Method for predicting ipsilateral movement direction of heterolateral lower limb myoelectric signals and related device

Abstract

The application provides a contralateral movement direction prediction method for heterolateral lower limb myoelectric signals and a related device, and belongs to the technical field of human biological signal processing and pattern recognition. The application uses the combined features of the surface myoelectric signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration to construct a training set and a test set; a three-class gait prediction model is constructed, the three-class gait prediction model is trained based on the constructed training set, the three-class gait prediction model training result is tested based on the constructed test set, and a trained three-class gait prediction model is obtained; the combined features of the surface myoelectric signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are input into the trained three-class gait prediction model for right foot movement direction prediction, and a right foot movement direction prediction result is obtained. The application solves the problem of low accuracy of contralateral movement direction prediction for heterolateral lower limb myoelectric signals.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of human biological signal processing and pattern recognition, and particularly relates to a contralateral motor direction prediction method for ipsilateral lower limb electromyography signals and a related device. BACKGROUND

[0002] According to relevant reports, by 2015, the total number of all types of disabled people in China exceeded 87 million, accounting for 6.4% of the total population. It is estimated that by 2050, the number of disabled people in China will increase to 168 million, accounting for 11%. Liu Fengpu et al. studied the rehabilitation needs and development of rehabilitation services of adult disabled people in Henan Province. The research results show that the proportion of limb disability among adult disabled people is as high as 62.2%, and the proportion of assistive device demand among rehabilitation needs is as high as 49.0%, and the proportion of functional training demand is 20.2%. Therefore, it is urgent to design lower limb rehabilitation robots for motor dysfunction such as stroke hemiplegia and spinal cord injury. Lower limb exoskeleton robots not only can help patients with motor dysfunction to walk and recover motor function, but also can improve the motor ability of the elderly, and can enhance the load intensity and endurance of manual laborers and soldiers. Unlike intelligent prostheses, exoskeletons are not substitutes for part of the human body, but need to be integrated with the human body to perceive the movement intention of the human body, so as to cooperate with the wearer to complete specific actions in a certain way. For lower limb exoskeletons, the analysis and recognition of lower limb movement are the key links for completing the perception and prediction of human movement intention. Accurate perception of the wearer's movement intention is the primary condition for the exoskeleton to cooperate with the wearer to complete the target movement, and is also the key technology to solve the problem of human-machine coordination.

[0003] The occurrence of human lower limb movement is a complex neurophysiological process that requires the cooperation of the cerebral cortex, thalamus, basal ganglia, cerebellum, brainstem, spinal cord, and muscles to complete. The idea of movement is first generated in the motor area of the cerebral cortex, transmitted to the brainstem in the form of electrical signals, and then the movement command is issued by the spinal cord. Subsequently, the conversion of electrical energy to mechanical energy is realized in the muscles, and movement is thus generated. At the same time, complex calculations are performed in the cerebral cortex, thalamus, basal ganglia, and brainstem to regulate the generated movement, so that the behavior of the human body is more coordinated and accurate. Therefore, the analysis and recognition of lower limb movement not only need to consider the kinematics and dynamics parameters of the lower limb, but also need to study the physiological signals of the cerebral motor cortex and the lower limb muscles, and the patient controls the exoskeleton through his own intention. On the one hand, it can improve the patient's participation and enthusiasm, and on the other hand, it can promote the plasticity of the brain. At present, the forms of movement information of lower limb exoskeletons include plantar pressure, acceleration, joint movement angle, and surface electromyography (sEMG) and the like.

[0004] Currently, only the Hybrid Assistive Limb (HAL) developed by the University of Tsukuba in Japan uses surface electromyography (sEMG) signals for lower limb movement control. Several other lower limb exoskeleton products use buttons for lower limb movement control. These systems, relying on preset trajectories, cannot sense the wearer's movement intentions and require the wearer to cooperate with the exoskeleton's movements, making them unsuitable for patients with strong lower limb voluntary movement abilities. Exoskeletons that detect gait phase based on plantar pressure, joint angles, and inertial measurements can detect the wearer's movement intentions, but the detected gait is after movement has occurred, and cannot predict movement intentions before movement. On one hand, surface EMG signals occur before actual movement; while this can be used to predict movement intentions, the EMG signals on the moving side occur almost simultaneously with the actual movement, resulting in poor prediction effectiveness. On the other hand, gait recognition and movement intention perception technologies based on sEMG are still in the experimental stage, and there are few lower limb exoskeleton products on the market that use EMG-based control methods. Summary of the Invention

