001] The present invention relates generally to the field of neurophysiological assessment techniques, and more particularly relates to a method, a system, and a wearable apparatus for assessing sleep quality of a subject.

[0004] BACKGROUND

[0005]

[0002] Sleep is a fundamental biological process that is essential for maintaining optimal cognitive function, emotional stability, and physical health. It is not merely a passive state of rest but involves active neurophysiological mechanisms that contribute to memory’ consolidation, learning, and overall well-being. Scientific research has consistently demonstrated that inadequate or poorquality sleep can lead to diminished cognitive performance, mood disturbances, and increased susceptibility to various health disorders.

[0006]

[0003] Traditionally, sleep quality has been assessed using polysomnography (PSG), which is a multi-parametric test that records biophysiological changes during sleep, including electroencephalogram (EEG), electrooculogram (EOG), electromyogram (EMG), and other vital parameters. While the PSG is considered a standard for sleep analysis, the PSG may require specialized equipment and clinical settings, making the PSG impractical for routine or large-scale use. In recent years, wearable devices have emerged as an alternative, offering the ability to monitor physiological signals such as heart rate, respiration, and movement during sleep. However, the wearable devices still rely on data acquisition during the sleep period and may be intrusive or uncomfortable for the user.

[0007]

[0004] Despite advancements in sleep monitoring technologies, there remains a significant gap in existing solutions that allow for the assessment of sleep quality without, requiring data collection during sleep. The existing solutions are either too complex, invasive, or dependent on continuous monitoring, which limits their applicability in everyday scenarios. Moreover, these solutions do not provide real-time insights into the cognitive state of an individual during wakefulness, which could be indicative of sleep deprivation or replenishment needs.

[0005] Therefore, there lies a need for an improved solution that can address the above-mentioned issues and the limitations of the existing systems and solutions.

[0008] SUMMARY

[0009]

[0006] This summary is provided to introduce a selection of concepts, in a simplified format, that are further described in the detailed description of the invention. This summary is neither intended to identify key or essential inventive concepts of the invention nor is it intended to determine the scope of the invention.

[0010]

[0007] In accordance with an embodiment of the present disclosure, a method for assessing sleep quality of a subject is disclosed. The method includes obtaining electroencephalogram (EEG) data associated with the subject from one or more electrodes coupled proximal to a cephalic region of the subject, during a wakefulness state. Further, the method includes determining EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time. The transitional sleep state is one of a hypnagogic state and a hypnopompic state. Furthermore, the method includes correlating the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject. Moreover, the method includes determining a deviation based on the correlation. Further, the method includes generating a sleep quality report corresponding to the subject based on the deviation. Furthermore, the method includes predicting, based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject.

[0011]

[0008] According to another embodiment of the present disclosure, a system for assessing sleep quality of a subject is disclosed. The system includes a wearable apparatus worn by the subject, proximal to a cephalic region of the subject, one or more electrodes coupled to the wearable apparatus, and one or more processors in communication with the one or more electrodes. The one or more processors are configured to obtain Electroencephalogram (EEG) data associated with the subject from the one or more electrodes during a wakefulness state. Further, the one or more processors are configured to determine EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time. The transitional sleep state is one of a hypnagogic state and a hypnopompic state. Furthermore, the one or more processors are configured to correlate the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject. Moreover, the one or more processors are configured to determine a deviation based on the correlation and generate a sleep quality report corresponding to the subject based on the deviation. Further, the one or more processors are configured to predict, based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject.

[0012]

[0009] According to another embodiment of the present disclosure, a wearable apparatus for assessing sleep quality of a subject is disclosed. The wearable apparatus includes an article worn by the subject, one or more electrodes coupled with the article and proximal to a cephalic region of the subject, and one or more processors in communication with the one or more electrodes. The one or more processors are configured to obtain Electroencephalogram (EEG) data associated with the subject from the one or more electrodes. The one or more processors are configured to determine EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time. The transitional sleep state is one of a hypnagogic state and a hypnopompic state. The one or more processors are configured to correlate the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject. The one or more processors are configured to determine a deviation based on the correlation and generate a sleep quality report corresponding to the subject based on the deviation. The one or more processors are configured to predict, based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject.

[0013]

[0010] To further clarify the advantages and features of the present invention, a more particular description of the invention will be rendered by reference to specific embodiments thereof, which are illustrated in the appended drawings. It is appreciated that these drawings depict only typical embodiments of the invention and are therefore not to be considered limiting of its scope. The invention will be described and explained with additional specificity and detail in the accompanying dr wi ngs.

[0014] BRIE F DESCRIPTION OF THE DRAWINGS

[0015] [Oil] These and other features, aspects, and advantages of the present invention will become better understood when the following detailed description is read with reference to the accompanying drawings in which like characters represent like parts throughout the drawings, wherein: Figure 1 illustrates an environment for implementing a system with a wearable apparatus for assessing sleep quality of a subject, in accordance with an embodiment of the present disclosure; Figure 2 illustrates a block diagram of the system for assessing the sleep quality of the subject, in accordance with an embodiment of the present disclosure;

[0016] Figure 3 illustrates a cross-sectional view of an exemplary wearable apparatus for assessing the sleep quality of the subject, in accordance with an embodiment of the present disclosure;

[0017] Figure 4 illustrates a process flow' of a method for assessing the sleep quality of the subject, in accordance with an embodiment of the present disclosure; and

[0018] Figure 5 illustrates an example of the wearable apparatus for assessing the sleep quality’ of the subject, in accordance with an embodiment of the present disclosure.

[0019]

[0012] Further, skilled artisans will appreciate that elements in the drawings are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow' charts illustrate the method in terms of the most prominent steps involved to help improve understanding of aspects of the present invention. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show? only those specific details that are pertinent to understanding the embodiments of the present invention so as not to obscure the drawings with details that will be readily apparen t to those of ordinary skill in the art having the benefit of the description herein.

[0020] DETAILED DESCRIPTION

[0021]

[0003] For the purpose of promoting an understanding of the principles of the invention, reference will now be made to the various embodiments, and specific language will be used to describe the same. It will nevertheless be understood that no limita tion of the scope of the invention is thereby intended, such alterations and further modifications in the illustrated system, and such further applications of the principles of the invention as illustrated therein, being contemplated as would normally occur to one skilled in the art to which the invention relates.

[0022]

[0014] The term “some” as used herein is defined as “none, or one, or more than one, or all.” Accordingly, the terms “none,” “one,” “more than one,” “more than one, but not all,” or “all” would all fall under the definition of “some.” The term “some embodiments” may refer to no embodiments or to one embodiment or to several embodiments or to all embodiments. Accordingly, the term “some embodiments’1is defined as meaning “no embodiment, or one embodiment, or more than one embodiment, or all embodiments.”

[0023]

[0015] The terminology and structure employed herein are for describing, teaching, and illuminating some embodiments and their specific features and elements, and do not limit, restrict, or reduce the spirit and scope of the claims or their equivalents.

