1764results about "Diagnostic signal processing" patented technology

The invention discloses an intelligent system and method for early screening of depression based on electroencephalogram-eye movement multi-modal data fusion. According to the system, in a virtual reality situation, emotion and cognitive response of a subject are stimulated through an elaborately-designed cognitive task, and brain electrical activity and sight behavior data are synchronously collected by adopting a wearable EEG device and a high-precision eye tracker. After signal preprocessing and feature extraction, deep fusion of multi-modal data is realized by using a weighted fusion formula or a graph neural network, the weight of each modal is automatically adjusted, interaction features between electroencephalogram and eye movement are extracted, and then the depression risk of a subject is accurately judged through a classifier. Experiments show that the method can effectively capture weak physiological abnormalities of mild depression patients, has the advantages of high sensitivity, high accuracy and real-time online screening, and meets the requirements of non-invasive, portable and intelligent clinical application.

The invention discloses a pig breeding intelligent management and control system based on multi-modal data monitoring, and belongs to the technical field of pig breeding management, and the system comprises a data collection and individual recognition module which comprises an RFID ear tag, an inspection robot, an environment sensor and an intelligent feeder, and is used for determining the identity information of a pig individual based on the data collected by the RFID ear tag and the inspection robot, associating the collected multi-modal data of the live pigs in the pig house, and uploading the multi-modal data to edge computing equipment through an MQTT protocol for preprocessing; the feature extraction module extracts physiological and behavior features of live pigs by using a multi-modal deep learning fusion model; the key breeding index analysis module constructs a live pig health index and an environment quality index; the abnormity early warning module adopts a CUSUM control chart to accumulate index deviation and respond to abnormity; the management regulation and control model constructs a Markov decision process by minimizing energy consumption and maximizing health indexes, intelligently adjusts the rotating speed of a fan and a feeding strategy, and realizes precise environmental control and feeding optimization.

The invention provides an emotion recognition method based on electroencephalogram eye movement multi-mode cross-attention feature fusion, and the method comprises the steps: firstly carrying out the preprocessing of an emotion recognition public data set, and building a corresponding training set and a test set; secondly, constructing an electroencephalogram eye movement multi-mode cross-attention feature fusion emotion recognition model; then carrying out model training and performance testing; finally, an electroencephalogram eye movement multi-mode online emotion recognition system is built, and the effectiveness of the method is verified. The method has the advantages that an electroencephalogram eye movement multi-mode cross-attention feature fusion emotion recognition model is designed, a dynamic graph convolutional network and an attention mechanism are flexibly applied, meanwhile, multi-dimensional data are used, the problem that single-mode emotion recognition information is insufficient is solved, and the recognition accuracy is improved; and an electroencephalogram eye movement multi-mode online emotion recognition system is built, so that the interactivity is enhanced. The average recognition accuracy of the method reaches 97.94% and is superior to that of an existing optimal method, and meanwhile the accuracy of online emotion recognition reaches 87.4%.

In one embodiment, a medical system includes a catheter configured to be inserted into a chamber of a heart of a living subject, and including multiple electrodes configured to capture electrical activity from electrical activation signals propagating in tissue of the chamber, a display, and processing circuitry configured to automatically select bipolar signals to be captured into an electro-anatomical map from respective electrode pairs of the multiple electrodes responsively to an alignment of the respective electrode pairs with a direction of propagation of the electrical activation signals, and render the electro-anatomical map to the display.

The present application discloses a multifunctional health monitoring method and system based on a millimeter wave radar, and a computer readable storage medium. The method comprises: receiving an echo signal in a space, and on the basis of the echo signal, calculating point cloud data of a user and phase change data caused by the respiration and heartbeat of the user; calculating behaviors of the user on the basis of the point cloud data; calculating vital signs of the user on the basis of the phase change data, wherein the vital signs comprise respiration rate and heart rate; and on the basis of the behaviors and / or the vital signs, determining that the user triggers a set alarm event, and on the basis of the type of the triggered alarm event, performing a corresponding alarm operation.