[0005] The purpose of this invention is to provide a method and related device for predicting the ipsilateral movement direction of electromyographic signals of the contralateral lower limb, in order to solve the problem of low accuracy in predicting the ipsilateral movement direction of electromyographic signals of the contralateral lower limb in the prior art.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a method for predicting the ipsilateral movement direction of electromyographic signals from the contralateral lower limb, comprising the following steps:

[0008] Acquire surface electromyographic signals of muscles in both lower limbs, plantar pressure of the left foot, and three-dimensional acceleration of the right foot;

[0009] The surface electromyography (EMG) signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot were resampled and preprocessed to obtain the preprocessed surface EMG signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot.

[0010] Feature extraction was performed on the surface electromyography (EMG) signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot after preprocessing. The temporal slope change features and mean absolute value features of the surface EMG signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot were obtained.

[0011] The time-domain slope change characteristics and mean absolute value characteristics of the surface electromyography signals of the left and right lower limb muscles, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot are combined to obtain the combined characteristics of the surface electromyography signals of the left and right lower limb muscles, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot.

[0012] The surface electromyogram of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are combined to construct a training set and a test set;

[0013] A three-class gait prediction model is constructed, the three-class gait prediction model is trained based on the constructed training set, the three-class gait prediction model training result is tested based on the constructed test set, and a trained three-class gait prediction model is obtained.

[0014] The surface electromyogram of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are combined to construct a training set and a test set;

[0015] The surface electromyogram of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are combined to construct a training set and a test set;

[0016] The surface electromyogram of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are combined to construct a training set and a test set;

[0017] The surface electromyogram of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are combined to construct a training set and a test set;

[0018] The surface electromyogram of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are combined to construct a training set and a test set;

[0019] The further improvement of the present application is that 70% of the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are used as the training set, and 30% are used as the test set.

[0020] The further improvement of the present application is that the LIBSVM toolbox is used to construct the three-class gait prediction model in the step of training the three-class gait prediction model based on the constructed training set.

[0021] In the second aspect, the present application provides a contralateral motion direction prediction system of ipsilateral lower limb electromyography signals, which comprises a data acquisition module, a data preprocessing module, a feature extraction module, a feature combination module, a data set construction module, a three-class gait prediction model training module and a right foot motion direction prediction module.

[0022] The data acquisition module is used to acquire the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0023] The data preprocessing module is used to resample and preprocess the acquired surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration, so as to obtain the preprocessed surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0024] The feature extraction module is used to extract features from the preprocessed surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration, respectively, so as to obtain the time domain slope change features and the average absolute value features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0025] The feature combination module is used to combine the obtained time domain slope change features and the average absolute value features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration, respectively, so as to obtain the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0026] The data set construction module is used to construct the training set and the test set by using the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0027] The three-class gait prediction model training module is used to construct the three-class gait prediction model, train the three-class gait prediction model based on the constructed training set, test the training result of the three-class gait prediction model based on the constructed test set, and obtain the trained three-class gait prediction model.

[0028] The right foot movement direction prediction module is configured to input the combined features corresponding to the surface electromyography signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration to be predicted into the trained three-class gait prediction model to predict the right foot movement direction, and obtain a right foot movement direction prediction result.

[0029] In a third aspect, the present application provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the ipsilateral movement direction prediction method of the contralateral lower limb electromyography signal when executing the computer program.

[0030] In a fourth aspect, the present application provides a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the ipsilateral movement direction prediction method of the contralateral lower limb electromyography signal.

[0031] Compared with the prior art, the present application has the following beneficial effects:

[0032] The present application is an improved application, and compared with the prior art, the ipsilateral movement direction prediction method of the contralateral lower limb electromyography signal provided by the present application can more comprehensively understand the movement information in the human body movement process on the one hand, because the present application obtains the surface electromyography signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration. On the other hand, the present application uses the corresponding combined features (the surface electromyography signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration) to realize the prediction of the three movement directions (left, middle and right) of the right foot, thereby improving the prediction accuracy of the right foot movement intention, providing a key technical basis for the development of the right lower limb human-computer interaction system, and effectively solving the problem of low accuracy of the ipsilateral movement direction prediction of the contralateral lower limb electromyography signal in the prior art.