[0024]

[0016] More specifically, any terms used herein such as but not limited to “includes,” “comprises,” “has,” “consists,” and grammatical variants thereof do NOT specify an exact limitation or restriction and certainly do NOT exclude the possible addition of one or more features or elements, unless otherwise stated, and furthermore must NOT be taken to exclude the possible removal of one or more of the listed features and elements, unless otherwise stated with the limiting language “MUST comprise” or “NEEDS TO include.”

[0025]

[0017] Unless otherwise defined, all terms, and especially any technical and / or scientific terms, used herein may be taken to have the same meaning as commonly understood by one having ordinary' skill in the art.

[0026]

[0018] Reference is made herein to some “embodiments.” It should be understood that an embodiment is an example of a possible implementation of any features and / or elements presented in the attached claims. Some embodiments have been described for the purpose of illuminating one or more of the potential ways in which the specific features and / or elements of the attached claim fulfill the requirements of uniqueness, utility, and non-obviousness.

[0027]

[0019] Use of the phrases and / or terms such as but not limited to “a first embodiment,” “a. further embodiment,” “an alternate embodiment,” “one embodiment,” “an embodiment,” “multiple embodiments,” “some embodiments,” “other embodiments,” “a further embodiment”, “furthermore embodiment”, “additional embodiment” or variants thereof do NOT necessarily refer to the same embodiments. Unless otherwise specified, one or more particular features and / or elements described in connection with one or more embodiments may be found in one embodiment or may be found in more than one embodiment, or may be found in all embodiments, or may be found in no embodiments.

[0028]

[0020] Although one or more features and / or elements may be described herein in the context of only a single embodiment, or the context of more than one embodiment, or further alternatively in the context of all embodiments, the features and / or elements may instead be provided separately or in any appropriate combination or not at all. Conversely, any feature and / or element described in the context of separate embodiments may alternatively be realized as existing together in the context of a single embodiment.

[0029]

[0021] Any particular and all details set forth herein are used in the context of some embodiments and therefore should NOT be necessarily taken as limiting factors to the attached claims. The attached claims and their legal equivalents can be realized in the context of embodiments other than the ones used as illustrative examples in the description below.

[0030]

[0022] Further, skilled artisans will appreciate those elements in the drawings that are illustrated for simplicity and may not have necessarily been drawn to scale. For example, the flow charts illustrate the method in terms of the most prominent steps involved to help improve understanding of aspects of the present disclosure. Furthermore, in terms of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only those specific details that are pertinent to understanding the embodiments of the present disclosure so as not to obscure the drawings with details that will be readily apparent to those of ordinary? skill in the art having the benefit of the description herein.

[0031]

[0023] The present di closure provides a method, a system, and a wearable apparatus for assessing sleep quality of a subject. The present disclosure focuses on data associated with Electroencephalogram (EEG) wave components, including theta, delta, alpha, and beta waves, to evaluate a subject’s cognitive state and, accordingly, predict an amount of sleep required to restore optimal brain function. Unlike the traditional sleep monitoring techniques that require sleep-state measurements, the present disclosure functions during wakefulness, offering real-time feedback on mental fatigue and sleep needs.

[0032]

[0024] An object of the present disclosure is to provide a system and method that overcomes the limitations found in prior art methods, systems, and devices related to neurophysiological assessment techniques.

[0033]

[0025] Another object of the present disclosure is to provide a wearable apparatus that is configured to determine EEG signal characteristics indicative of detection of a transitional sleep state of the subject.

[0034]

[0026] Another object of the present disclosure is to generate a sleep quality report associated with the subject.

[0027] Yet another object of the present disclosure is to predict a sleep duration capable of restoring one or more cognitive functions associated with the subject based on the sleep quality report.

[0035]

[0028] Embodiments of the present invention will be described below in detail with reference to the accompanying drawings.

[0036]

[0029] Figure 1 illustrates an environment for implementing the system 100 with a wearable apparatus 102 for assessing sleep quality of a subject, in accordance with an embodiment of the present disclosure.

[0037]

[0030] In an embodiment, the system 100 may include the wearable apparatus 102 worn by the subject, one or more electrodes 104 coupled to the wearable apparatus 102, and one or more processing units 106 (as illustrated in Figure 2) in communication with the one or more electrodes 104. Further, the wearable apparatus 102, the one or more electrodes 104, and one or more processing units 106 may communicably couple with each other.

[0038]

[0031] In an embodiment, the system 100 may be implemented in the wearable apparatus 104 and may be adapted to operate without interfering with the subject’s routine activities. In another embodiment, the system 100 may interact with a server or a user equipment (UE) such as a smart phone (not shown) to perform data processing for assessing the sleep quality of the subject.

[0039]

[0032] In an embodiment, the wearable apparatus 102 may refer to an article integrated with the one or more electrodes 104, worn by the subject. The wearable apparatus 102 may be configured to facilitate acquisition of neurophysiological data for assessing sleep quality. The wearable apparatus 102 may be positioned proximally to a cephalic region of the subject. In an exemplary scenario, the wearable apparatus 102 may be worn on a head of the subject. The wearable apparatus 102 may be implemented in various wearable formats, including but not limited to smart watches, head bands, helmets, caps, sleep eye masks, smart earbuds, smartwatches, biomedical diagnostic devices, or other body-mounted articles worn proximally to the cephalic region of the subject.

[0040]

[0033] In an embodiment, the one or more electrodes 104 may be indicative of one or more electrically conductive elements that are operatively connected to the wearable apparatus 102. The one or more electrodes 104 may be configured to acquire or obtain or receive electroencephalogram (EEG) signals from the subject during a wakefulness state. In an embodiment, the coupling of the one or more electrodes 104 to the wearable apparatus 102 may facilitate stable and continuous contact with the subject’s skin, thereby enabling accurate acquisition of bioelectrical signals for real-time neurophysiological assessment.

[0041]

[0034] In an embodiment, the one or more processing units 106 may be operatively coupled with the one or more electrodes 104 and are configured to perform signal acquisition, signal processing, and data analysis functions. The one or more processing units 106 may be implemented as microprocessors, microcontrollers, digital signal processors (DSPs), neural processing units (NPUs), optical neural networks (ONNs) or any combination thereof, and are adapted to obtain electroencephalogram (EEG) data from the subject during a wakefulness state. The one or more processing units 106 may also be configured to interface with external or local devices for data transmission and may include embedded artificial intelligence (Al) modules for real-time analysis and adaptive control.

[0042]

[0035] In an embodiment, the one or more processing units 106 may be configured to obtain the EEG data associated with the subject from the one or more electrodes 104 during the wakefulness state. In a non-limiting example, the EEG data may include electrical signals generated by neuronal activity in the brain and may be captured during the wakefulness state of the subject. The EEG data may include various wave components such as alpha, beta, delta, and theta waves, which may be indicative of the subject’s cognitive and neurophysiological state. In a non-limiting example, the wakefulness state may correspond to a neurophysiological condition of the subject associated with active cognitive engagement and absence of sleep.

