51 results about "Motor behavior" patented technology

An automated intelligent computer system for analyzing motor or locomotor behavior and method of use is provided. The system comprises an automatic, objective, fast and consistent assessment of the level of injury and course of recovery in animal models of spinal cord injury and other gait and motor coordination disorders. The system also is useful for analyzing other types of motor or neurologic dysfunction.

The invention relates to the video image processing and identification technology field, provides a bus passenger flow statistics method based on multi-motion passenger behavior analysis and can settle disadvantages of error judgement and missing judgement existing in a passenger flow statistical method in the prior art during number statistics of passengers in a bus to effectively improve number statistics accuracy of the passengers in the bus. The method comprises steps that: video images of getting-up-and-down passengers are acquired; processing on the acquired images is acquired to extract passenger head targets, and rectangle frames are generated to limit the extracted passenger head targets; matching for centroid points of adjacent frames is carried out in combination with distances of centroid points of the passenger head targets, position information of the centroid points is updated and stored, and each centroid point is connected to acquire a movement locus; locus clustering on the acquired movement locus is carried out to analyze movement behaviors of the passengers; a number statistics result is acquired through counting and determination.

The invention discloses a method for carrying out toxicity analysis on tail water of a sewage treatment plant by using caenorhabditis elegans. The method comprises the following steps of (1) cultivation of the caenorhabditis elegans; (2) cultivation of escherichia coli OP 50; (3) anabiosis of the caenorhabditis elegans; (4) passage of caenorhabditis elegans; (5) synchronization of the caenorhabditis elegans; and (6) testing the comprehensive toxicity of a to-be-detected tail water sample by using the caenorhabditis elegans. The method provided by the invention has the beneficial effects that model organism-caenorhabditis elegans is utilized to carry out toxicity analysis on the tail water of the sewage treatment plant, and the size of the comprehensive toxicity of the waste water is judged by contrasting the difference of fatality rate, reproduction rate, motor behavior and generation cycle of nematodes and exposing nematodes of a blank control group.

The invention discloses a human body abnormal behavior identification method based on a monitoring system; the method comprises the following steps: 1, sample image input; 2, foreground extraction; 3, background updating; 4, foreground image denoising process; 5, motion target tracking and recording: using a Mean-Shift target tracking algorithm to track the foreground image after denoising, and recording the motion information of the motion target; 6, behavior feature extraction: using a background differencing method to extract a motion area of the motion target according to the motion target motion information recorded in step5, and selecting a foreground image with features according to the motion target motion behaviors; 7, building a standard behavior database; 8, result analysis and abnormity determinations; 9, abnormity alarming. The method can improve the foreground image clearness, and can improve the abnormity behavior determination accuracy.

The invention provides a simulation system of a current responding three-phase permanent magnet synchronous motor. The simulation system comprises a three-phase DC / AC power electronic converter, a three-phase passive impedance network, a current control circuit and a motor behavior processor; the three-phase DC / AC power electronic converter and the three-phase passive impedance network are used for simulating the current responding characteristic of the current responding three-phase permanent magnet synchronous motor, and exchanging electrical energy with an external motor drive system; the current control circuit is used for closed-loop control on the current of a three-phase alternating current power port of the simulation system; and the motor behavior processor is used for generating a current reference signal of the current control circuit according to a voltage signal of the three-phase alternating current power port of the simulation system and an input load torque signal, and outputting a corresponding motor speed signal and a motor rotor position signal. The simulation system can be directly connected with a real motor drive system and exchange electrical energy, thus realizing an all-electronic motor drive test, and improving the test efficiency and the safety.

The invention provides a three-phase simulator of a current-response permanent magnet synchronous motor and a drive system thereof. The three-phase simulator comprises at least two three-phase DC / AC converters, an electrical impedance network, a direct current power supply, a drive behavior processor, a motor behavior processor, a voltage control link and a current control link. Each three-phase DC / AC converter is used to simulate the working status of the permanent magnet synchronous motor and the drive system thereof at the circuit level. The drive behavior processor is used to simulate theelectrical characteristics of the drive system. The motor behavior processor is used to simulate the electrical and mechanical behavior characteristics of the permanent magnet synchronous motor. According to the invention, the simulator can simulate voltage applied to the three-phase permanent magnet synchronous motor port by the drive system and the current response of the permanent magnet synchronous motor to the voltage, so as to simulate the dynamic and static electrical and mechanical behaviors of the permanent magnet synchronous motor and the drive system thereof; the simulator can realize all-electric experiment and test of the motor and the drive system thereof; the test cost is saved; and the test efficiency and safety are improved.