The invention discloses an intelligent orthopedic rehabilitation self-adaptive evaluation method and device based on multi-modal physiological feedback. The method comprises the steps that multi-modal physiological data including electromyographic signals, knee joint three-dimensional motion trails, plantar pressure distribution and cognitive input degree of a subject are synchronously collected; constructing a three-dimensional baseline vector according to the MMT muscle force test, knee joint ROM measurement and VAS pain score of the subject; inputting the multi-modal physiological data and the three-dimensional baseline vector into a personalized orthopedic rehabilitation model, and outputting a knee joint function index prediction value and personalized rehabilitation adjustment parameters; dynamically adjusting electrical stimulation parameters according to rehabilitation adjustment parameters output by the personalized orthopedic rehabilitation model; if the cognitive load index exceeds the early warning line, the electrical stimulation intensity is reduced; otherwise, activating the hippocampus body wave stimulation mode. Adjustment is carried out according to the real-time state of the subject, blindness and subjectivity in the rehabilitation process are avoided, and the rehabilitation efficiency and success rate are improved.

The invention relates to the field of man-machine interaction training, virtual reality and intelligent evaluation, and particularly discloses a psychological exercise ability training method and system based on mixed reality and behavior analysis. The method comprises the steps that a multi-scene psychological training environment is constructed and presented in mixed reality equipment, action behavior data, eye movement path data and operation response time data of a pilot in the training process are collected, multi-modal original behavior characteristics are constructed, and then a psychological exercise ability label set is constructed; and realizing capability-task modeling through matching of a capability label and a task structure, generating a personalized training path and a capability difference atlas based on difference analysis with a preset capability standard, adjusting task parameter configuration data, dynamically updating a training scene, generating a capability evolution trajectory, and outputting a training analysis result. In this way, accurate ability modeling, task dynamic adaptation and visual tracking of the training effect can be achieved, and the individuation and intelligence level of psychological exercise ability training is remarkably improved.

The invention discloses a transcranial electrical stimulation intracranial vector electric field detection device and method, and belongs to the transcranial electrical stimulation intracranial electric field detection technology, the device inputs an individual head model in a stimulation system, sets a target spot and calculates transcranial electrical stimulation parameters; the implantation position and angle of the vector detection electrode are planned through the navigation system, electrical stimulation is applied to a brain target area through the stimulation electrode, and intracranial electric signals are collected in real time through the vector detection electrode; performing high-precision amplification on the acquired weak signal, and converting the weak signal into a digital signal; the collected electric field signals are calculated and processed in real time, and electric field distribution generated by transcranial electrical stimulation in the brain is analyzed and visualized; according to the method, time domain and frequency domain analysis is carried out on electric signals before and after stimulation, the influence of stimulation on neural signals in a detection area is evaluated, and high-precision measurement of the intensity and direction of a three-dimensional electric field is achieved through the design of a high-precision and multi-layer vector detection electrode.

The invention provides a closed-loop nerve regulation method and device, a medium and a program product, and relates to the technical field of nerve regulation. The method comprises the steps that an electroencephalogram collection module collects electroencephalogram signals in real time and provides real-time feedback data for nerve regulation and control; the magnetic resonance imaging module provides high-precision brain structure and function positioning information; the three different stimulation modules (transcranial alternating current stimulation, low-field magnetic field stimulation and transcranial magnetic stimulation) can stimulate brain regions with different depths and ranges; the multi-mode navigation module carries out accurate positioning based on the magnetic resonance image; the electroencephalogram detection module analyzes the collected signals; and the central control module coordinates the work of each module. According to the multi-module cooperative working mode, accurate stimulation of different areas and different depths of the brain is achieved, meanwhile, the stimulation effect is ensured through real-time monitoring, and therefore the accuracy and effectiveness of nerve regulation and control are improved.