[0043]

[0036] In an embodiment, the one or more processing units 106 may be configured to determine EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time. In a non-limiting example, the EEG signal characteristics may include, but are not limited to, waveform patterns, frequency components (such as the alpha, the beta, the delta, and the theta waves), amplitude variations, signal coherence, and temporal dynamics. In a non-limiting example, the transitional sleep state is one of a hypnagogic state, a hypnopornpic state, and the wakefulness state associated with the presence of spindle-like activity. In a nonlimiting example, the hypnagogic state corresponds to a transitional neurophysiological condition experienced by the subject during the onset of sleep, i.e., the period between wakefulness and sleep initiation. The hypnagogic state is associated with specific EEG signal patterns, including increased theta wave activity' and reduced beta wave activity, which reflect a gradual decline in cognitive alertness and sensory responsiveness. The hypnopornpic state corresponds to a transitional neurophysiological condition experienced by the subject during emergence from sleep into the wakefulness state. The hypnopompic state is marked by the EEG signal characteristics indicative of reactivation of cognitive functions, including a shift from delta and theta wave dominance toward alpha and beta wave activity.

[0044]

[0037] In an embodiment, the one or more processing units 106 may be configured to correlate the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject. In a non-limiting example, the predefined threshold neurophysiological data may be associated with a sleep adequate state. For instance, the predefined threshold neurophysiological data may represent the EEG wave patterns, such as balanced alpha and beta wave activity, previously recorded from the subject following a night of uninterrupted, high-quality sleep. The predefined threshold neurophysiological data may serve as a benchmark or reference for the sleep adequate state. In an exemplary embodiment, when the EEG signal characteristics may deviate significantly from the predefined threshold neurophysiological data, the system 100 may infer that the subject is experiencing cognitive fatigue or sleep deprivation.

[0045]

[0038] In an embodiment, the one or more processing units 106 may be configured to determine a deviation based on the correlation.

[0046]

[0039] In an embodiment, the one or more processing units 106 may be configured to generate a sleep quality report corresponding to the subject based on the deviation. In a non-limiting example, the sleep quality report may include an assessment of the subject’s neurophysiological condition, including deviations from the predefined threshold neurophysiological data associated with the sleep adequate state. The report may include indicators of cognitive fatigue, transitional sleep state detection (such as the hypnagogic or the hypnopompic states), precise measurement of sleep onset latency, sleep inertia, integrity of sleep architecture, and recommendations for sleep duration required to restore one or more cognitive functions. The sleep quality report may also integrate multimodal physiological parameters such as heart rate variability (HRV), galvanic skin response (GSR), and spindle characteristics to provide a comprehensive evaluation of the subject’s sleep.

[0047]

[0040] In an embodiment, the one or more processing units 106 may be configured to predict, based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject. In a non-limiting example, the one or more cognitive functions may correspond to mental processes associated with the subject’s ability to perceive, think, learn, remember, and respond to stimuli. The one or more cognitive functions may include,

[0048] o but are not limited to, attention, memory, executive function, decision-making, problem-solving, and sensory-motor coordination. Thus, the one or more cognitive functions are assessed through analysis of the EEG signal characteristics that may indicate impairment or fatigue in one or more cogniti ve functions, thereby enabling prediction of the sleep duration required to restore optimal cognitive performance.

[0049]

[0041] In an embodiment, prior to correlation of the EEG signal characteristics, the one or more processing units 106 may be configured to generate one or more auditory stimuli for the subject and acquire the EEG data corresponding to the one or more auditor}' stimuli. In a non-limiting example, the one or more auditory stimuli may be indicative of externally generated sound-based signals that are presented to the subject during wakefulness or transitional sleep states, for the purpose of eliciting measurable neurophysiological responses. In a non-limiting example, the EEG data may include at least one of auditory evoked potentials (AEPs) and auditory steady-state responses (ASSRs). Further, the one or more processing units 106 may be configured to determine the EEG signal characteristics based on the EEG data. In a non-limiting example, the EEG signal characteristics may be indicative of detection of one of: the transitional sleep state or partial sleep stages.

[0050]

[0042] In an embodiment, the one or more processing units 106 may be configured to generate an adaptive sensory intervention for the subject based on the detection of the transitional sleep state. In a non-limiting example, the adaptive sensory intervention may include a recommendation for modulation of one or more interventional properties configured to facilitate a transition of the subject from or into out of sleep. In a non-limiting example, the one or more sensory interventional properties may include light intensity, sound frequency, temperature, haptic or tactile feedback, intended to assist the subject in transitioning into or out of sleep.

[0051]

[0043] For instance, upon detecting the hypnagogic state, the one or more processing units 106 may initiate the adaptive sensory intervention by gradually dimming ambient light and playing low-frequency auditory tones to facilitate sleep onset. Conversely, during the hypnopompic state, the one or more processing units 106 may increase light intensity and introduce stimulating sounds to promote wakefulness.

[0052]

[0044] In an embodiment, the one or more processing units 106 may be configured to modulate the one or more sensory’ interventional properties of the adaptive sensory intervention in real-time based on variation in the EEG signals in real-time. For instance (continuing the example above), the one or more processing units 106 may adjust the sensory interventional properties dynamically and immediately based on continuous EEG signal variation, thereby ensuring timely and personalized support for the subject’s sleep transition.

[0053]

[0045] In an embodiment, the one or more processing units 106 may be configured to receive data corresponding to planned schedule of the subject. The one or more processing units 106 may be configured to predict a circadian rhythm disruption based on the received data. The one or more processing units 106 may be configured to determine a jet lag debt based on the circadian rhythm disruption. The one or more processing units 106 may be configured to mitigate the jet lag debt based on modulation of the adaptive sensory intervention. In a non-limiting example, the circadian rhythm disruption may correspond to a physiological misalignment or disturbance in the subject’s endogenous circadian cycle, which governs the sleep-wake pattern, hormonal secretion, body temperature regulation, and other biological processes over 24 hours. For instance, if the subject is scheduled to travel across multiple time zones, the system 100 may identify a potential disruption in the sleep-wake cycle due to jet lag. Accordingly, the one or more processing units 106 may be configured to determine the jet lag debt resulting from the misalignment between the subject’s internal circadian rhythm and the external environment. To mitigate the jet lag debt, the one or more processing units 106 may be configured to modulate the one or more sensory interventional properties in real-time, thereby facilitating gradual circadian realignment and improving sleep quality and cognitive recovery.

[0054]

[0046] In an embodiment, to correlate the EEG data with the predefined neurophysiological threshold data, the one or more processing units 106 may be configured to extract one or more neurophysiological parameters from the EEG data and compare values of one or more neurophysiological parameters to values corresponding to the predefined threshold neurophysiological data. In a non-limiting example, the one or more neurophysiological parameters may include, but are not limited to, the frequency components of the EEG signals, the amplitude variations, spindle characteristics, the signal coherence, and the temporal dynamics. In another embodiment, the one or more neurophysiological parameters may also encompass multimodal indicators such as the HRV, the GSR, and pressure-modulated vascular responses.