The invention provides a method for analyzing correlations between motor behavior and cognitive ability. The method includes the steps of extracting a motion feature set from motor behavior data, wherein the motion feature set reflects behavior features; adopting an iterative random forest to select an optimal feature subset for detecting the cognitive ability from the motion feature set; adopting the optimal feature subset to acquire analysis results of the correlations between the motor behavior and the cognitive ability by the adoption of a classifier. According to the method for analyzing the correlations between the motor behavior and the cognitive ability, the correlations between the motor behavior and the cognitive ability can be effectively analyzed, and especially for a data set with unbalanced small samples, the recognition rate of patients suffering from cognitive disorders can be increased.

The invention provides a somatosensory motion simulation system. The simulation system comprises a user gravity center movement data acquisition unit, a standard movement model generation unit, a processing unit, a safety protection unit and a teaching unit. According to the simulation system provided by the invention, the gravity center movement data of a user can be collected in real time, whether the movement of the user is standard or not is analyzed according to the gravity center movement data of the user, when great deviation exists between the movement of the user and the standard movement, prompt is given out or the on-going movement is controlled, so that the movement behavior of the user is corrected and improved, further, the user masters the essential of the movement rapidly,therefore, the safety of the movement is guaranteed, in addition, the system has the functions of timely protection, movement body sensing and motion load generation and management, thus the user canbe helped to overcome the psychological disorder, the waist, back and leg strength is increased, and the training comprehensive effect is promoted.

A cognitive / multisensory stimulation system simulates sports scenarios during real sports actions for assessing, profiling, training, or improving performance of athletes or other populations. Cognitive / multisensory training can be provided by: establishing with an athlete a sensory semantic language for relating a number of sensory signals to corresponding possible actions, the sensory semantic language being essentially new to the athlete; instructing the athlete to perform an athletic exercise involving skills and full body movement; providing during exercise sensory signals to the athlete to require rapid discernment by the athlete of the semantic meaning of the sensory signal to correctly chose one possible action; and determining whether the athlete correctly responds to the selected sensory signal during said exercise.

Athletic performance monitoring and tracking may provide multiple ways in which to track athletic movement and activity. Workouts may also be tagged with various parameters including mood, weather, terrain, athletic equipment, friends used and the like. Workout information may be shared to social messaging and networking outlets. Workout information shared may include map information including images of maps, interactive maps, links to maps, route information and the like and / or combinations thereof. Additionally or alternatively, an application may be configured to execute within a context of a social networking system to facilitate athletic activity data transfer and generation of workout entries in the social networking site.

The invention discloses a child behavior and motion trail monitoring system and method. The system comprises a CPU (central processing unit) as well as a motion sensor, a human body sign detector, a GPS (global positioning system) positioning and tracking module, a displayer and a wireless receiving and transmitting unit which are connected with the CPU, wherein the wireless receiving and transmitting unit is connected with a background database server and wirelessly connected with a smart phone. The comprehensive scheme integrates big data acquisition, analysis and application, on the basis of trail positioning and tracking, a motion behavior trail and APP virtual pet game manner is imported, and the motion condition of a child is dynamically reflected through pet feeding growth postures derived from child motion amount converted energy values, so that parent-child communication is established and promoted. The system and the method can be applied to child positioning and child motion behavior tracking and monitoring, arouse the motion interest of the child, develop the motion behavior habit of the child and play an important role in the personality molding and physical growth process of the child.

The invention provides application of an aminoadamantane mononitrate compound in preparation of drugs for preventing and treating diseases such as glaucoma, vascular dementia, subarachnoid hemorrhage and pulmonary arterial hypertension. Discovered by experiments, the aminoadamantane mononitrate compound can be combined with an NMDA receptor and release nitric oxide (NO), excitatory toxicity of nerve cells induced by glutamic acid can be lowered, the compound plays a role in dilating cerebral blood vessels, cerebral blood flow can be improved, but peripheral blood pressure is not lowered; retinal ganglion cell injury induced by high intraocular pressure can be reduced, and the intraocular pressure is lowered through releasing the NO; in a vascular dementia model, the cerebral blood flow can be improved, motor behavior disorder is relieved, and learning cognitive ability is improved; behavioral abnormality and cerebrovascular spasm induced by subarachnoid hemorrhage can be relieved; discovered by researches on tissue distribution of the drugs, MN-08 can be gathered in pulmonary tissue, in a pulmonary arterial hypertension model, pulmonary blood vessels can be dilated, right ventricular pressure can be lowered, and plumpness of right ventricle can be reduced.