The invention discloses a remote monitoring and guiding system for rehabilitation training in the orthopedics department, particularly relates to the technical field of medical rehabilitation intelligent monitoring, and is used for solving the problems that in an existing remote rehabilitation system, timing sequence dislocation exists in action recognition and regulation and control instruction execution, and joint movement safety early warning is delayed. According to the method, localized time sequence alignment processing is performed on joint movement data and electromyographic signals based on edge computing nodes, a joint linkage action time sequence difference is generated, and an abnormal action risk level is judged in real time by combining an electromyographic signal pre-activation feature and a conflict detection mechanism of a standard action intention; historical abnormal records are matched through the cloud platform to generate a hierarchical regulation and control instruction set, and progressive safety intervention is triggered by the patient end equipment according to the dynamic deviation of the joint activity; through a collaborative mechanism of edge side action stage accurate analysis, electromyographic signal feed-forward verification and multi-stage instruction dynamic binding, millisecond-level response of joint linkage abnormity in staged rehabilitation training is realized, and the risk of joint over-limit activity is effectively avoided.

The invention belongs to the technical field of medical robot control, and discloses a physiotherapy robot self-adaptive control method and system based on multi-mode biological feedback, and the method comprises the steps: carrying out the preprocessing of a biomechanical sensing signal obtained in advance, carrying out feature extraction and dynamic weight fusion on the preprocessed biomechanical sensing signal by utilizing wavelet transform and frequency domain transform to obtain a joint feature; establishing a system dynamics model based on a Lagrange equation, generating a time-varying impedance trajectory model by utilizing a joint state acquired in real time and combining a rolling optimization algorithm, and dynamically adjusting impedance parameters of the time-varying impedance trajectory model according to joint features to generate a safe motion trajectory; and performing double closed-loop control on the physiotherapy robot according to the safe movement track and a biomechanical sensing signal obtained in real time to obtain a control signal of the physiotherapy robot, and realizing joint motor driving of the physiotherapy robot based on the control signal. The device can be flexibly changed according to individual differences of patients and rehabilitation processes.

The invention discloses a sleep state monitoring and analyzing system based on multi-sensor fusion, and relates to the technical field of health monitoring, the sleep state monitoring and analyzing system comprises a multi-modal sensor module used for collecting multi-dimensional data related to a sleep state, the multi-dimensional data comprises a bio-electricity signal, a physiological parameter, body movement data and an environment parameter, and the multi-modal sensor module is used for collecting the multi-dimensional data; the multi-modal sensor module comprises a non-contact sensor, a flexible electronic skin sensor and a bio-electricity signal sensor, and the data fusion and processing module is used for carrying out preprocessing, dynamic self-adaptive fusion and federal learning modeling on collected original data. According to an existing contact type sleep state monitoring scheme, more flexible and accurate sleep state data are realized through a non-contact type monitoring sensor in cooperation with dynamic adjustment of sleep monitoring content and adjustment of weights of various sensors for monitoring the sleep state; and a more accurate and intuitive reference report is provided for the sleep state and the health state of the subsequent user.

The invention relates to the technical field of brain-computer interfaces, in particular to a method, a device and equipment for detecting the cognitive state of attention glasses in real time. The method comprises the following steps: acquiring multi-channel electroencephalogram data of attention glasses, acquiring multi-dimensional features corresponding to the multi-channel electroencephalogram data, and generating a detection sequence; performing time sequence analysis on the detection sequence, extracting change characteristics to construct a cognitive sequence, and generating state description according to the cognitive sequence; performing trend analysis on the state description, performing feature extraction on an analysis result corresponding to the trend analysis, constructing a conversion rule according to the extracted features, and generating a prediction sequence according to the conversion rule; performing threshold division on the prediction sequence, marking state intervals, constructing a criterion sequence, and generating an evaluation result according to the criterion sequence for performing signal detection to obtain detection information; and performing data conversion on the detection information, constructing a display sequence to mark a state type, and generating cognitive state information. And data continuity and signal integrity in a feature extraction process are realized.

