An intelligent prosthetic system for identity verification and myoelectric text conversion

Abstract

The application relates to an intelligent artificial limb system for identity authentication and myoelectric text conversion and belongs to the technical field of robots; the intelligent artificial limb system solves the problem that the intelligent artificial limb system in the prior art cannot realize the functions of myoelectric activation, text conversion and identity authentication; the intelligent artificial limb system comprises, which are electrically connected in sequence, a myoelectric signal detection sensor, a myoelectric signal recognition control module, a motor driving device and a bionic hand device; wherein the myoelectric signal detection sensor is used for detecting myoelectric signals and sending the myoelectric signals to the myoelectric signal recognition control module; the myoelectric signal recognition control module is used for recognizing and processing the received myoelectric signals, and mode conversion is carried out according to the myoelectric signal recognition result, so as to realize identity authentication, daily action control and conversion of myoelectric signals into texts; the motor driving device is used for controlling the bionic hand device to make actions corresponding to the myoelectric signals based on the recognition result of the myoelectric signal recognition control module, so as to realize daily action control.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of robots, in particular to an intelligent prosthetic system for identity verification and myoelectric text conversion. BACKGROUND

[0002] Upper limb amputees can assist them in completing the basic object picking and placing in daily life by wearing intelligent prostheses. The current mainstream intelligent prosthesis mainly controls the hand movement through the acquisition of myoelectric signals of the residual limb, decodes the action intention of the amputee through signal processing and pattern recognition algorithms, and then controls the bionic hand to perform corresponding operations. The current research on bionic hands is committed to improving the mechanical structure or control strategy to design a bionic hand that is more in line with human mechanics and structure, to achieve more delicate hand movements and to provide better user experience for patients. However, the prior art ignores another scenario where people often use both hands: typing. If a single-arm amputee can still use the other healthy hand to type, a double-arm amputee loses this ability completely. Amputees who have lost their fingers can achieve character writing by controlling wrist movement. Therefore, an intelligent prosthesis that realizes both object picking and handwriting input capability has become an urgent problem to be solved.

[0003] In addition, as the technology of intelligent prostheses becomes more mature, their application scenarios are also becoming more and more extensive. Precise identity verification of users using intelligent prosthetic systems has become an essential function. The current existing identity verification methods usually identify the identity through the collection of physiological characteristics (such as DNA, fingerprints, faces, irises, etc.) and behavioral characteristics (such as handwriting, voice, gait, etc.) inherent to the human body. However, there are different risks when using these physiological characteristics for verification. DNA can be easily stolen through hair or saliva; faces can be forged by 3D models; fingerprints can be copied from latex; voices can be copied by recording devices; and irises can be forged by printing features on contact lenses. Surface myoelectric signals can establish a changeable identity feature while maintaining the user's biological uniqueness, thereby improving personal security. Therefore, the research on identity verification methods based on surface myoelectric signals not only solves the function of user verification of intelligent prosthetic systems, but also helps to expand the application of new biometric technologies in the Internet and human-computer interaction. How to achieve identity verification function through surface myoelectric signals has become an extremely significant research direction. SUMMARY

[0004] In view of the above analysis, the present application aims to provide an intelligent prosthetic system for identity verification and myoelectric text conversion; solve the problem that the intelligent prosthetic system in the prior art cannot realize myoelectric activation, text conversion and identity verification functions.

[0005] The objective of this invention is mainly achieved through the following technical solutions:

[0006] This invention provides an intelligent prosthetic system for identity verification and electromyography (EMG) text conversion. The intelligent prosthetic system includes an EMG signal detection sensor, an EMG signal recognition and control module, a motor drive device, and a bionic hand device, which are connected in sequence.