The invention relates to a visual inspection technology, and discloses an abnormal behavior analysis method based on intelligent linkage of multiple video cameras, which comprises the following steps of: performing framing processing and key frame screening on video data of the multiple video cameras to obtain a target frame image; background image reconstruction and background stripping are carried out on the target frame image to obtain behaviors of the moving target and an abnormal behavior library; according to the association weights of the moving target and the multiple video cameras, extracting a behavior set of the moving target from the target frame images corresponding to the multiple video cameras, and according to the behavior feature and the skeleton feature of each behavior in the behavior set, calculating to obtain a moving behavior and a limb behavior of the moving target; and according to the abnormal behavior library, determining the abnormal behavior of the motion target for the motion behavior and the limb behavior. The invention further provides an abnormal behavior analysis device based on intelligent linkage of the multiple video cameras. According to the invention, the accuracy of abnormal behavior detection and the flexibility of detection in different environments can be improved.

The invention puts forwards a method and a device for prompting information to users, relating to the field of mobile health. The method comprises following steps: obtaining three-dimensional behavioral models of users; and determining current three-dimensional behavioral models and continuing time of users and generating relevant reminders by matching the pre-set rules based on users' behavior suggestions corresponding to the matching rules. The three-dimensional behavioral model comprises users' sleeping behaviors, users' motion behaviors and users' mobile terminal usage behaviors. The method for prompting information to users obtains users' mobile terminal usage behaviors, motion behaviors and sleeping behaviors for matching by collecting metadata of a mobile terminal, motion data and sleeping data and is capable of generating relevant reminders for users according to matching of current behaviors and pre-set rules.

The invention discloses a multi-agent parking system simulation system and a construction method thereof, and the system is characterized in that the system comprises a multi-agent simulation module, a randomness simulation module, a system dynamics simulation module, a process simulation module, and a rule simulation module; the multi-agent simulation module is used for describing fixed facilities, vehicles and pedestrians in the parking system, wherein the vehicles and the pedestrians are main bodies and are movable agents with active behaviors; and the fixed facility is at a position and is an immovable agent with passive behavior. Accurate description of motion behaviors and mutual influence processes of all agents in the system can be realized, simulation of motion tracks and selection behaviors of the agents is completed through a logic rule model, a visual system dynamic process and potential problems are provided by means of visualization and result analysis functions, reliable data support is provided for design and operation of the parking system, and the parking system simulation method based on the dynamic parking demand is provided.

The invention is directed to compositions and methods for treating or reducing the likelihood of the development of epilepsy in an individual. The method comprises administering to the central nervous system of an individual in need of such treatment a therapeutically effective amount of an agent capable of increasing the expression and / or activity of miR-128.

The invention provides a simulation system of a voltage response type three-phase permanent-magnet synchronous motor. The simulation system comprises a three-phase DC / AC electric and electronic converter, a direct-current power supply port, a motor behavior processor and a voltage control link. The three-phase DC / AC electric and electronic converter is used for simulating port voltage response ofthe three-phase permanent-magnet synchronous motor during current inputting and performs electric energy exchange with an external motor driving system. The motor behavior processor is used for describing the electrical and mechanical behavior characteristics of the three-phase permanent-magnet synchronous motor. The voltage control link is used for using a permanent-magnet synchronous motor portvoltage signal calculated by the motor behavior processor as a reference and controlling alternating-current-end output voltage of the three-phase DC / AC converter. The simulation system can directly perform electric energy exchange with a real motor driving system and effectively simulate port voltage response of the three-phase permanent-magnet synchronous motor during current inputting of the motor driving system, achieves full-electrical motor driving testing, saves the testing cost and improves the testing efficiency and safety.

The invention discloses a motion scene simulation method based on behavior recognition. The motion scene simulation method includes the steps: firstly, acquiring a real-time staff motion image; secondly, preprocessing the real-time image and drawing the outline of a human body according to the processed image by an edge detection algorithm; thirdly, building a human body structure model accordingto a human body bone structure and joint characteristics; fourthly, recording information parameters of the human body structure model in each motion behavior according to a large number of human bodymotion images of a human body behavior database recorded in advance to obtain a human body motion behavior information base; fifthly, calculating the positions of a trunk and four limbs of the humanbody in motion, the motion state of the human body and the rotating and twisting angles of main joints of the human body in a matching manner by multi-frame continuous matching of the real-time images; sixthly, matching the parameters with the built human body motion behavior information base to recognize the motion mode and motion state information of current motion staff. The motion scene simulation method solves the problem of limitation of a virtual scene playing mode in body-building in the prior art.