[0033] Further, in the step of combining the time domain slope change features and the average absolute value features corresponding to the surface electromyography signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration to obtain the combined features corresponding to the surface electromyography signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration, the combined features corresponding to the surface electromyography signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration are features in the form of a vector group. The features in the form of a vector group contain rich movement feature information, such as pressure (especially the left foot plantar pressure, containing key information for predicting the right foot movement), acceleration and direction change rate. These feature information is crucial for later movement direction prediction, because they can comprehensively and accurately describe the movement state of the human body.

[0034] Further, the application also discloses a three-class gait prediction model, and the three-class gait prediction model is trained based on the constructed training set, and the steps of obtaining the trained three-class gait prediction model, and the three-class gait prediction model is constructed by using the LIBSVM toolbox. The LIBSVM toolbox has high efficiency in processing high-dimensional data and strong generalization ability when the three-class gait prediction model is established, and the accuracy of the later motion direction prediction is improved. BRIEF DESCRIPTION OF DRAWINGS

[0035] Figure 1 A flow chart of the contralateral motion direction prediction method of the ipsilateral lower limb myoelectric signal of the application;

[0036] Figure 2 A schematic diagram of the contralateral motion direction prediction system of the ipsilateral lower limb myoelectric signal of the application;

[0037] Figure 3 A control principle diagram of the VR-based kicking game experiment paradigm of the application;

[0038] Figure 4 A control flow chart of the VR-based kicking game of the application;

[0039] Figure 5 A structural schematic diagram of the electronic device of the application. DETAILED DESCRIPTION

[0040] In order to further understand the content of the application, the application will be described in detail below in combination with the drawings and specific embodiments. It should be understood that the embodiments are only used to explain the application and are not limited.

[0041] The contralateral motion direction prediction method of the ipsilateral lower limb myoelectric signal of the application inputs the combined features corresponding to the surface myoelectric signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration into the trained three-class gait prediction model to predict the right foot motion direction, and obtains the right foot motion direction prediction result. Compared with the prior art, the application effectively solves the problem that the accuracy of the contralateral motion direction prediction of the ipsilateral lower limb myoelectric signal is not high.

[0042] Embodiment 1:

[0043] The flow chart of the contralateral motion direction prediction method of the ipsilateral lower limb myoelectric signal of the application is shown in Figure 1 The contralateral motion direction prediction method of the ipsilateral lower limb myoelectric signal of the application includes the following steps:

[0044] S1. Obtain the surface myoelectric signals of the left and right lower limb muscles, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0045] S2. The obtained left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration are resampled and pretreated to obtain pretreated left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration.

[0046] S3. The pretreated left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration are respectively extracted to obtain time domain slope change features and average absolute value features corresponding to the left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration.

[0047] S4. The time domain slope change features and average absolute value features corresponding to the left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration are respectively combined to obtain combined features corresponding to the left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration.

[0048] S5. The combined features corresponding to the left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration are used to construct a training set and a test set.

[0049] S6. A three-class gait prediction model is constructed, the three-class gait prediction model is trained based on the constructed training set, the three-class gait prediction model training result is tested based on the constructed test set, and a trained three-class gait prediction model is obtained.

[0050] S7. The combined features corresponding to the left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration to be predicted are input into the trained three-class gait prediction model for right foot movement direction prediction to obtain a right foot movement direction prediction result.

[0051] Embodiment 2:

[0052] The schematic diagram of the contralateral movement direction prediction system of ipsilateral lower limb electromyogram signals of the application is shown in Figure 2 The contralateral movement direction prediction system of ipsilateral lower limb electromyogram signals of the application includes a data acquisition module, a data preprocessing module, a feature extraction module, a feature combination module, a data set construction module, a three-class gait prediction model training module and a right foot movement direction prediction module.

[0053] The data acquisition module is used to acquire left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration.