[0007] The electromyography (EMG) signal detection sensor includes electrode pads for attaching to the surface of the residual limb wearing the smart prosthesis, for detecting EMG signals and sending them to the EMG signal recognition and control module;

[0008] The electromyography signal recognition and control module is used to recognize and process the received electromyography signals, and to perform mode conversion based on the electromyography signal recognition results, so as to realize identity verification, daily movement control and electromyography signal to text conversion;

[0009] The motor drive device is used to control the bionic hand device to perform actions corresponding to electromyographic signals based on the recognition results of the electromyographic signal recognition and control module, thereby realizing daily movement control.

[0010] Furthermore, the electromyography signal recognition and control module includes a mode switching unit, an authentication unit, a daily control unit, and an electromyography text conversion unit;

[0011] The mode switching unit is used to switch the working mode of the intelligent prosthetic system, including daily control mode and electromyography-text conversion mode.

[0012] The authentication unit is used to identify whether the user to be authenticated is an authorized user in the authentication mode;

[0013] The daily control unit is used to perform actions corresponding to electromyographic signals in the daily control mode;

[0014] The electromyography-to-text conversion unit is used to convert electromyography signals into text in the electromyography-to-text conversion mode.

[0015] Furthermore, the electromyographic text conversion unit includes a pre-trained electromyographic model and a language model;

[0016] The electromyography model is trained using a pre-built electromyography text conversion dataset. It is used to extract features and classify the electromyography signals corresponding to each gesture, and to obtain the predicted probability of each character corresponding to each gesture.

[0017] The language model is used to perform character search based on the character prediction probability corresponding to each gesture output by the electromyography model, and obtain the converted text.

[0018] Furthermore, the electromyography (EMG) model is based on a deep separable convolutional network, and the training of the EMG model includes:

[0019] The electromyography (EMG) signal detection sensor is used to collect multiple dynamic gesture EMG signals from multiple users. The dynamic gesture EMG signals include the corresponding EMG signals obtained by controlling wrist movements to perform writing actions of multiple English letters and punctuation marks.

[0020] The collected electromyographic signals were amplified to construct an electromyographic text conversion dataset;

[0021] The electromyography (EMG) text conversion dataset is input into a depthwise separable convolutional network model, and the EMG model is obtained by iteratively updating the model through a loss function.

[0022] Furthermore, data augmentation can be performed using any of the following methods:

[0023] The waveform is altered to amplify the data, including: multiplying the sampled value of the acquired electromyographic signal by a preset ratio to change the amplitude; interpolating and downsampling the acquired electromyographic signal to change the velocity, thus obtaining the amplified electromyographic signal;

[0024] Data augmentation is performed by perturbing the detection results, including: after obtaining the complete electromyographic activity segment of the electromyographic signal through the electromyographic activity segment detection method, obtaining different activity segments of the electromyographic signal by moving the detection window left and right to obtain the amplified electromyographic signal; or by increasing the judgment threshold of the activity segment to reduce the length of the activity segment; or by decreasing the judgment threshold of the activity segment to increase the length of the activity segment to obtain the amplified electromyographic signal.

[0025] Data augmentation is achieved by modifying the spectrum, including altering the spectrum of the electromyographic signal through time warping, frequency masking, and temporal masking to obtain an amplified electromyographic signal.

[0026] Furthermore, the language model is used to perform character search based on the character prediction probability corresponding to each gesture output by the electromyography model, to obtain the converted text, including:

[0027] Save the top m characters with the highest predicted probability for each gesture;

[0028] If no electromyographic signal is detected after a preset time, it is considered a space, and all characters between the spaces are taken as a prediction combination;

[0029] Based on the order of predicted probabilities from largest to smallest, the first m predicted characters corresponding to the first gesture in the space-space string are taken as the root node. Based on the order of each gesture and the predicted probabilities of the first m predicted characters corresponding to each gesture, the predicted characters corresponding to each gesture are combined and used as child nodes. A search tree is built in sequence, and each branch of the search tree is a group of prediction combinations. The prediction combinations are matched in the corpus.