The invention relates to a gymnasium fire evacuation behavior data collection system based on virtual reality and a collection method thereof. The invention relates to the technical field of building safety and evacuation simulation. A virtual gymnasium three-dimensional building model is built, and a fire smoke visual scene is simulated in the gymnasium model; through a behavior data acquisition module, behavior data of experimenters during movement during fire simulation are acquired, and after simulation is finished, a subjective body strength table (RPE) is used for subjective evaluation of movement intensity; the collected behavior data are analyzed, and movement behaviors under different evacuation postures are determined; basic information, human body posture data, human body motion parameters, the fatigue evaluation grade and the RPE evaluation data of an experimenter are matched, the data are grouped and numbered, the number further comprises an experiment date and an experiment sequence, and the data are stored and stored.

The invention discloses a sleep detection method and device, intelligent wearable equipment and a computer readable storage medium, and the method comprises the steps: entering a sleep state detectionmode after determining that a user is in a sleep state, judging whether the motion behavior of the user is detected or not, if the motion behavior is detected, judging whether the user is still in asleep state or not, if the user is still in the sleep state, acquiring physiological index data, determining a wearing state by utilizing the physiological index data, and judging whether to quit a sleep state detection mode or not according to the wearing state. According to the method, the exercise behavior, the sleep state and the physiological index data are judged, and exit is performed whenthe sleep state detection mode needs to exit, so that the problem of misjudgment on the sleep condition of the user is avoided.

The invention discloses a monitoring method used in a motion process, which comprises the following steps: acquiring physiological health data, gyroscope data, acceleration data and video stream data of a user in a current state, decoding the video stream data into an image, inputting the image into a motion posture classification model, and outputting a motion posture classification result; according to the motion posture classification result and the physiological health data, the current motion posture of the user is comprehensively judged, and data used for representing the current motion state of the user is output; scoring the current motion posture of the user, generating a correction result, and sending the correction result to terminal equipment corresponding to the user; or carrying out abnormal condition grading on the current motion posture of the user, and sending help information to related personnel. Motion monitoring combining various observation data of the user is achieved, the motion postures of the user are classified, scores are generated and corrected, or help information is sent. And the accuracy and generalization of motion behavior monitoring are obviously improved.

The present invention is a method of obtaining information regarding an individual's environment using a programmable device. The first step of the method is sensing a psychomotor behavioral element of an activity engaged by the individual. The type of activity engaged by the individual can be any sensible activity under the sun, including breathing, thinking, generating heat, etc. The next step in the inventive method is determining the preferred modalities of the individual based on the psychomotor behavioral element of the activity engaged by the individual. Provided herein are calculations used for determining the preferred modalities of the individual based on the psychomotor behavioral element of the activity. In the present context, the preferred modalities are the semi-conscious or nonconscious desires of the individual, indicated by nonconscious actions, to experience her environment in a specific manner. The information obtained by the inventive method can be used in several ways. One way to use the information obtained is by automatically altering the environment. Another way to use the information is to make the individual or other individuals aware of the nonconscious or semi-conscious interests

The embodiment of the invention provides a method for training an exercise intensity recognition system. The method comprises the following steps of: A1, constructing an exercise intensity recognition system which comprises a data preprocessing module, a parallel convolution processing stream, a bilinear pooling module and a multi-task learning module which are connected in sequence, wherein the parallel convolution processing stream comprises two parallel convolution processing streams; A2, preprocessing motion data marked with labels through the data preprocessing module, and obtaining a training set composed of motion information and the corresponding labels, wherein the motion data are acquired by an inertial sensor, and the labels marked for the motion data comprise multiple different motion intensity labels and multiple different motion behavior labels; A3, training the exercise intensity recognition system by using the training set; according to the method, features extracted from a convolutional layer are optimized from the channel dimension and the space dimension, important features are concerned, unnecessary features are inhibited, and the recognition precision of the exercise intensity can be improved.

The invention discloses a periodic behavior report generation method, device and system, a storage medium and electronic equipment. The method comprises the following steps: collecting behavior data and health index parameters of a user in a predetermined period, the behavior data comprising at least one of an exercise behavior, a diet behavior and a medication behavior; at least partially utilizing a machine learning model to generate a periodic behavior report of the predetermined period for the user according to the behavior data and the health index parameters, the periodic behavior report at least comprising an evaluation result of the predetermined period and behavior suggestions and / or index targets of the next period; updating a behavior tag of the user based on the periodic behavior report, and collecting patient education content matched with the behavior tag; and sending the periodic behavior report and the patient education content to the user. According to the invention, the user behavior intervention effect is greatly improved, and the user experience is improved.