[0055]

[0047] In an embodiment, the one or more processing units 106 may be configured to determine a variation in the spindle characteristics based on analysis of one or more spindle parameters from among the one or more neurophysiological parameters. In an embodiment, the one or more processing units 106 may be configured to determine whether the variation exceeds or falls below a predefined threshold variation. In an embodiment, the one or more processing units 106 may be configured to predict recovery state of the one or more cognitive functions based on the determination that the variation is less than the predefined threshold variation. For instance, if the subject may exhibit heightened spindle density and longer spindle duration in the EEG data acquired during the wakefulness state, the one or more processing units 106 may determine that the variation falls above the predefined threshold variation. Based on the determination, the one or more processing units 106 may predict that the subject is in a state of cognitive fatigue and has not yet achieved sufficient recovery of one or more cognitive functions. Accordingly, the system 100 may recommend a specific sleep duration or initiate the adaptive sensory intervention to facilitate cognitive restoration.

[0056]

[0048] In an embodiment, the one or more processing units 106 may be configured to determine a cognitive fatigue value corresponding to the subject based on the sleep quality report. The one or more processing units 106 may be configured to determine whether the cognitive fatigue value exceeds a predefined threshold value. In a non-limiting example, the predefined threshold value may correspond to a benchmark established based on historical data or normative standards representing an acceptable or optimal cognitive state. The one or more processing units 106 may be configured to generate a notification based on the determination that the cognitive fatigue value exceeds the predefined threshold value. In a non-limiting example, the notification may indicate an alert associated with drowsiness of the subject.

[0057]

[0049] The one or more processing units 106 may be configured to transmit the notification to one or more entities. In a non-limiting example, the one or more entities may be one or more external or internal recipients, systems, devices, or stakeholders that are configured to receive notifications, data, or outputs generated by the one or more processing units 106 of the wearable apparatus 102. The one or more entities may include, but are not limited to, computing devices such as smartphones, smart earphone, smart glass, tablets, smartwatches, medical monitoring systems, cloud-based servers, healthcare professionals, caregivers, or alert management systems. For instance, when the cognitive fatigue value of the subject exceeds the predefined threshold, the one or more processing units 106 may generate the notification, such as initiating a rest protocol, alerting supervisory personnel, or logging the event for health monitoring purposes.

[0050] In another embodiment, the system 100 may be configured to compute a Cognitive Reactivity Index (CRI) to quantitatively assess an extent of the cognitive fatigue and to predict the requisite duration of sleep necessary for restoring optimal cognitive function. The CRI may be derived from the EEG signal characteristics of the EEG data collected during wakeful states. The CRI may represent a percentage-based metric, in which a CRI of 100% may denote no cognitive fatigue, and a CRI of 0% may indicate severe sleep deprivation. The CRI may further be utilized to predict the amount of sleep required for cognitive recovery, either through a lookup table or a machine learning model trained on individual sleep profiles and historical EEG data. For instance, a CRI of 75% may correspond to a requirement of 3-4 hours of additional sleep, whereas a CRI of 50% may indicate a need for 6-8 hours of restorative sleep. The CRI may thus serve as a real-time, non-invasive biomarker for cognitive fatigue and sleep need estimation, enabling proactive cognitive health management.

[0058]

[0051] In an embodiment, the system 100 may be configured to employ a machine learning (ML) model to enhance the accuracy and personalization of sleep replenishment predictions based on the EEG data collected during the wakefulness states. The ML model may be trained on individual sleep profiles, historical EEG patterns, and cognitive performance metrics to generate tailored sleep duration recommendations. The ML model may utilize features extracted from the EEG data to identify deviations from normative baselines. Based on such deviations, the sleep quality report and the CRI may be computed, which may then be mapped to a corresponding sleep requirement of the subject using either the lookup table or the ML-based regression or classification model. The ML model may further adapt over time by incorporating feedback from wearable sleep trackers, smartwatches, and user-reported outcomes, thereby refining the predictive accuracy of sleep need estimations. In an implementation, the ML models may also be configured to detect and classify transitional states such as hypnagogic and hypnopompic phases, seizure activity, or sleep disorders, including narcolepsy, based on real-time bio-signal data. Additionally, edge artificial intelligence (Al) capabilities may be integrated into wearable EEG devices to enable on-device processing of EEG data, thereby reducing latency, preserving data privacy, and providing immediate feedback on cognitive fatigue and sleep quality. The ML model may also support the adaptive sensory interventions, such as personalized auditory cues, light exposure adjustments or haptic feedback, to optimize sleep onset and recovery, thus enabling a closed-loop system for realtime cognitive health management.

[0052] In an embodiment, the system 100 may be configured to perform coherence and connectivity analysis to evaluate the synchronization between different regions of the brain using the EEG data collected during wakeful states. The coherence analysis may involve quantifying the degree of functional connectivity between cortical regions, such as frontal and parietal lobes. The reduced coherence may be indicative of cognitive overload or impaired neural communication, which may further reflect mental fatigue. For instance, hemispheric desynchronization may be assessed by analyzing the correlation between EEG signals from bilateral sensors, such as those on the left and right of a headband, in each EEG Earphone, or embedded in the legs of eyeglass-based EEG wearables.

[0059]

[0053] In an embodiment, the system 100 may be configured to detect and predict seizure activity, particularly in subjects prone to nocturnal seizures. The system 100 may be adapted to identify early neurophysiological indicators, such as epileptiform discharges or other abnormal neurological events, by analyzing the EEG data acquired during the wakefulness state. Furthermore, the system 100 may be configured to leverage the ML model and the edge Al capabilities to continuously refine predictive accuracy. The ML model may be trained on the historical EEG patterns and seizure profiles to enhance the system’s ability to understand the interplay between sleep quality and cognitive health. Accordingly, the system 100 may be configured to support proactive neurological monitoring and timely intervention for seizure management.

[0060]

[0054] In an embodiment, the system 100 may be configured to detect and analyze hypnic jerks, which are sudden, involuntary muscle contractions that may occur during the transition from the wakefulness to the sleep, commonly referred to as the hypnagogic state. The detection of hypnic jerks may be facilitated through the integration of electromyography (EMG) sensors and accelerometers, which may capture muscle activity and motion artifacts associated with such events. The system 100 may correlate the EMG and accelerometer data with the EEG signal characteristics to accurately identify timing and frequency of hypnic jerks. The system 100 may be configured to track the onset of sleep with high precision and may provide insights into the subject’s sleep initiation patterns and overall sleep health. In implementation, the system 100 may utilize the occurrence and characteristics of hypnic jerks as physiological markers to determine the subject's entry into the hypnagogic state and to calculate sleep onset latency (SOL). The system 100 may further utilize the SOL to personalize the adaptive sensory intervention, thereby enhancing the transition into sleep and improving sleep quality.

[0061]

[0055] In an embodiment, the system 100 may be configured to utilize the one or more spindle parameters as key indicators for assessing the cognitive functions and the sleep quality based on the EEG data collected during the wakefulness states. The system 100 may be configured to detect spindle-like activity, which may typically manifest as oscillatory bursts in the 11-16 Hz frequency range, and may persist in wakeful EEG data due to prior sleep deprivation or neurological dysfunction. The system 100 may be configured to quantify spindle density, amplitude, and duration. The spindle density may refer to the number of spindles per epoch, the spindle amplitude may indicate the intensity of oscillations, and the spindle duration may represent the temporal length of individual spindle events. These metrics may be compared against baseline values obtained under optimal cognitive conditions to determine deviations indicative of cognitive impairment. Accordingly, a Spindle Residue Score (SRS) may be computed using a weighted combination of normalized spindle density, amplitude, and duration. Further, a higher SRS value may correlate with increased cognitive fatigue. The SRS may be expressed using expression (1) as shown below:

[0062]

[0063] wherein w1,w2,w3represent adjustable weights corresponding to the spindle density, the amplitude, and the duration.