[0030] If a predicted combination exists in the corpus, it is identified as the final word recognition result, and the search tree construction is terminated; otherwise, the search tree continues to be built and the search continues until all possible combinations have been searched; if none of the obtained combinations appear in the corpus, the maximum predicted probability of each character is taken as the final prediction result of the string.

[0031] Furthermore, the authentication unit includes a pre-trained authentication model for authenticating users wearing smart prostheses; the training of the authentication model includes:

[0032] Obtain the electromyographic signals of authorized users’ password gestures and construct a training dataset of password gesture electromyographic signals. The training dataset includes N sets of password gesture electromyographic signals of authorized users and corresponding user labels.

[0033] The single-classification model is trained using the training data of each authorized user in the training dataset, and a threshold is set to obtain the identity model of each user.

[0034] The process of verifying the identity of users wearing smart prosthetics includes:

[0035] The electromyography (EMG) signals of a user wearing a smart prosthesis are acquired, preprocessed, and then the preprocessed EMG signals are subjected to active segment detection and feature extraction. The extracted feature data is then input into an identity verification model.

[0036] Retrieve the pre-established identity model of the authorized user to be matched, and determine whether the user to be verified is an authorized user or an unauthorized user based on a pre-set threshold.

[0037] Furthermore, the step of training a single-classification model using the training data of each authorized user in the training dataset to obtain an identity model for each user includes:

[0038] N sets of training data from authorized users are used as positive class training samples, and the positive class training sample data are mapped from the original space to the feature space through a nonlinear transformation function.

[0039] Using the support vector description algorithm, a minimum hypersphere is trained based on the training data of each authorized user mapped to the feature space. The data of all users are input into the identity verification model to obtain the distance of each user's data to the surface of the minimum hypersphere. A threshold is set based on the distance to obtain the corresponding user identity model.

[0040] Furthermore, the daily control unit is trained using a pre-built daily control electromyography dataset to identify electromyography signals of daily control gestures, and controls the bionic hand device to complete the corresponding daily control actions through the motor drive device.

[0041] Furthermore, the mode switching unit is trained on the conjoined network based on the activated gesture electromyography signal dataset, and is used to perform electromyographic wake-up or mode switching on the smart prosthesis in low-power sleep mode after detecting the activated gesture electromyography signal, including:

[0042] The user's electromyography (EMG) signals are collected in sleep mode, and the EMG signals are sequentially subjected to sliding window framing, preprocessing, active segment detection, and feature extraction.

[0043] The features of each frame of electromyography (EMG) signal extracted are input into the mode switching unit to calculate the similarity with the pre-stored EMG features of activated gestures; based on a preset threshold, it is determined whether the acquired EMG signal is an activated frame.

[0044] Accumulate 5 frames and perform a mode decision. If more than 3 of the 5 frames are identified as active frames, then the gesture is considered an active gesture; otherwise, it is considered an inactive gesture.

[0045] The beneficial effects of this technical solution are:

[0046] 1. This invention constructs an electromyography-text conversion model that combines an electromyography model and a language model by collecting and amplifying electromyographic signals of text characters, thereby realizing electromyography-to-text sequence recognition. This invention can restore the ability of amputees to input characters and, combined with gesture recognition, enable them to grasp everyday objects, thus maximizing the restoration of amputees' self-care abilities in daily life and work.

[0047] 2. This invention enables the activation of wearable devices through electromyography signals, allowing the devices to enter a low-power sleep mode when not in use, thereby reducing power consumption and minimizing accidental touches.

[0048] 3. This invention applies the SVDD model to an authentication method based on surface electromyography (SEMG) signals. This model only needs to collect the signals of authorized users to distinguish all unauthorized users corresponding to them. The method is simple and efficient. It realizes a real-time portable authentication system based on surface electromyography (SEMG) signals. The system solution provided can not only meet the requirements of real-time performance, but also meet the security performance level of biometrics.

[0049] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description

[0050] The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Throughout the drawings, the same reference numerals denote the same parts.

