44 results about "Effect of gait parameters on energetic cost" patented technology

The invention provides a system for evaluating hearing-speech rehabilitation training and curative effect of patients with post-stroke dysarthria and a device thereof. The system comprises a patient selecting module (1), an effect evaluating module (2), a training module (3) and a clinical curative effect evaluating module (4). The invention also provides a method for evaluating hearing-speech rehabilitation training and curative effect of patients with post-stroke dysarthria. The method comprises the following steps: selecting patients with post-stroke dysarthria, evaluating before training, training language, evaluating after training and evaluating clinical curative effect. The system and the method are used for training pronunciation and reading in hearing-speech rehabilitation treatment of the patients with post-stroke dysarthria, providing curative effect evaluation, improving pronunciation accuracy degree and continuous pronunciation coordination ability of the patients, subdividing treatment grades according to different conditions of the patients, making individual training schemes and improving pertinence, relieving working strength of hearing-speech rehabilitation therapists and effectively improving the working efficiency and the individual treatment training effect.

The invention provides an upper limb active rehabilitation method and a rehabilitation device based on electroencephalogram and functional electric stimulation, and relates to the technical field of rehabilitation robots. The upper limb active rehabilitation method comprises the following steps: under a circumstance of stimulating left and right hands, acquiring electroencephalogram signals basedon left and right hand motor imagery in accordance with stimulation paradigm; amplifying and pre-processing electroencephalogram signals, and implementing characteristic extracting on the pre-processed electroencephalogram signals, so that characteristic vectors which are used for classifying left and right hand motion rehabilitation intentions are obtained; inputting the characteristic vectors into a classifier and classifying the characteristic vectors, so that left/right hand motion rehabilitation intentions; implementing functional electric stimulation on corresponding parts of a rehabilitation object by virtue of an FES system in accordance with the rehabilitation intentions; and implementing functional electric stimulation by virtue of the FES system, so that plastic rehabilitation feedback to brain functions is formed. According to the upper limb active rehabilitation method and device provided by the invention, recognition of active rehabilitation intentions of rehabilitation objects is achieved through the electroencephalogram signals, and functional stimulation is implemented by virtue of the FES system in accordance with the rehabilitation intentions, so that a better active, objective and accurate rehabilitation effect can be achieved.

The invention discloses a hemoglobin information based recognition method for multiple walking gait adjusting intents. The hemoglobin information based recognition method for the multiple walking gaitadjusting intents, disclosed by the invention, is characterized by comprising the steps: carrying out data preprocessing on cerebral cortex hemoglobin concentrations recorded at walking gait adjusting moments, wherein the cerebral cortex hemoglobin concentrations recorded at the walking gait adjusting moments are obtained in a manner that a testing experiment is performed by using a near infraredspectrum brain imaging technique (NIRS) and testees finish corresponding walking gait adjusting tasks in a fixed region; subjecting preprocessed cerebral cortex hemoglobin information to corresponding channeling according to distribution of cerebral functional areas, and calculating and extracting relevant parameters as characters; modeling a detection model for four kinds of gait adjusting intents by applying a pattern recognition algorithm. The method has the beneficial effect that the testing experiment is performed by using the near infrared spectrum brain imaging technique, and thus, themethod is simple and convenient.

The invention discloses a motor-imaginary and enhanced reality based rehabilitation training method. According to the invention, motor imaginary is combined with enhanced reality technology, a rehabilitation training mode based on motor imaginary is designed aiming at a characteristic that the athletic ability of a patient suffering cerebral apoplexy in a flaccid paralysis phase is very weak, namely, collection, processing and analysis of electroencephalogram signals of the patient are performed, and control of rehabilitation scenes is realized through offline training and online control basedon motor imaginary. A real scene is acquired by utilizing a Kinect scanning technology, and virtual objects are added into the real scene through the enhanced reality technology, so that an effect ofreality enhancement is achieved. The patient can realize control of the virtual objects in the real scene through a motor imaginary mode and implement corresponding tasks. Therefore, enthusiasm of the patient for rehabilitation training is improved substantially, so that an effect of brain function remolding can be achieved and rehabilitation of the patient is facilitated. The method improves enthusiasm of the patient for rehabilitation training greatly and achieves the effect of brain function remolding.