[0064]

[0056] The system 100 may be configured to further correlate spindle variability with cognitive performance under stress, enabling early detection of subclinical cognitive decline. In implementation, the one or more spindle parameters may also be used to detect sleep state misperception, narcolepsy, or other sleep-related disorders by identifying abnormal spindle activity during wakefulness. The integration of spindle analysis into the EEG signal characteristics may enhance the accuracy of indices such as the sleep quality report and the CRI.

[0065]

[0057] In an embodiment, the system 100 may be configured to compute a perquisite sleep index (PSI) to evaluate sleep deficiency and impact of the sleep deficiency on the cognitive function and performance. The PSI may aggregate multiple sleep-related parameters, including but not limited to sleep duration, sleep efficiency, stage distribution, and continuity, into a unified score that may reflect the overall quality and sufficiency of sleep. A higher PSI score may indicate a greater sleep deficit, which may correlate with reduced cognitive performance, including impairments in memory, attention, and emotional regulation. The PSI may be used in conjunction with the EEG data collected during the wakefulness state and the sleep states to provide comprehensive assessment of sleep health. In implementation, the PSI may also be employed to detect sleep state misperception or paradoxical insomnia by identifying discrepancies between objective EEG-derived sleep metrics and the user’s subjective perception of sleep quality. Furthermore, the PSI may assist in identifying and tracking sleep-related disorders such as chronic fatigue syndrome (CFS), excessive daytime sleepiness (EDS), delayed and advanced sleep phase syndromes (DSPS / ASPS), non-24-hour sleep-wake disorder, hypersomnia, obstructive sleep apnea, and parasomnias. The PSI may be integrated into the system’s adaptive feedback mechanism to recommend targeted interventions aimed at improving sleep hygiene and cognitive recovery.

[0066]

[0058] Figure 2 illustrates a block diagram of the system 100 for assessing the sleep quality of the subject, in accordance with an embodiment of the present disclosure.

[0067]

[0059] In an embodiment, the system 100 may include at least one processor 202, a memory 204, a plurality of units 206, a data unit 208, and the wearable apparatus 102. The at least one processor 202, the memory 204, the plurality of units 206, the data unit 208, and the wearable apparatus 102 are communi cably coupled with each other.

[0068]

[0060] In an embodiment, the at least one processor 202 may be in communication with the memory 204. The at least one processor 202 may be a single processing unit or several units, all of which could include multiple computing units. The at least one processor 202 may be implemented as one or more microprocessors, microcomputers, microcontrollers, digital signal processors, central processing units, state machines, logic circuitries, and / or any devices that manipulate signals based on operational instructions. Among other capabilities, the at least one processor 202 may be configured to fetch and execute computer-readable instructions and data stored in the memory 204. Further, the at least one processor 202 may be in communication with the one or more processing units 106 of the wearable apparatus 102.

[0069]

[0061] In an embodiment, the memory 204 may include any non-transitory computer-readable medium known in the art including, for example, volatile memory, such as static random access memory (SRAM) and dynamic random access memory (DRAM), and / or non-volatile memory, such as read-only memory (ROM), erasable programmable ROM, flash memories, hard disks, optical disks, and magnetic tapes.

[0062] In an embodiment, the plurality of modules 206 may be configured to assess the sleep quality of the subject.

[0070]

[0063] In some embodiments, the plurality of modules 206 may include a set of instructions that can be executed to cause the processing unit 112 to perform any one or more of the methods disclosed. The processing unit 112 may operate as a standalone device or may be connected, e.g., using a network, to other computer systems or peripheral devices. Further, while a single processing unit 112 is illustrated, the term “processing unit” shall also be taken to include any collection of processing units, implemented across the wearable device 100 that individually or jointly execute a set, or multiple sets, of instructions to perform one or more computer functions.

[0071]

[0064] In an embodiment, the plurality of modules 206 may be implemented using one or more artificial intelligence (Al) units or foundational models that may include a plurality of neural network layers. Examples of neural networks include, but are not limited to, transformer neural network (TNN), convolutional neural network (CNN), deep neural network (DNN), recurrent neural network (RNN), and Restricted Boltzmann Machine (RBM). Further, ‘learning’ may be referred to in the disclosure as a method for training a predetermined target device (for example, a robot) using a plurality of learning data to cause, allow, or control the target device to decide or predict. Examples of learning techniques include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, reinforcement learning or self-attention mechanisms. At least one of a plurality of TNN, CNN, DNN, RNN, RMB models and the like may be implemented to thereby achieve execution of the present subject matter’s mechanism through an Al model. A function associated with an Al unit may be performed through the non-volatile memory, the volatile memory, and the processor. The processor 202 may include one or a plurality of processors. At this time, one or a plurality of processors may be a general-purpose processor, such as a central processing unit (CPU), an application processor (AP), or the like, a graphics-only processing unit such as a graphics processing unit (GPU), a visual processing unit (VPU), an optical neural network (ONN) and / or an Al-dedicated processor, such as a neural processing unit (NPU). One or a plurality of processors control the processing of the input data in accordance with a predefined operating rule or artificial intelligence (AI) model stored in the non-volatile memory and the volatile memory. The predefined operating rule or artificial intelligence model is provided through training or learning.

[0072] 17

[0065] In an embodiment, the data unit 208, amongst other things, includes routines, programs, objects, components, data structures, and the like, which perform tasks or implement data types. The data unit 208 may also be implemented as signal processor(s), state machine(s), logic circuitries, and / or any other device or component that manipulates signals based on operational instructions. Further, the data unit 208 may be implemented in hardware, instructions executed by a processing unit, or by a combination thereof. The processing unit may comprise a processor, such as the at least one processor 202, a state machine, a logic array, or any other suitable device capable of processing instructions. The processing unit may be a general-purpose processor that executes instructions to cause the general-purpose processor to perform the required tasks, or the processing unit can be dedicated to performing the required functions. In another embodiment of the present disclosure, the data unit 208 may be machine-readable instructions (software) that, when executed by the processor 202, perform any of the described functionalities.

[0073]

[0066] Figure 3 illustrates a cross-section view of an exemplary wearable apparatus 102, in accordance with an embodiment of the present disclosure.

[0074]

[0067] As shown, the wearable device 102 may comprise an article worn by the subject, such as an earphone, as depicted. In a non-limiting example, the article may correspond to any wearable item adapted to be worn by the subject, particularly in proximity to the cephalic region, and configured to facilitate integration of the one or more electrodes 104 for acquisition of bio-signal data. In a non-limiting example, the article may include, but is not limited to, headbands, caps, helmets, sleep eye masks, smart earbuds, smartwatches, smart glasses, biomedical diagnostic devices, or other body-mounted accessories.