[0051] Figure 1 This is a schematic diagram of the structure of an intelligent prosthetic system for identity verification and electromyographic text conversion according to an embodiment of the present invention.

[0052] Figure 2 This is a schematic diagram illustrating the mode switching of the intelligent prosthetic system according to an embodiment of the present invention;

[0053] Figure 3 This is a schematic diagram of the electromyographic activation process according to an embodiment of the present invention;

[0054] Figure 4 This is a hardware module diagram of an identity verification system based on surface electromyography signals according to an embodiment of the present invention. Detailed Implementation

[0055] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0056] This embodiment presents an intelligent prosthetic system for identity verification and electromyographic text conversion, such as... Figure 1 As shown, it includes an electromyography (EMG) signal detection sensor, an EMG signal recognition and control module, a motor drive device, and a bionic hand device, which are connected in sequence; wherein,

[0057] The electromyography (EMG) signal detection sensor includes electrode pads for attaching to the surface of the residual limb of a person wearing a smart prosthesis, for detecting EMG signals and sending them to the EMG signal recognition and control module;

[0058] The electromyography (EMG) signal recognition and control module is used to recognize and process the received EMG signals, and to perform pattern conversion based on the EMG signal recognition results, thereby realizing identity verification, daily movement control, and conversion of EMG signals to text.

[0059] The motor drive device is used to control the bionic hand device to perform actions corresponding to electromyographic signals based on the recognition results of the electromyographic signal recognition control module, thereby realizing daily movement control.

[0060] Specifically, the intelligent prosthetic system in this embodiment uses surface electromyography (EMG) signals from the residual limb as the signal source for recognizing movement intentions, assisting amputees in maximizing their ability to grasp objects and input handwriting. In addition to the aforementioned structure, the intelligent prosthetic system also includes a cavity for connecting the patient's residual limb and the bionic hand device. The shape of the bionic hand device in the system is fixed, while the EMG acquisition and recognition module and the cavity can be adaptively designed according to different types of amputees. During EMG signal acquisition, the electrode pads of the EMG signal detection sensor are attached to the surface of the residual limb, ensuring that the absolute position of the electrode pads remains as constant as possible during each acquisition.

[0061] Figure 2 This diagram illustrates the mode switching process of the intelligent prosthetic system in this embodiment. When the system is in sleep mode, it operates at low power. The system wakes up by detecting the electromyographic (EMG) signal corresponding to the activated gesture through the mode switching unit, switching the intelligent prosthetic system to the daily control mode. In daily control mode, this embodiment designs four commonly used gestures to perform most hand tasks in daily life. Activated gestures are also recognized in daily control mode. If an activated gesture is detected in daily control mode, the system switches to EMG-to-text conversion mode. In EMG-to-text conversion mode, the intelligent prosthetic system of this embodiment can recognize the EMG signals corresponding to 26 lowercase English letters and 2 punctuation marks, convert them into text information, and transmit them wirelessly or via wired means to display devices such as mobile phones and computers for display, thus realizing the conversion of EMG signals into text sequences. Furthermore, the system can be switched back to sleep mode by activating a gesture in EMG-to-text conversion mode.

[0062] Specifically, the electromyography signal recognition and control module includes a mode switching unit, an authentication unit, a daily control unit, and an electromyography text conversion unit;

[0063] The mode switching unit is used to switch the working modes of the intelligent prosthetic system. The working modes include authentication mode, daily control mode and electromyography-text conversion mode.

[0064] The authentication unit is used to identify whether the user to be authenticated is an authorized user in authentication mode;

[0065] The daily control unit is used to perform actions corresponding to electromyographic signals in daily control mode;

[0066] The electromyography-text conversion unit is used to convert electromyography signals into text information in electromyography-text conversion mode.

[0067] In this embodiment, the mode switching unit, daily control unit, and electromyography text conversion unit of the intelligent prosthetic system all require data collection and construction of training datasets, which are then used for training.