The present invention provides a method for predicting movie box office based on fuzzy linear regression, comprising the following steps: S1, quantifying the weight of factors affecting movie box office, obtaining the weight of the influencing factors, and performing a clustering process; S2, quantifying The final weight value is solved through the fuzzy linear regression model; S3, input the training samples, solve the regression coefficient, obtain the regression equation after training, input the test samples, and obtain the predicted value. S4, according to the predicted value of the sample, calculate the relative percentage error between the sample and the true value, and calculate the probability distribution of the relative percentage error of the sample, which intuitively reflects the prediction effect.

The invention provides a virtual reality rehabilitation training method and system based on surface myoelectricity information and depth image information for forearm amputation patients. The method comprises: collecting residual limb myoelectricity information of an amputation patient, and obtaining a palm action category corresponding to the myoelectricity information through a trained gesture recognition model; meanwhile, acquiring the stump pose information of the amputation patient through a depth camera, and identifying the arm action category following the palm action based on the poseinformation; and finally, based on the palm action category and the arm action category, generating a control instruction for controlling a virtual hand action in a virtual environment so as to assistrehabilitation training. According to the method and the corresponding system, the surface myoelectricity information and the depth image information can be fused, the rehabilitation training effectand efficiency of the forearm amputation patient are improved, and the patient can be helped to adapt to the artificial limb as soon as possible.

The invention provides a dyskinesia non-intrusive rehabilitative closed-loop brain-computer integrated system based on an FPGA. The FPGA is used as a control core of the system, nuclei basales and thalamic-cortical prosthesis hardware model is set up, data obtained through calculation of a self-adaptation control algorithm based on the FPGA is used as input to control model parameter setting and force feedback and adjustment until an expected control result is achieved, the self-adaptation control algorithm based on the dynamic causal model is realized, force feedback signals are output, and therefore rehabilitation of patients with the dyskinesia nervous system diseases is achieved. Rehabilitation of the patients with dyskinesia nervous system diseases is achieved, and the complex nuclei basales and thalamic-cortical neuron network and the self-adaptation control algorithm of the dynamic causal model are modeled. The platform provides the effective theoretical basis and technical support for rehabilitation of the dyskinesia nervous system diseases and has important practical value in research on control and treatment on nerve diseases such as Parkinson's disease, epilepsia and alzheimer's disease.

In order to improve the efficiency of each joint and make optimization objective more targeted, aiming to perform trajectory optimization on joint space of six-axis joint type robot in accordance withPieper criterion, based on the analysis of the structure and performance of a six-axis mechanical arm, the invention provides a trajectory optimization strategy based on time grouping. Trajectory optimization is carried out on three front axes and three rear axes of the six-axis mechanical arm under different time dimensions, and targeted objective optimization is carried out according to joint torque characteristics, so that the optimization effect of shortening posture adjusting time and reducing pulsation is achieved. By analyzing the characteristics of a time-based trajectory optimizationalgorithm, an exchange pool of a genetic algorithm is introduced into a particle swarm optimization algorithm, the phenomenon of iteration omission of multi-dimensional information is improved, and the optimization efficiency of the algorithm is effectively improved. Through experiment simulation and comparison with other optimization strategies and target setting optimization effects, an averageof 15% of posture adjusting time is reduced.