[0075]

[0068] In an embodiment, the wearable apparatus 100 may be configured to maintain stable contact with the skin surface to ensure accurate signal acquisition and user comfort during prolonged usage. The wearable device 102 may be adapted to acquire bio-signal data, including, but not limited to, the EEG, electromyography (EMG), and electrocardiogram (ECG) or EKG data. The bio-signal data may be utilized for assessing the sleep quality of the subject based on signal signatures obtained during wakefulness and sleep states. The wearable device 102 may include the one or more electrodes 104 disposed on a connecting arm 302. The placement and configuration of the one or more electrodes 104 may be optimized to ensure high-fidelity signal acquisition, thereby enabling real-time monitoring of neurophysiological parameters relevant to sleep quality assessment. Further, the connecting arm 302 may be mechanically supported by a dynamic size- adjusting mechanism 304. The dynamic size-adjusting mechanism 304 may be configured to adapt the positioning of the electrodes 104 in proximity to the cephalic region of the subject, thereby facilitating optimal signal acquisition. The arrangement shown in Figure 3 may enable real-time monitoring and analysis of neurophysiological signals, which may be further processed to determine sleep-related parameters.

[0076]

[0069] In an embodiment, the wearable apparatus 100 may further comprise the one or more processing units 106 communicatively coupled with the one or more electrodes 104. The one or more processing units 106 may be configured to obtain the EEG data associated with the subject from the one or more electrodes 104 during the wakefulness state. The processing units 106 may be further configured to determine EEG signal characteristics indicative of the detection of the transitional sleep state. In a non-limiting example, the transitional sleep state may be one of the hypnagogic state and the hypnopompic state. In a non-limiting example, the EEG signal characteristics may include waveform patterns, frequency components, amplitude variations, and temporal dynamics, which may be analyzed in real-time to identify neurophysiological transitions associated with sleep onset or emergence.

[0077]

[0070] In an embodiment, the one or more processing units 106 may be configured to correlate the EEG signal characteristics with the predefined threshold neurophysiological data corresponding to the subject.

[0078]

[0071] In an embodiment, the one or more processing units 106 may be configured to determine the deviation based on the correlation and generate the sleep quality report corresponding to the subject based on the deviation.

[0079]

[0072] In an embodiment, the one or more processing units 106 may be configured to predict, based on the sleep quality report, the sleep duration capable of restoring the one or more cognitive functions associated with the subject.

[0080]

[0073] The detailed explanation of each step has been provided in the accompanying diagrams and is not repeated herein for the sake of conciseness.

[0081]

[0074] Figure 4 illustrates a process flow' of a method for assessing the sleep quality of the subject, in accordance with an embodiment of the present disclosure.

[0082]

[0075] The method 400 may be a computer-implemented method executed, for example, by the one or more processing units 106 of the wearable device 102. For the sake of brevity’, constructional and operational features of the wearable device 102 that are already explained in the description of Figures 1-3 are not explained in detail in the description of Figure 4.

[0083]

[0076] At step 402, the method 400 may include obtaining the EEG data associated with the subject from the one or more electrodes 104 during the wakefulness state. In a non-limiting example, the EEG data may comprise electrical signals generated by neuronal activity in the brain and is captured during the wakefulness state of the subject. The EEG data may include various wave components such as alpha, beta, delta, and theta waves, which are indicative of the subject’s cognitive and neurophysiological state. In a non-limiting example, the wakefulness state may correspond to a neurophysiological condition of the subject associated with active cognitive engagement and absence of sleep.

[0084]

[0077] At step 404, the method 400 may include determining the EEG signal characteristics indicative of the detection of a transitional sleep state based on analysis of the EEG data in real time. In a non-limiting example, the EEG signal characteristics may include, but are not limited to, the waveform patterns, the frequency components (such as the alpha, the beta, the delta, and the theta waves), the amplitude variations, the signal coherence, and the temporal dynamics. In a non-limiting example, the transitional sleep state is one of the hypnagogic state, the hypnopompic state and the wakefulness state associated with the presence of spindle-like activity.

[0085]

[0078] At step 406, the method 400 may include correlating the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject. In a non-limiting example, the predefined threshold neurophysiological data may be associated with a sleep adequate state.

[0086]

[0079] At step 408, the method 400 may include determining the deviation based on the correlation.

[0087]

[0080] At step 410, the method 400 may include generating the sleep quality report corresponding to the subject based on the deviation.

[0088]

[0081] At step 412, the method 400 may include predicting, based on the sleep quality report, the sleep duration capable of restoring one or more cognitive functions associated with the subject.

[0089]

[0082] In an embodiment, prior to correlating the EEG signal characteristics, the method 400 may include generating the one or more auditory stimuli for the subject and acquiring the EEG data corresponding to the one or more auditory stimuli. In a non-limiting example, the one or more auditory stimuli may be indicative of externally generated sound-based signals that are presented to the subject during wakefulness or transitional sleep states, for the purpose of eliciting measurable neurophysiological responses. In a non-limiting example, the EEG data may include at least one of auditory evoked potentials (AEPs) and auditory steady-state responses (ASSRs). Further, the method 400 may include determining the EEG signal characteristics based on the EEG data. In a non-limiting example, the EEG signal characteristics may be indicative of detection of one of: the transitional sleep state or partial sleep stages.

[0090]

[0083] In an embodiment, the method 400 may include generating the adaptive sensory intervention for the subject based on the detection of the transitional sleep state. In a non-limiting example, the adaptive sensory intervention may include the recommendation for modulation of the one or more sensory interventional properties configured to facilitate the transition of the subject from in or out of sleep. In a non-limiting example, the one or more sensory interventional properties may include light intensity, sound frequency and intensity, temperature, haptic or tactile feedback, intended to assist the subject in transitioning into or out of sleep.

[0091]

[0084] In an embodiment, the method 400 may include modulating the one or more sensory' interventional properties of the adaptive sensory intervention in real-time based on variation in the EEG signals in real-time.

[0092]

[0085] In an embodiment, the method 400 may include receiving the data corresponding to the planned schedule of the subject. The one or more processing units 106 may be configured to predict the circadian rhythm disruption based on the received data. The one or more processing units 106 may be configured to determine the jet lag debt based on the circadian rhythm disruption. The one or more processing units 106 may be configured to mitigate the jet lag debt based on modulation of the adaptive sensory intervention.

[0093]

[0086] In an embodiment, for correlating the EEG data with the predefined threshold data, the method 400 may include extracting the one or more neurophysiological parameters from the EEG data and comparing values of the one or more neurophysiological parameters to values corresponding to the predefined threshold neurophysiological data. In a non-limiting example, the one or more neurophysiological parameters may include, but are not limited to, the frequency components of the EEG signals, the amplitude variations, spindle characteristics, the signal coherence, and the temporal dynamics. In another embodiment, the one or more neurophysiological parameters may also encompass multimodal indicators such as HRV, GSR, and the pressure-modulated vascular responses.