[0054] The data preprocessing module is used to resample and pretreat the obtained left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration to obtain pretreated left and right lower limb muscle surface electromyogram signals, left foot plantar pressure and right foot three-dimensional acceleration.

[0055] The feature extraction module is configured to extract features from the preprocessed surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration, respectively, to obtain time-domain slope change features and average absolute value features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0056] The feature combination module is configured to combine the time-domain slope change features and the average absolute value features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration, respectively, to obtain combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0057] The data set construction module is configured to construct a training set and a test set using the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0058] The three-class gait prediction model training module is configured to construct a three-class gait prediction model, train the three-class gait prediction model based on the constructed training set, test the three-class gait prediction model training result based on the constructed test set, and obtain a trained three-class gait prediction model.

[0059] The right foot movement direction prediction module is configured to input the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration to be predicted into the trained three-class gait prediction model for right foot movement direction prediction, and obtain a right foot movement direction prediction result.

[0060] Embodiment 3:

[0061] S1. Obtain the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0062] First, the surface electromyography signals of the left and right lower limbs sEMG (the muscle channels used in this embodiment include the biceps brachii, the medial vastus muscle, the gastrocnemius muscle and the tibialis anterior muscle of the left and right legs), the left foot plantar pressure and the right foot three-dimensional acceleration. The full name of sEMG is Surface Electromyography, which means surface electromyography signal.

[0063] In this step, the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are obtained through the OPEN BCI wireless signal acquisition system, the motion signal wireless acquisition device Shadow and the Vive external headset device.

[0064] The OPEN BCI wireless signal acquisition system has a sampling frequency of 500 Hz. Each foot pressure insole includes two sensors at the toe and heel. The foot pressure insole is connected to the motion signal wireless acquisition device Shadow. The pressure signal is sent to the software system of the motion signal wireless acquisition device Shadow through the WiFi of the motion signal wireless acquisition device Shadow.

[0065] The motion signal wireless acquisition device Shadow is a motion capture system including hardware and software. It can measure the kinematics data of seven positions of the waist, thigh, lower leg and foot through a three-axis accelerometer, gyroscope and magnetometer. The sampling frequency is 100 Hz.

[0066] S2. The obtained left and right lower limb muscle surface electromyography signals, left foot pressure and right foot three-dimensional acceleration are resampled and pretreated to obtain the pretreated left and right lower limb muscle surface electromyography signals, left foot pressure and right foot three-dimensional acceleration.

[0067] The obtained left and right lower limb muscle surface electromyography signals, left foot pressure and right foot three-dimensional acceleration are resampled and pretreated to obtain the pretreated left and right lower limb muscle surface electromyography signals, left foot pressure and right foot three-dimensional acceleration. The resampling frequency is 500 Hz.

[0068] In this step, the obtained left and right lower limb muscle surface electromyography signals are also filtered and denoised to obtain the filtered and denoised left and right lower limb muscle surface electromyography signals.

[0069] In this step, the obtained left and right lower limb muscle surface electromyography signals are filtered and denoised by using a band-pass filter (specifically, an Elliptic band-pass filter with a pass band of 10-350 Hz) and wavelet denoising to obtain the filtered and denoised left and right lower limb muscle surface electromyography signals.

[0070] S3. The pretreated left and right lower limb muscle surface electromyography signals, left foot pressure and right foot three-dimensional acceleration are respectively extracted to obtain the time domain slope change feature and average absolute value feature corresponding to the left and right lower limb muscle surface electromyography signals, left foot pressure and right foot three-dimensional acceleration.

[0071] In this step, the pre-processed surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are respectively extracted by using the multi-scale time window method to obtain the time domain slope sign change (SSC) features and the mean absolute value (MAV) features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration. The length of the time window is set to 100 ms, 250 ms and 500 ms respectively.

[0072] S4. The time domain slope sign change features and the mean absolute value features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are combined to obtain the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration.

[0073] In this step, the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are obtained in the form of a vector group.

[0074] S5. The combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are used to construct a training set and a test set.

[0075] The combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are used to construct a training set and a test set. 70% of the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are used as the training set, and 30% are used as the test set. As other embodiments, the 70% and 30% in this step can be adjusted according to actual needs, for example, 80% of the combined features corresponding to the surface electromyography signals of the left and right lower limbs, the left foot plantar pressure and the right foot three-dimensional acceleration are used as the training set, and 20% are used as the test set.