Computer-implemented methods are disclosed for assessing the effect of musculoskeletal activities on disease and / or clinical events, the method comprising: receiving a patient-specific vascular and musculoskeletal model of a patient's anatomy, including at least one vessel of the patient; receiving at least one characteristic of the patient's musculoskeletal activity; generating or updating a computational anatomic vascular and musculoskeletal model of the patient's anatomy based on the received at least one characteristic of musculoskeletal activity; performing at least one of a computational fluid dynamics analysis or a structural mechanics simulation on the computational anatomic vascular and musculoskeletal model; and estimating at least one of the patient's risk of disease or clinical events based on the performed computational fluid dynamics analysis and / or structural mechanics simulation. Systems and computer readable media for executing these methods are also disclosed.

The invention belongs to the technical field of intelligent medical treatment, and discloses a camera-free intelligent vital sign monitoring patient bed system which comprises a sickbed body, a vital sign monitoring module, a state sensing module, an abnormal behavior recognition module, an intelligent reminding module and a computer terminal. The sickbed body is used for sensing whether a patient is on the bed, the lying position and the body movement condition, the vital sign monitoring module is used for monitoring vital signs of the patient in real time, the state sensing module is used for judging the life state of the patient, and the abnormal behavior recognition module is used for recognizing whether the behavior of the patient is abnormal. The intelligent reminding module is used for reminding medical staff to pay attention to the condition of the patient, and the computer terminal is used for displaying the real-time state of the patient in each sickbed. According to the camera-free intelligent vital sign monitoring patient bed system, the vital signs, states and behaviors of the patient can be monitored in real time on the premise that the privacy of the patient is protected, and a nurse is reminded to deal with abnormal conditions in time.

The invention relates to the field of wearable equipment, and discloses a data processing method for assisting old people based on a smart watch, and the method comprises the steps: building an old people individual physiological baseline library at a smart watch end, and carrying out the dynamic comparison of the dislocation difference between a real-time collection signal and the baseline library; performing behavior interference separation on the individual compensation sequence, and generating a health time sequence feature block after interference stripping based on a multi-scene embedding model; an event entropy triggering mechanism is introduced into the health time sequence feature block, and when the drift rate exceeds an individual self-adaptive threshold value, a candidate health abnormal event is automatically marked; calibrating a signal source corresponding to the candidate health abnormal event as a local feedback loop node, and performing coupling correction on a signal in a local feedback loop; and based on the health monitoring priority feedback map, in combination with the global circadian rhythm change trend and the accumulated weight of the abnormal event, generating a multi-level interaction prompt instruction. The method has the advantage of improving the accuracy of the health monitoring data of the old people.

The invention relates to the technical field of artificial intelligence and biomedical sensing, and discloses a cognitive disorder risk identification device and method integrating multi-modal physiological data, and the device comprises an EEG module, an eye movement module, an fNIRS module, an edge calculation module and an acceleration sensor; the EEG module collects EEG data, the eye movement module collects eye movement eye-tracing data, and the fNIRS module collects near infrared spectrum fNIRS data and inputs the data to the edge calculation module; the edge calculation module runs the multi-modal space-time attention fusion model to output a cognitive impairment risk assessment result by using the multi-modal space-time attention fusion model; the acceleration sensor operates based on an operation dynamic filtering algorithm of a motion accelerometer to inhibit signal drift caused by head motion. According to the invention, through the modularized head-mounted multi-mode edge device, the physiological data is collected and edge end processing and cognitive disorder recognition and screening are carried out in combination with the edge calculation module, so that early recognition and screening of neurodegenerative diseases can be conveniently and effectively carried out at low cost.