[0068] Specifically, this embodiment collects data and constructs a database from no fewer than five amputees (with or without wrist or forearm amputation). Each patient's dataset is collected in two parts: static gestures and dynamic gestures. Static gestures include electromyographic activation gestures used by the mode switching unit and daily control gestures used in the daily controllable mode; dynamic gestures are those used by the electromyographic text conversion unit. During electromyographic signal acquisition, electrodes are attached to the surface of the patient's residual limb, ensuring that the absolute position of the electrodes remains as constant as possible during each acquisition.

[0069] For static gesture acquisition tasks, the tasks include the electromyographic activation gesture "OK" (gesture 1) and daily control gestures. Daily control gestures include at least four gestures, which can be a five-finger grip (gesture 2, used for grasping tasks), a thumb and index finger pinch (gesture 3, used for pinching tasks), a five-finger spread (gesture 4, used for greeting), and an index finger point (finger 5, used for indicating direction).

[0070] For the dynamic gesture acquisition task, at least 26 lowercase English letters and at least two punctuation marks (comma and period) are included, totaling at least 28 gestures. The writing of the 26 English letters and two punctuation marks is achieved by controlling the movement trajectory of the wrist to achieve a shape similar to the characters. In this embodiment, the comma is written as a greater than sign ">", and the period is written as a tilde "~" to enhance the distinguishability of the electromyographic signals corresponding to each gesture.

[0071] More specifically, the static gesture collection task is divided into no fewer than 9 sessions (each session includes all static gestures), with one independent session per day, and the collected content is completely identical. At least 4 sessions are used as the training set, at least 2 sessions as the validation set, and at least 3 sessions as the test set. Each session is divided into 5 trials, executing gestures 1 through 5 respectively. In each trial, each gesture is executed for 3 seconds, followed by a 3-second rest, for a total of 20 executions. Therefore, each session generates 100 (5*20) sets of data.

[0072] The dynamic gesture acquisition task is also divided into at least 9 sessions (each session includes all dynamic gestures), with one independent session per day. At least 4 sessions are used as the training set, at least 3 sessions as the validation set, and at least 2 sessions as the test set. In this embodiment, the training set acquisition task is to acquire dynamic electromyographic signals of 26 lowercase English letters, commas, and periods. Each session is divided into 28 trials, executing 28 gestures respectively, with each gesture executed for 3 seconds followed by a 3-second rest, for a total of 10 trials. Specifically, in this embodiment, at least one session of the validation set acquires 52 commonly used words, along with 4 sets each of comma, period, and activation gestures, for a total of 55 trials; at least one session acquires 30 commonly used phrases, along with 4 sets each of comma, period, and activation gestures, for a total of 33 trials; at least one session acquires 15 sentences with punctuation marks, along with 4 sets of activation gestures, for a total of 16 trials. The test set uses text-based content collected in each session, sourced from social media, news websites, and technology books. Within each trail, each character gesture has a 3-second execution time followed by a 3-second rest period.

[0073] The collected data is divided into three datasets using the above method: activated gesture EMG signal dataset, daily control EMG dataset, and EMG text conversion dataset. The activated gesture EMG signal dataset includes positive and negative pairs and their corresponding labels. Positive pairs consist of any two activated gesture EMG signals from the same user collected in different sessions; in this embodiment, the label for positive pairs is set to 1. Negative pairs are sample pairs consisting of activated and non-activated gesture EMG signals, labeled with 0. The daily control EMG dataset includes four daily control gesture EMG signals and their corresponding gesture classification labels. The EMG text conversion dataset includes the aforementioned dynamic gesture EMG signals and their corresponding text labels.

[0074] After collecting the training samples, the electromyographic signal data in the training samples needs to be processed for calculation in each unit. The processing includes:

[0075] Sliding window framing: The usual method is to divide the signal into frames by passing it through a window with a length of 128ms and a movement step of 64ms.