[0076] S6. A three-class gait prediction model is constructed, the three-class gait prediction model is trained based on the constructed training set, the three-class gait prediction model training result is tested based on the constructed test set, and a trained three-class gait prediction model is obtained.

[0077] In this step, the LIBSVM toolbox is used to construct a three-class gait prediction model, the three-class gait prediction model is trained based on the constructed training set, the three-class gait prediction model training result is tested based on the constructed test set, and a trained three-class gait prediction model is obtained.

[0078] S7. The combined features corresponding to the surface electromyography signals of the left and right lower limbs muscles to be predicted, the left foot plantar pressure and the right foot three-dimensional acceleration are input into the trained three-class gait prediction model to predict the right foot movement direction, and a right foot movement direction prediction result is obtained.

[0079] In order to verify the effectiveness of the contralateral movement direction prediction method of ipsilateral lower limb electromyography signals proposed in the application, the embodiment first designs a VR-based kicking game experiment paradigm, and then uses the method proposed in the application to predict the contralateral movement direction of the ipsilateral lower limb electromyography signals. The control principle and control process of the VR-based kicking game experiment paradigm are as shown in Figure 3 and Figure 4 The specific control principle and control process of the VR-based kicking game experiment paradigm are as follows:

[0080] The game includes three lower limb actions of kicking to the left, kicking to the right and kicking to the middle. The game process includes three processes of stimulus presentation, signal processing and game control, which cooperate with each other. At a specific time, communication is carried out through TCP / IP to realize the active control of the virtual device by the game player through his own bioelectricity signals. The whole game process needs to be completed on two computers. The system stimulus presentation, sEMG and movement data acquisition and synchronization are completed in computer 2, and the signal processing and VR game control are completed in computer 1. After the game starts, the picture and voice prompt of the action stimulus in the experiment paradigm are presented in the display of computer 2 and the VR game model of computer 1 through the human-computer interface. At the same time, the collected sEMG and movement signals are sent to computer 2 through WiFi and signal synchronization is carried out. The signal processing module, computer 1 receives the synchronized data through TCP / IP protocol. When the stimulus duration exceeds 500 ms and the acceleration of the swing foot (also called the right foot) is greater than the set threshold value (set according to actual needs), the movement intention decoding is started, and the decoding result is converted into a game control instruction, which is sent to computer 2 through TCP / IP protocol, and then sent to unity by computer 2. The game control module controls the VR game according to the instruction type when unity detects the movement instruction. When the number of stimuli reaches the set data value, the stimulus presentation module, signal processing module and game module stop running. During the game process, the action within 500 ms after the instruction is issued may be a false action, so the data is processed after 500 ms. Secondly, if the swing foot acceleration is greater than the set threshold value 3000 ms after the movement instruction is issued, it is considered that the subject does not make the corresponding action, and the current task is ended, waiting for the next task to start.

[0081] The application is based on surface electromyography signals of left and right lower limb muscles, left foot plantar pressure and right foot three-dimensional acceleration to verify the prediction method proposed by the application. The prediction result 100ms before the movement occurs is shown in Table 1.

[0082] Table 1: Prediction result 100ms before the movement occurs

[0083]

[0084] Table 1 data shows that the prediction method proposed by the application can accurately predict the right foot movement direction, proving the effectiveness of the prediction method proposed by the application.

[0085] Embodiment 4:

[0086] Please refer to Figure 5 The application also provides an electronic device 100 for predicting the ipsilateral movement direction of the contralateral lower limb electromyography signal. The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0087] The memory 101 can be used to store the computer program 103, and the processor 102 can realize the steps of the ipsilateral movement direction prediction method of the contralateral lower limb electromyography signal by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required by a function (such as a sound playing function, an image playing function, etc.), etc.; the data storage area can store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 can include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device.

[0088] The at least one processor 102 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic, discrete hardware components, etc. The processor 102 can be a microprocessor or the processor 102 can also be any conventional processor, etc., which is a control center of the electronic device 100 and connects all parts of the electronic device 100 through various interfaces and lines.