The invention discloses a training method for sensory stimulation of a vestibular sensation system. The method is characterized by specifically comprising procedures in six stages including the training procedure of sensory stimulation of the vestibular sensation system in the first stage before a child is 1 year old, the training procedure of sensory stimulation of the vestibular sensation systemin the second stage when the child is 1-3 years old, the training procedure of sensory stimulation of the vestibular sensation system in the third stage when the child is 4-6 years old, the trainingprocedure of sensory stimulation of the vestibular sensation system in the fourth stage when the child is 7-12 years old, the training procedure of sensory stimulation of the vestibular sensation system in the fifth stage when the child is 13-18 years old and the training procedure of sensory stimulation of the vestibular sensation system in the first stage when the child becomes an adult. The training method has the advantages that compared with traditional training, the most practical sensory integration development information of the child can be promoted, that is to say, the targeted training procedures can be set to substantially assist the development of the sensory integration ability of the child.

The invention discloses a gait detection and analysis method and a device thereof, and the device comprises a carrier, a data collector, a microprocessor, and a battery. The method is characterized byanalyzing and processing the acquired data, calculating corresponding data, transmitting the data to an intelligent terminal, and executing the gait detection and analysis method; the method comprises the following steps: 1) collecting signals; 2) positioning a complete landing time point; 3) carrying out gait detection; 4) performing single-step signal division; 5) performing step number statistics; 6) calculating the size of the angle; 7) determining a walking mode, (8) determining a landing mode, and (9) judging pronation and extorsion; and (10) determining in-toe gait and out-toe gait. The gait can be conveniently, rapidly and accurately detected and analyzed by the method and the device, and objective gait analysis basis and effect evaluation after rehabilitation treatment, correction or exercise improvement are provided for doctors, exercise coaches and users.

The invention provides a dynamic brain fitness training method which comprises a nerve muscle activating exercise step. The nerve muscle activating exercise step comprises ankle training, knee-joint training, hip joint training, shoulder joint training and cervical vertebra training. The dynamic brain fitness training method has the advantages that a brain structure is changed and a brain function is improved through some specific limb training, and an ordinary person can develop better and quicker than a person who is not trained in cognitive function and is more competitive. An exerciser utilizes single limb training to activate and strengthen the muscle-brain pathway, finally the self-control ability, movement executing ability, attention, memory, planning capability and the like are ultimately enhanced. The actual effect of brain fitness is exercised through actions, the brain function is improved, accordingly the body action efficiency is improved, action damages are prevented, body pain is reduced, body and brain functions are maintained, and the life quality of people is comprehensively improved.

The invention provides a Leap Motion-based finger rehabilitation error correction method. The method comprises the steps that 1, the normal hand of a patient is subjected to behavior prediction, LeapMotion performs data collection on two-hand movements, and data is displayed in real time through an upper computer; 2, the computer compares the data of the two-hand movements; 3, if errors are within an effective range, a quantized value of complete action of hands of a patient is output, if the errors are not within the effective range, prompt messages are output, and data is corrected throughan algorithm; 4, the corrected data is transmitted to lesion side fingers, the steps from first to third continue to be executed, and finally the errors are within the effective range. Accordingly, data of rehabilitation training for the patient is displayed in real time, the time delay problem of symmetrical movements of the two hands of the patient is effectively solved, the errors of the movements are reduced, the effect of symmetric rehabilitation of the two hands of the patient is improved, the time cost of the patient is lowered, and the activity of the patient for treatment is enhanced.

The invention relates to a human body physiological age analysis method, system and model based on conventional physical examination indexes. The characteristic rules of the conventional physical examination indexes and human body physiological age changes are analyzed, the age analysis model based on the conventional physical examination indexes is established, and the human body physiological age is analyzed. A physiological age analysis model is established on the basis of conventional physical examination indexes (height, weight, blood pressure, pulse, heart rate, blood routine, blood biochemistry, hemorheology, urine routine and the like) to detect the physiological age of a human body, so that the physiological age of a human body can be detected in real time, the aging degree of a human body can be accurately and quantitatively evaluated, the anti-aging effect of various anti-aging intervention measures can be evaluated, and then a personalized and accurate anti-aging scheme based on aging monitoring can be established.