The invention discloses a peripheral vein puncture blood vessel pressure monitoring system for image enhancement examination based on multi-modal fusion, and relates to the technical field of medical image assistion.The peripheral vein puncture blood vessel pressure monitoring system comprises the steps that image data, sensor data and personalized data of a patient are collected; generating an image feature vector, a sensor feature vector and a personalized feature vector based on the preprocessed multi-modal data, carrying out feature interaction on a multi-modal feature line, carrying out representation fusion by combining Transform with contrast learning, and generating a fusion representation vector; the maximum tolerance pressure, the extravasation risk level and the recommended injection flow rate range of the target puncture point under the current injection flow rate are predicted and evaluated in the blood vessel pressure resistance prediction model, injection suggestions and injection alarms of the target puncture point are generated, and injection parameters are automatically adjusted. According to the method, the personalized safety pressure threshold values of patients with different blood vessel conditions are accurately evaluated, and the safety and accuracy of peripheral vein puncture are remarkably improved.

The invention relates to the technical field of intelligent fall detection, in particular to an old people fall detection and early warning system based on multi-modal data fusion, which comprises a dynamic weight fusion unit, a precursor trigger unit, a multi-level decision unit and a verification feedback unit, the dynamic weight fusion unit collects three-axis acceleration, surface electromyographic signals and millimeter wave radar data, multi-source data association analysis is achieved through a double-variable attenuation model and dynamic threshold calibration, and the precursor trigger unit activates electromyographic high-frequency sampling and joint three-dimensional space included angle monitoring when the exercise intensity is abnormal. And the multi-level decision-making unit constructs a tumble probability algorithm based on a random forest model, and performs three-level verification in combination with acceleration standard deviation, ground contact point density and historical mode matching, thereby realizing accurate discrimination of tumble events, providing a high-reliability intelligent solution for safety protection of old people, reducing the risk of tumble injury, and improving the safety of the old people. And the first-aid response efficiency is improved.

The invention provides an intelligent monitoring system and method for swallowing rehabilitation, and the method comprises the steps: determining the mistaken aspiration risk feature of a pressure peak value in the swallowing rehabilitation through the high-frequency energy sudden change amount of cough sound and the delay feature of a food mass through the pharynx, and when the mistaken aspiration risk feature is greater than a risk threshold value in the swallowing rehabilitation, stopping the swallowing rehabilitation. According to biomechanical information in swallowing rehabilitation, coordination scores of all rehabilitation stages in the swallowing rehabilitation process are determined, and then function recovery indexes of the swallowing function in the pharyngeal period in the swallowing rehabilitation process are determined according to all the coordination scores and mistaken aspiration risk characteristics. The swallowing efficiency index in swallowing rehabilitation is extracted, then the rehabilitation deviation characteristic of the pharynx is determined through the swallowing efficiency index and the function recovery index, and personalized adjustment is conducted on the swallowing rehabilitation scheme after sound-light alarm based on the rehabilitation deviation characteristic. Based on the scheme, personalized coordination of the rehabilitation scheme in swallowing rehabilitation can be realized, so that the recovery efficiency of the swallowing function in the pharyngeal period can be improved.

The invention provides a pet state analysis method and system based on remote monitoring, and relates to the technical field of pet state evaluation. The method comprises the following steps: collecting multi-source historical health monitoring data about a pet, and determining a plurality of multi-source combination states of the pet; performing physiological behavior joint analysis based on morphological change on the plurality of multi-source combination states of the pet, generating a plurality of physiological behavior joint modes of the pet, and determining a recessive compensation mode in each physiological behavior joint mode; constructing a state association map of the pet, and performing anomaly analysis on the multi-source real-time health monitoring data of the pet to determine a state anomaly event; and determining a target joint mode to which the pet belongs according to the multi-source real-time health monitoring data, performing compensation stability analysis on the pet according to a recessive compensation mode of the target joint mode, and generating a compensation imbalance evaluation result of the pet. According to the invention, accurate evaluation of the health state of the pet in the transportation process is realized.