[0089] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a contralateral movement direction prediction method of ipsilateral lower limb myoelectric signals, and the processor 102 can execute the plurality of instructions to implement:

[0090] Obtaining surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration;

[0091] Resampling and preprocessing the obtained surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration to obtain preprocessed surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration;

[0092] Extracting features from the preprocessed surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration respectively to obtain time-domain slope change features and average absolute value features corresponding to the surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration;

[0093] Combining the obtained time-domain slope change features and average absolute value features corresponding to the surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration respectively to obtain combined features corresponding to the surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration;

[0094] Constructing a training set and a test set using the combined features corresponding to the surface myoelectric signals of left and right lower limbs, left foot plantar pressure and right foot three-dimensional acceleration;

[0095] Constructing a three-class gait prediction model, training the three-class gait prediction model based on the constructed training set, testing the three-class gait prediction model training result based on the constructed test set, and obtaining the trained three-class gait prediction model;

[0096] The combined features corresponding to the surface electromyogram signals of the left and right lower limbs muscles to be predicted, the left foot plantar pressure and the right foot three-dimensional acceleration are input into the trained three-class gait prediction model to perform right foot movement direction prediction, and a right foot movement direction prediction result is obtained.

[0097] Embodiment 5:

[0098] The modules / units integrated in the electronic device 100, if realized in the form of software function units and sold or used as independent products, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program can implement the steps of each method embodiment when executed by a processor. The computer program includes computer program code, which can be in the form of source code, object code, executable files or some intermediate forms. The computer readable medium can include any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory and read-only memory (ROM).

[0099] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can take the form of a computer program product implemented on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0100] The present application is described with reference to flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to embodiments of the present application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, and the combination of flows and / or blocks in the flowcharts and / or block diagrams can be implemented by computer program instructions. These computer program instructions can be provided to a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the instructions executed by the computer or other programmable data processing devices produce a device that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks Figure 1 The device that implements the functions specified in one flow or multiple flows and / or blocks

[0101] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flow Figure 1 The functions described can be implemented in one or more flow(s) and / or block(s) and / or in combination with other functions. Figure 1 The functions described can be implemented in one or more flow(s) and / or block(s) and / or in combination with other functions.

[0102] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow Figure 1 The functions described can be implemented in one or more flow(s) and / or block(s) and / or in combination with other functions. Figure 1 The functions described can be implemented in one or more flow(s) and / or block(s) and / or in combination with other functions.

[0103] Finally, it should be noted that the above-mentioned embodiments are merely used to illustrate the technical solutions of the present application, rather than limit the present application. Although the present application has been described in detail with reference to the above-mentioned embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalent replaced without departing from the spirit and scope of the present application, and any modification or equivalent replacement should be covered in the protection scope of the claims of the present application.

Claims

1. A method for predicting the ipsilateral movement direction of contralateral lower limb electromyographic signals, characterized in that, Includes the following steps: Acquire surface electromyographic signals of muscles in both lower limbs, plantar pressure of the left foot, and three-dimensional acceleration of the right foot; The surface electromyography (EMG) signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot were resampled and preprocessed to obtain the preprocessed surface EMG signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot. In the step of resampling and preprocessing the obtained surface electromyography (EMG) signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot to obtain the preprocessed surface EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot, the obtained surface EMG signals of the left and right lower limb muscles are also filtered and denoised to obtain the filtered and denoised surface EMG signals of the left and right lower limb muscles. Feature extraction was performed on the surface electromyography (EMG) signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot after preprocessing. The temporal slope change features and mean absolute value features of the surface EMG signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot were obtained. In the step of extracting features from the preprocessed surface electromyography (EMG) signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot to obtain the temporal slope change features and mean absolute value features corresponding to the EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot, a multi-scale time window method is specifically used to extract features from the preprocessed surface EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot to obtain the temporal slope change features and mean absolute value features corresponding to the EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot. The time-domain slope change characteristics and mean absolute value characteristics of the surface electromyography signals of the left and right lower limb muscles, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot are combined to obtain the combined characteristics of the surface electromyography signals of the left and right lower limb muscles, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot. In the step of combining the obtained surface electromyography (EMG) signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot with the temporal slope change characteristics and the average absolute value characteristics, respectively, to obtain the combined features of the surface EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot, the specifically obtained combined features of the surface EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot are features in the form of vector groups. Training and test sets were constructed using the combined features of surface electromyography signals of the muscles of the left and right lower limbs, plantar pressure of the left foot, and three-dimensional acceleration of the right foot. A three-class gait prediction model is constructed, trained on the constructed training set, and tested on the constructed test set to obtain a well-trained three-class gait prediction model. In the step of constructing a three-class gait prediction model, training the three-class gait prediction model based on the constructed training set to obtain a trained three-class gait prediction model, the LIBSVM toolbox is specifically used to construct the three-class gait prediction model. The combined features of the surface electromyography signals of the muscles of the left and right lower limbs to be predicted, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot are input into the trained three-class gait prediction model to predict the direction of movement of the right foot, and the prediction result of the direction of movement of the right foot is obtained.