The invention provides a behavior detection method. The behavior detection method comprises: extracting human body feature point coordinate information; enhancing the coordinate information content of the human body feature points to obtain kinematics information of human body postures; combining the human body feature point coordinate information and the kinematics information to obtain high-dimension information, and meanwhile, preseting a nonlinear dimension reduction algorithm to obtain low-dimension effective data subjected to redundancy elimination and low signal-to-noise ratio; and performing unsupervised clustering on the low-dimensional effective data, constructing convolutional neural network training to form a behavior recognition classifier, and outputting and displaying the motion behavior of the human body posture. After the attitude mode is obtained by fusing the relevance information of the attitude and the action and kinematics parameters and adopting an unsupervised algorithm, classifier training is carried out by using 1DCNN (one-dimensional convolutional neural network) and combining continuous frame time sequence information to obtain the action category, so that the effect of behavior recognition is achieved, and the problem that accurate behavior detection is relatively difficult is solved.

This invention relates to a device that is intended to synchronize electroencephalograms (EEGs), recorded by any digital equipment, to physical events (sensorial, visual or auditory stimuli) and behavioral events (motor response, vocal response), in order to allow EEG signal mediation for the purpose of visualizing Evoked Potentials or Event-Related Potentials, which are important research subjects in the neurosciences and clinical investigations into neurological and psychiatric pathologies. This invention allows any digital EEG device to be transformed into equipment that can record Evoked Potentials. This invention also provides a method for analog synchronization of EEGs with oscillating electric light-related events and motor behaviors.

The invention provides a behavior modeling method of a moving vehicle in a virtual environment. The problem about realistic display of the posture of the moving vehicle on a natural uneven earth surface is researched. Representation of moving behaviors of moving vehicle dynamic models on a regular pavement is relatively simple, but it is much more complex to correctly represent moving postures of the dynamic models on irregular uneven pavements. Along with irregular unevenness of terrains in the virtual environment, postures of the vehicle need to be correspondingly changed along with change of local features of terrains making contact with a vehicle body under the action of gravity of the vehicle. According to the modeling method, posture display parameters adaptive to terrain changes are calculated through a defined vehicle supporting plane and are displayed in a three-dimensional mode, and the dynamic process of moving of the vehicle is effectively and vividly represented.

The invention discloses a step counting and motion behavior recognition method based on an acceleration sensor, which is characterized in that the sensor used in the method is placed in the following manner: the forward direction of the foot is the positive direction of the X axis, and the leftward direction is the Y axis The positive direction of the axis, the direction of lifting the foot is the negative direction of the Z axis. At the same time, due to the relatively large displacement in the X-axis direction when the human body is moving, the acceleration changes are also obvious and have obvious periodicity; therefore, as long as a reasonable threshold is set It can identify the number of moving steps and identify the movement behavior; the invention makes the waveform smoother and reduces errors by means of smoothing filter and Kalman filter, so that the system can record steps accurately in real time; at the same time, it can also accurately distinguish people's various Second, it can calculate the number of steps of various sports in real time; Third, the calculation performance of the system is not very high, and a mobile phone or a general-purpose single-chip microcomputer (MCU) with ordinary configuration can complete the calculation.

The invention discloses a microfluidic chip for monitoring nematode movement behavior and physiological characteristics, wherein: a fluid inlet, a culture chamber array, a sampling channel, an electrical impedance tomography detection chamber, an electrical impedance spectrum detection chamber and a fluid outlet are sequentially connected The sampling control valve is set on the sampling channel for controlling the conduction or closing of the channel; the detection control valve is set between the electrical impedance tomography detection chamber and the electrical impedance spectroscopy detection chamber for controlling the conduction or closure of the channel Closed; the electrical impedance tomography electrode array is connected to the electrical impedance tomography detection cavity; the electrical impedance spectrum detection electrode array is connected to the electrical impedance spectrum detection cavity. Using the above technical scheme, the integration of the culture chamber, electrical impedance tomography detection chamber and electrical impedance spectroscopy detection chamber can be realized, and the functions of nematode cultivation, movement behavior and physiological structure detection can be realized. Combined with the control valve, high automation, Efficient cultivation and detection.

A method includes engaging Parkinson's Disease (PD) subjects in a continuous motor performance task that elicits natural motor variability, quantifying natural motor variability of each PD subject with an array of motor metrics at short timescales, applying a machine-learning classification or regression algorithm to determine weights for each of these metrics to maximally differentiate each patient's motor performance from that of controls performing the same task, and combining the weights to determine a scalar metric of motor performance for each short epoch of motor behavior.