The invention provides a tri-parameter power function model linearization method of accelerated degradation of an accelerometer. In the method, assuming that zero offset and scale factor degradation of an accelerometer conform to a tri-parameter power function model and a corrected parameter is unrelated to the temperature; raising the highest temperature mean square related coefficient maximum principle determined by the corrected parameter under the condition that the experimental time under different temperatures are basically the same; and realizing the linearization of the tri-parameter power function model by fixed corrected parameters. The method comprises the following specific steps: 1, building a degradation track model related coefficient function under the highest temperature; 2, building a degradation track model mean square related coefficient function under the highest temperature; 3, determining a degradation track model corrected parameter; and 4, performing linearization and parameter identification for the degradation track model. The method of the invention can avoid the initial value sensitive and convergent problems of non-linear fitting, and ensure significance of the whole fitting effect of the model and the integrity of the degradation track characteristics by the high-temperature mean square related coefficient.

The invention provides a nonlinear regression tuning method for synchronous motor model parameters based on penalty factors. The nonlinear regression tuning method for motor model parameters comprisesthe following steps: establishing a mathematical model, extracting key data points of peak and valley points, and obtaining nonlinear regression problem and nonlinear parameter regression solutions under large residual error. The LM algorithm can be used to solve the nonlinear regression parameter problem without residual error. If there is residual error, the LM algorithm can not find the idealsolution. The invention aims at the parameter regression analysis of the sudden short circuit of the synchronous motor with residual error, the nonlinear parameter regression analysis of the sudden short circuit test of the synchronous machine is solved, the nonlinear parameter regression analysis is insensitive to the initial value when the nonlinear regression analysis is made when there is residual error, and a better fitting effect can be obtained. The method has the universality of solving all nonlinear parameter regression. Through the present invention, an engineering solution is provided to the problem of residual nonlinear parameter regression analysis.

A human health detection system detects the resistance value in each of twelve meridians of a human body to judge whether disorders occur in the corresponding organs or portions of the human body. Thus, a patient can understand his or her health condition. Furthermore, a doctor can use the detection result to more accurately diagnose problems in various portions of the human body, increasing the effect and efficiency of diagnosis.

The invention discloses a rapid scanning imaging method of a 3D motion platform for cell DNA ploidy analysis. An image on a glass slide is rapidly scanned, the average variable quantity of gradient value of each step motion of the Z axis is calculated according to gradient value data during each change of the Z axis, the difference between the gradient value at the moment and the maximum gradientvalue is calculated through calculation of gradient values of all scanned images, the number of steps between positions of the Z axis when the position distance of the Z axis at the moment is the maximum gradient value is calculated, and the number of the steps is taken as a compensation basis. The average change quantity of the gradient value is multiplied with the number of the steps, the gradient value required to be compensated is obtained for image compensation, and the technical effect identical to focusing is obtained. Compared with the prior art, the rapid scanning imaging method of the 3D motion platform for cell DNA ploidy analysis is applicable to the processing process of batch scanning of images, the whole scanning process of one glass slide only requires one focusing, the scanning time is shortened, and the efficiency is improved.

The invention discloses a gait recognition method based on a GRU, and belongs to the technical field of prostheses. According to the invention, the problems of complex calculation, poor real-time performance and the like of a traditional gait classification method are solved; complex feature extraction engineering is omitted through the GRU, only model parameters need to be used for classification, the calculation speed is greatly increased, real-time calculation of the gait stage is achieved, and the tedious process that traditional gait recognition needs to be classified offline is eliminated. The method comprises the following steps: acquiring plantar pressure information during walking by using an FSR film pressure sensor worn on the plantar of an artificial limb; marking correspondinglabels on the data queues according to the target typical walking characteristics and the timestamps; building a GRU network model; defining a GRU unit, a full connection layer and each activation function; and dividing the obtained data label pair into a training set and a test set, sending the training set to a GRU network model for training, evaluating a model classification effect by using the test set after training is completed, and performing online real-time classification.