The invention relates to the technical field of medical rehabilitation, and particularly discloses a finger rehabilitation electrical stimulation parameter control method and system, and the method comprises the steps: obtaining a multi-channel surface electromyogram signal and finger joint kinematics data of a patient; according to the multi-channel surface electromyogram signals, target fine actions of the patient are recognized; according to the target fine motion and the finger joint kinematics data, a multi-muscle group cooperative activation mode and an expected motion trail are obtained through analysis; generating an electrical stimulation parameter combination for different muscle groups according to a multi-muscle group collaborative activation mode; outputting multi-channel electrical stimulation to the patient based on the electrical stimulation parameter combination, and continuously adjusting the electrical stimulation parameter combination on line according to the deviation between the kinematics data of the finger joints and the expected motion trail; the method solves the problems that an existing method is difficult to effectively simulate complex multi-muscle group coordination, complex in parameter adjustment and difficult to adapt to dynamic changes of a patient, and the effect of assisting the patient in complex and fine finger action training is achieved.

The invention belongs to the technical field of magnetic particle imaging, relates to a magnetic particle imaging reconstruction method based on a calibration magnetic field generation system matrix, and aims to solve the problems that a traditional magnetic particle imaging reconstruction method is poor in applicability in asymmetric bilateral structure magnetic particle imaging equipment (A-MPI) and cannot perform imaging in any region. The method comprises the following steps: performing grid division on an imaging area, calibrating magnetic field intensity, and obtaining magnetic field gradient distribution of each point; obtaining a theoretical system matrix according to a mathematical calculation mode; randomly moving the positions of the non-magnetic field points for scanning to obtain actually measured magnetic field gradient distribution and a system matrix, and constructing a data set; expanding the data set based on the simulation system; constructing a deep learning model, and inputting the extended data set and the measured data into the training deep learning model; and inputting a theoretical system matrix at any position, and obtaining an accurate system matrix by using the trained model. According to the invention, the system matrix at any position can be obtained under the A-MPI equipment, so that imaging at any position is realized.

The invention discloses a whole-course accompanying robot for disabled old people and an automatic control system of the whole-course accompanying robot, relates to the technical field of intelligent accompanying, and is used for solving the problems of inaccurate positioning, untimely task response and poor service continuity in the accompanying process of the disabled old people. The multi-modal perception and state analysis module divides the accompanying environment into a plurality of sub-regions based on region characteristics, and accurately perceives the position and state change of the disabled elderly. And the task generation and scheduling execution module intelligently judges service requirements of disabled old people, and dynamically screens optimal robot resources for task matching and execution. The task feedback closed-loop module collects and analyzes task execution process and result data, and timely rechecks the state of the old person according to feedback. And the self-control module adjusts the accompanying strategy and periodically reviews the priority of the task queue. Through cooperative operation of the above modules, the system can achieve precise perception, intelligent decision and dynamic optimization of accompanying of disabled old people, and remarkably improves continuity, intelligence and reliability of accompanying service.

The invention relates to the technical field of acupuncture, in particular to an intelligent acupuncture point precise positioning and stimulation regulation and control system based on combination of traditional Chinese medicine and western medicine, and the system firstly collects body surface acupuncture point information of a user, analyzes sensitivity and generates visual data. The information processing module fuses the data, generates acupoint comprehensive characteristics and marks a target acupoint. And the virtual visualization module generates a virtual acupoint image and marks a target acupoint. The needling instrument massage module formulates a needling instrument pushing scheme according to acupuncture point characteristics and needling instrument parameters, and the needling instrument pushing scheme is executed by the body surface needling instrument pushing device. Meanwhile, the electrical stimulation regulation and control module generates parameters, the electrical stimulation intensity, frequency and time are controlled, and the electric acupuncture massage device is combined with body surface acupuncture massage operation to execute treatment. According to the system, accurate acupoint positioning, personalized needle pushing scheme making and electrical stimulation regulation and control are achieved, the effect and safety of needle pushing treatment are improved, and innovative technical support is provided for modernization of traditional Chinese medicine.