2. The method for predicting ipsilateral movement direction from contralateral lower limb electromyographic signals according to claim 1, characterized in that, Specifically, bandpass filtering and wavelet denoising were used to filter and denoise the surface electromyography (EMG) signals of the left and right lower limb muscles, resulting in filtered and denoised EMG signals of the left and right lower limb muscles.

3. The method for predicting ipsilateral movement direction from contralateral lower limb electromyographic signals according to claim 1, characterized in that, The training set consists of 70% of the combined features of surface electromyography signals of the muscles of the left and right lower limbs, plantar pressure of the left foot, and three-dimensional acceleration of the right foot, and the test set consists of 30%.

4. A system for predicting ipsilateral movement direction based on contralateral lower limb electromyographic signals, characterized in that, It includes a data acquisition module, a data preprocessing module, a feature extraction module, a feature combination module, a dataset construction module, a three-class gait prediction model training module, and a right foot movement direction prediction module; The data acquisition module is used to acquire surface electromyographic signals of the muscles of the left and right lower limbs, plantar pressure of the left foot, and three-dimensional acceleration of the right foot. The data preprocessing module is used to resample and preprocess the obtained surface electromyography signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot to obtain the preprocessed surface electromyography signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot. The data preprocessing module further filters and denoises the obtained surface electromyography (EMG) signals of the left and right lower limb muscles to obtain filtered and denoised surface EMG signals of the left and right lower limb muscles. The feature extraction module is used to extract features from the preprocessed surface electromyography (EMG) signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot, respectively, to obtain the temporal slope change features and mean absolute value features corresponding to the surface EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot. The feature extraction module specifically uses a multi-scale time window method to extract features from the preprocessed surface electromyography (EMG) signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot, respectively, to obtain the temporal slope change features and mean absolute value features corresponding to the surface EMG signals of the left and right lower limb muscles, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot. The feature combination module is used to combine the obtained surface electromyography signals of the left and right lower limb muscles, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot, and the time-domain slope change features and average absolute value features, respectively, to obtain the combined features of the surface electromyography signals of the left and right lower limb muscles, the plantar pressure of the left foot and the three-dimensional acceleration of the right foot. The feature combination module specifically obtains the combined features of the surface electromyography signals of the muscles of the left and right lower limbs, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot as features in the form of vector groups. The dataset construction module is used to construct training and testing sets using the combined features of surface electromyography signals of the muscles of the left and right lower limbs, plantar pressure of the left foot, and three-dimensional acceleration of the right foot. The three-class gait prediction model training module is used to construct a three-class gait prediction model, train the three-class gait prediction model based on the constructed training set, and test the training results of the three-class gait prediction model based on the constructed test set to obtain a trained three-class gait prediction model. The three-class gait prediction model training module specifically utilizes the LIBSVM toolbox to construct the three-class gait prediction model; The right foot movement direction prediction module is used to input the combined features of the surface electromyography signals of the muscles of the left and right lower limbs to be predicted, the plantar pressure of the left foot, and the three-dimensional acceleration of the right foot into the trained three-class gait prediction model to predict the right foot movement direction and obtain the right foot movement direction prediction result.

5. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for predicting the ipsilateral movement direction of the electromyographic signal of the contralateral lower limb as described in any one of claims 1 to 3.

6. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for predicting the ipsilateral movement direction of the electromyographic signal of the contralateral lower limb as described in any one of claims 1 to 3.

Images