[0087] In an embodiment, the method 400 may include determining the variation in the spindle characteristics based on analysis of the one or more spindle parameters from among the one or more neurophysiological parameters. In an embodiment, the method 400 may include determining whether the variation exceeds or falls below the predefined threshold variation. In an embodiment, the method 400 may include predicting the recovery state of the one or more cognitive functions based on the determination that the variation is less than the predefined threshold variation.

[0094]

[0088] In an embodiment, the method 400 may include determining the cognitive fatigue value corresponding to the subject based on the sleep quality report. In an embodiment, the method 400 may include determining whether the cognitive fatigue value exceeds the predefined threshold value. In a non-limiting example, the predefined threshold value may correspond to a benchmark established based on historical data or normative standards representing an acceptable or optimal cognitive state. In an embodiment the method 400 may include generating the notification based on the determination that the cognitive fatigue value exceeds the predefined threshold value. In a non-limiting example, the notification may indicate the alert associated with drowsiness of the subject.

[0095]

[0089] In an embodiment, the method 400 may include transmitting the notification to the one or more entities. In a non-limiting example, the one or more entities may be the one or more external or internal recipients, systems, devices, or stakeholders that are configured to receive notifications, data, or outputs generated by the one or more processing units 106 of the wearable apparatus 102. The one or more entities may include, but are not limited to, computing devices such as smartphones, tablets, smartwatches, smart earphones, smart glasses, medical monitoring systems, cloud-based servers, healthcare professionals, caregivers, or alert management systems.

[0096]

[0090] Figure 5 illustrates an example of the wearable apparatus 500 for instance a smart glass for assessing the sleep quality of the subject, in accordance with an embodiment of the present disclosure.

[0097]

[0091] As shown, the wearable apparatus 500 may be adapted to be worn on eyes (proximal to cephalic region) by the subject and may be configured for the acquisition of bio-signal data from an electrode array coupled to the wearable apparatus 500. The electrode array 502 may include the one or more electrodes 104 positioned to establish contact with the subject’s skin, particularly in proximity to the cephalic region, thereby enabling acquisition of neurophysiological signals such as the EEG data.

[0092] The wearable apparatus 500 may further include a signal processing unit 504 operatively coupled to the electrode array 502. The signal processing unit 504 may be configured to receive raw bio-signal data (such as the EEG data) from the electrode array 502 and may perform preliminary filtering, amplification, and digitization of the acquired EEG data to obtain processed EEG data. The processed EEG data may be transmitted to a remote computing device, such as the UE or may be stored locally for further analysis. The arrangement shown in Figure 5 may demonstrate a scalable and modular design wherein the electrode array 502 may be distributed across the surface of the wearable apparatus 500. The arrangement may facilitate enhanced spatial resolution and signal fidelity during acquisition, thereby improving the accuracy of sleep quality assessment and detection of transitional sleep states. The detailed explanation of processing of the EEG data has been provided in the aforesaid paragraphs and is not repeated herein for the sake of conciseness.

[0098]

[0093] In an exemplary use case, a commercial airline may deploy the system 100 in the form of EEG- integrated crew caps (the wearable apparatus 104) worn by flight personnel (the subject) during long-haul operations. During the course of a transcontinental flight, the system 100 may continuously monitor the EEG signals of the flight personnel (the subject, such as the pilot or cabin crew) through embedded electrodes 104 positioned within an inner lining of the cap (the wearable apparatus 104). The EEG data, collected during wakefulness states may be processed in real-time to extract the EEG signal characteristics, such as theta and delta wave activity. Upon detecting deviations from baseline (the predefined threshold neurophysiological data) of the EEG signal characteristics, the system 100 may compute the sleep quality report or the CRI value. For instance, a CRI value of 45% indicates significant cognitive fatigue. Based on this CRI value, the system 100 may automatically generate a recommendation for a rest break and may transmit an alert to the airline operations center. The system 100 may further suggest a rotation of duties to mitigate the risk of performance degradation, especially in case of critical roles like piloting the flight. Additionally, the system 100 may integrate the HRV and the GSR data to provide a comprehensive assessment of the crew7member’s physiological and cognitive state, thereby enhancing flight safety and operational efficiency.

[0099]

[0094] In an embodiment, in addition to detecting transitional hypnagogic and hypnopompic signatures, the system, method and wearable apparatus also facilitate identification and quantification of sleep-associated neurophysiological traits that manifest during wakefulness and are predictive of sleep need. The sleep-associated neurophysiological traits may include but are not limited to Theta-Beta Ratio, Alpha attenuation and interstice Alpha coherence, transient Theta intrusions, localized Delta bursts, spindle like residual activity, and alternating Alpha-Theta microstate cycles. Further, the quantitative indices associated with the sleep-associated neurophysiological traits may include the SRS), the CRI, a Wake-State Instability metric (WSI), and a Slow-Wave Carryover measure (SWC). These indices are computed from the EEG data obtained during wakefulness state using standard signal analyses such as power spectral density, time-frequency decomposition, spindie detection, coherence and connectivity’ analysis, microstate segmentation, and event-related potential latency measures (for example P300 latency), optionally augmented by machine learning regression or classification models trained on individualized baselines.

[0100] 095] In an embodiment, the system, method and wearable apparatus may further integrate multimodal wakeful measures to strengthen prediction accuracy, including heart rate variability, electrodermal activity, oculometnc features (such as blink rate and slow eye movements) and accelerometry. Further, comparison of the extracted wakeful indices to predefined subject-specific baseline values obtained after restorative sleep yields a deviation metric that is used to generate the sleep quality report and to predict the amount of sleep required to restore cognitive functions. The wakeful-state indices and any model-based mapping to required sleep duration are usable to trigger adaptive sensory interventions, notifications, or scheduling recommendations, and are achievable without acquiring EEG during nocturnal sleep.

[0101]

[0096] In an embodiment, the assessment of wakefulness and transitional sleep states may further employ auditory stimulation and analysis of corresponding neurophysiological responses as an objective indicator of sleep onset latency and sleep adequacy. The auditory stimulation may include but not limited to tone bursts, amplitude-modulated noise, or speech segments, and may be presented to the subject during wakefulness or transitional phases, while the one or more electrodes acquire event-related EEG responses including auditory evoked potentials (AEPs) and auditory steady-state responses (ASSRs). Further, auditory responses such as progressive attenuation of AEP amplitude, delay in peak latency, or reduction in phase locking to the auditory stimulus may serve as an indicator of cortical disengagement and impending sleep onset. The magnitude and timing of the auditory’ responses, compared against baseline wakeful responses obtained after restorative sleep, provide an additional quantitative measure of cognitive fatigue and neurophysiological sleep quality. In addition, the integration of auditory-response metrics with sleep-associated neurophysiological traits such as the Theta-Beta ratio, spindle residue score, and cognitive reactivity index enhances the system’s capability to determine real-time sleep pressure and predict the restorative sleep duration required, all without the need for data collection during nocturnal sleep.

[0102]

[0097] The present disclosure provides various advantages as mentioned below:

[0103] a) The present disclosure enables integration of the one or more electrodes into the article worn by the subject, such as caps, headbands, glasses, earphones, thereby ensuring that the monitoring system does not interfere with the subject’s routine activities or cause discomfort during prolonged usage.