The invention provides a sleep staging analysis method and device based on electroencephalogram signals, and belongs to the technical field of data analys.The method specifically comprises the steps that staging deviation time periods in sleep analysis results are determined according to the sleep staging results corresponding to different credible monitoring positions; determining the matching conditions of the electroencephalogram signals of different credible monitoring positions at different moments and the monitoring data of other dimensions, and determining the abnormal change moments of different credible monitoring positions by combining the deviation conditions of the electroencephalogram signals at different moments and other credible monitoring positions; according to the distribution data of the abnormal change moments of the different credible monitoring positions in the staging deviation period and the early period of the staging deviation period, when it is determined that the reference monitoring position exists in the staging deviation period, the sleep staging result in the staging deviation period is determined through the reference monitoring position, and the accuracy of the sleep staging result is improved.

The invention relates to the technical field of stoma nursing devices, and discloses an AI visual stoma leakage early warning system, which comprises a plurality of passive piezoelectric film sensors embedded in a stoma chassis and used for capturing acoustic signals generated by adhesion interface structure instability; the edge calculation unit periodically collects an electric signal sequence and calculates an information entropy value, and through comparison with a self-adaptive resting entropy baseline, the structural instability risk is judged and early warning is generated when the entropy value continuously and abnormally rises. The risk orientation is accurately identified in combination with a multi-sensor cooperative positioning technology, body movement interference is avoided by using a dynamic compensation mechanism, and the early warning accuracy and clinical practicability are improved.

The invention discloses an intelligent muscle rehabilitation detection method and system, and relates to the technical field of muscle rehabilitation, and the method comprises the steps: obtaining a resistance value of a stretchable joint strip sensor before each rehabilitation training, measuring an electromyographic signal, calculating a correction factor of the resistance value, and obtaining a reference value; the rehabilitation value of the patient is collected in the rehabilitation training process of the patient; calculating the difference degree between the rehabilitation value and the reference value; a difference degree threshold value is set, the rehabilitation condition of the patient is judged according to the difference degree, and the rehabilitation condition comprises rehabilitation completeness, good rehabilitation progress and poor rehabilitation condition; for a patient with poor rehabilitation conditions, a rehabilitation prediction model is established based on historical resistance values of the patient, a future stage rehabilitation target is predicted, a hierarchical reinforcement learning algorithm is defined based on the stage rehabilitation target of the patient, a rehabilitation training strategy is optimized by using a meta-strategy and a sub-strategy, and personalized muscle rehabilitation detection is realized.

The invention discloses a wrist joint spasm assessment method and a wrist joint spasm assessment device based on multi-source data fusion. The rotating speed data, the rotating angular speed data and the angle change data of the wrist joint, the pressure change data of the whole palm, the acceleration change data of the palm, the torque change data of the wrist joint and the electromyographic change data of related muscles in the movement process are measured, and scoring is carried out in combination with an expert system. The evaluation of wrist spasm is realized by combining a multiple linear regression algorithm with a differential evolution algorithm; and based on the multi-source data fusion, establishing an evaluation model by using a Bi-LSTM network so as to realize spasm evaluation. The wrist serves as a spasm detection part, and compared with traditional spasm detection equipment, a more convenient data acquisition mode is achieved while the evaluation precision is guaranteed.

The invention discloses a non-contact sleeping posture detection and vital sign monitoring method based on a millimeter-wave radar, and the method employs a multi-transmitting and multi-receiving millimeter-wave radar, employs an innovative signal processing algorithm and a data processing algorithm, and carries out sleep monitoring through comprehensive consideration of frequency spectrum information and point cloud information. Comprising the steps of extraction of vital sign data such as respiration and heartbeat and judgment of in-bed, body movement and sleeping posture states. Breathing and heartbeat components are effectively extracted through cross-correlation entropy operation, then the signal-to-noise ratio of the breathing and heartbeat components is increased, then fast Fourier transform is carried out on cross-correlation entropy, and it is proved that the breathing and heartbeat frequency is effectively extracted.