[0104] b) The present disclosure facilitates continuous EEG analysis, thereby providing immediate feedback on the subject’s cognitive function levels. The real-time assessment supports timely interventions to prevent performance degradation in cognitively demanding tasks. c) The present disclosure may be configured to integrate EEG data with other physiological parameters such as heart rate variability (HRV) and galvanic skin response (GSR). Thus, enabling a holistic understanding of the subject’s mental and physical state.

[0105] d) The present disclosure ensures that the subject receives timely recommendations for rest or recovery based on assessment of sleep quality and cognitive functions in real-time. Thus, contributing to improved performance, well-being, and safety across various operational environments, including healthcare, transportation, education, and industrial sectors.

[0106]

[0098] As would be apparent to a person in the art, various working modifications may be made to the method to implement the inventive concept as taught herein. The drawings and the foregoing description give examples of embodiments. Those skilled in the art will appreciate that one or more of the described elements may well be combined into a single functional element. Alternatively, certain elements may be split into multiple functional elements. Elements from one embodiment may be added to another embodiment. For example, orders of processes described herein may be changed and are not necessarily limited to the manner described herein.

[0107]

[0099] Moreover, the actions of any signal flow' diagram need not be implemented in the order shown; nor do all of the acts necessarily need to be performed. Also, those acts that are not dependent on other acts may be performed in parallel with the other acts.

Claims

I CLAIM:

1. A method (400) for assessing sleep quality of a subject, the method (400) comprising: obtaining (402) electroencephalogram (EEG) data associated with the subject from one or more electrodes (104) coupled proximally to a cephalic region of the subject, during a wakefulness state,determining (404) EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time;correlating (406) the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject;determining (408) a deviation based on the correlation;generating (410) a sleep quality report corresponding to the subject based on the deviation; andpredicting (412), based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject.

2. The method (400) as claimed in claim 1, wherein prior to correlating (406) the EEG signal characteristics comprises:generating one or more auditory stimuli for the subject;acquiring the EEG data corresponding to the one or more auditory stimuli, wherein the EEG data comprises at least one of auditory evoked potentials (AEPs) and auditory steady-state responses (ASSRs); anddetermining the EEG signal characteristics based on the EEG data, wherein the EEG signal characteristics indicative of detection of one of: the transitional sleep state or partial sleep stages.3, The method (400) as claimed in claim 1 comprising:generating an adaptive sensory intervention for the subject based on the detection of the transitional sleep state, wherein the adaptive sensory intervention comprises a recommendation for modulation of one or more sensory interventional properties configured to facilitate a transition of the subject from into or out of sleep and wherein the transitionalsleep state is one of: a hypnagogic state, a hypnopompic state and a wakefulness state associated with presence of spindle-like activity; andmodulating the one or more sensory interventional properties of the adaptive sensory intervention in real-time based on variation in the EEG signals in real-time.

4. The method (400) as claimed in claim 3, comprising:receiving data corresponding to planned schedule of the subject;predicting a circadian rhythm disruption based on the received data; determining a jet lag debt based on the circadian rhythm disruption; and mitigating the jet lag debt based on modulation of the adaptive sensory intervention.

5. The method (400) as claimed in claim 1, wherein correlating the EEG signal characteristics with the predefined threshold data comprises:extracting one or more neurophysiological parameters from the EEG signal characteristics; andcomparing values of one or more neurophysiological parameters to values corresponding to the predefined threshold neurophysiological data, wherein the predefined threshold neurophysiological data is associated with a sleep adequate state.

6. The method (400) as claimed in claim 1, wherein prior to generating the sleep quality report, the method comprises:receiving physiological data obtained from one or more sensors coupled to a body of the subject; andcorrelating the EEG signal characteristics with the physiological data, for generating the sleep quality report.

7. The method (400) as claimed in claim 5, comprising:determining a variation in spindle characteristics based on analysis of one or more spindle parameters from among the one or more neurophysiological parameters;determining whether the variation exceeds or falls below a predefined threshold variation; andpredicting a recovery state of the one or more cognitive functions based on the determination that the variation is less than the predefined threshold variation.

8. The method (400) as claimed in claim 1 comprising:determining a cognitive fatigue value corresponding to the subject based on the sleep quality report;determining whether the cognitive fatigue value exceeds a predefined threshold value; generating a notification based on the determination that the cognitive fatigue value exceeds the predefined threshold value, wherein the notification indicates an alert associated with drowsiness of the subject; andtransmitting the notification to one or more entities.

9. The method (400) as claimed in claim 1, comprising:generating one or more recommendations for the subject to restore the one or more cognitive functions.

10. A system (100) for assessing sleep quality of a subject, the system (100) comprising:a wearable apparatus (102) worn by the subject, proximal to a cephalic region of the subject;one or more electrodes (104) coupled to the wearable apparatus (102); and one or more processing units (106) in communication with the one or more electrodes (104), the one or more processing units (106) configured to:obtain Electroencephalogram (EEG) data associated with the subject from the one or more electrodes (104) during a wakefulness state;determine EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time;correlate the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject;determine a deviation based on the correlation;generate a sleep quality report corresponding to the subject based on the deviation; andpredict, based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject.

11. The system (100) as claimed in claim 10, the one or more processing units (106) configured to:generate an adaptive sensory intervention for the subject based on the detection of the transitional sleep state, wherein the adaptive sensory intervention comprises a recommendation for modulation of one or more sensory’ interventional properties configured to facilitate a transition of the subject from into or out of sleep and wherein the transitional sleep state is one of a hypnagogic state, a hypnopompic state and a wakefulness state associated with presence of spindle-like activity’; andmodulate the one or more sensory interventional properties of the adaptive sensory intervention in real-time based on variation in the EEG signals in real-time.

12. The system (100) as claimed in claim 10, wherein to correlate the EEG data with the predefined threshold data, the one or more processing units (106) configured to:extract one or more neurophysiological parameters from the EEG data; and compare values of one or more neurophysiological parameters to values corresponding to the predefined threshold neurophysiological data, wherein the predefined threshold neurophysiological data is associated with a sleep adequate state.

13. A wearable apparatus (102) for assessing sleep quality of a subject, the wearable apparatus (102) comprising:an article worn by the subject;one or more electrodes (104) coupled with the article and proximal to a cephalic region of the subject; andone or more processing units (106) in communication with the one or more electrodes (104), the one or more processing units (106) configured to:obtain Electroencephalogram (EEG) data associated with the subject from the one or more electrodes (104) during a wakefulness state;determine EEG signal characteristics indicative of detection of a transitional sleep state based on analysis of the EEG data in real time, wherein the transitional sleep state is one of a hypnagogic state, a hypnopompic state and a wakefulness state associated with presence of spindle-like activity;correlate the EEG signal characteristics with predefined threshold neurophysiological data corresponding to the subject;determine a deviation based on the correlation;generate a sleep quality report corresponding to the subject based on the deviation; andpredict, based on the sleep quality report, a sleep duration capable of restoring one or more cognitive functions associated with the subject.

Images