[0076] Signal preprocessing: The framed signal is filtered out by a Butterworth 4th order 30-500Hz bandpass filter to remove baseline drift and motion artifacts, and then filtered out by a 50Hz notch filter to remove power frequency interference.

[0077] Active Segment Detection (EAD): In this embodiment, the electromyography (EMG) signal detection sensor is a multi-channel acquisition device. During active segment detection, the EMG signal from one channel is selected, and its pre-processed framed signal is used for feature extraction. A feature matrix is ​​formed by calculating the root mean square (RMS) of the sub-bands using a three-frequency sub-band filtering method (80Hz-150Hz, 150Hz-300Hz, 300Hz-450Hz). Since the EMG data in the feature matrix is ​​unlabeled, it is impossible to distinguish between EMG signals and noise beforehand. This embodiment is based on the difference between EMG and noise. A clustering approach using the expectation-maximization algorithm is employed, iterating through multiple rounds to aggregate similar data. Then, the maximum a posteriori probability estimate of the Gaussian mixture model parameters is obtained based on the aggregated data, thereby dividing the framed signals into two categories: active frame signals and resting frame signals.

[0078] Feature Extraction: The detected active frame signal is used as the unit for feature extraction, extracting signal features from all channels. Two types of feature extraction techniques are used: intra-channel features and inter-channel features. Intra-channel features are used to calculate the characteristics of a single-channel signal. Intra-channel features include time-domain features, frequency-domain features, and autoregressive coefficients. Time-domain features typically include root mean square (RMS), waveform length, short-time zero-crossing rate, mean absolute value, and rate of change of slope sign. Frequency-domain features include mean amplitude spectrum, median frequency, and mean power frequency. Autoregressive coefficients are generally selected from 1st to 4th order autoregressive coefficients. Inter-channel features calculate the characteristics between pairs of channels; inter-channel features include mutual information and Pearson correlation coefficient.

[0079] After processing the data and extracting features from each dataset, it can be used to train each model.

[0080] First, the mode switching unit is trained on the conjoined network based on the activated gesture EMG signal dataset. It is used to activate the smart prosthesis in low-power sleep mode or switch the working mode of the smart prosthesis system after detecting the activated gesture EMG signal. The working modes include daily control mode and EMG-text conversion mode. EMG activation technology, also known as key gesture detection technology, requires detecting the EMG signal corresponding to a predefined activated gesture or key gesture from a series of EMG signals, without needing to recognize all EMG signals. The EMG activation technology in this embodiment is similar to voice wake-up technology. Voice wake-up technology is the foundation for enabling voice interaction capabilities of embedded devices and can be applied to various devices, such as mobile phones, smart speakers, robots, smart homes, in-vehicle devices, and wearable devices. Typically, the device wake-up word is default or pre-set, usually consisting of 3 or 4 syllables, such as Apple's "Hi Siri," Google Assistant's "Hey Goggle," Alibaba's "Tmall Genie," and Xiaomi's "Xiao Ai." When the device is in sleep mode, it continues to pick up and detect wake words. Once a wake word is detected, the device switches from sleep mode to working mode, awaiting subsequent interaction. Voice wake-up technology requires detecting the complete wake word, while electromyography (EMG) activation technology only needs to detect the signal generated by the activation gesture. When the activation gesture is executed and held, the generated EMG signal is continuous and consistent, thus the activation gesture can be recognized during its execution. This invention uses the "OK" gesture as the activation gesture. Figure 3 This is a flowchart of the electromyography activation technology of the present invention.

[0081] Specifically, a Siamese Network is a symmetric network where two symmetrical parts share the same weights and have identical structures. It can employ Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs). The goal is to learn whether the inputs to the two symmetrical parts are identical. The output layer of the Siamese Network uses a loss function to fuse the two symmetrical parts. This loss function represents the similarity or distance between the EMG signals of the test samples input to the two input terminals of the Siamese Network and the EMG signals of the activated gestures. Binary crossentropy is typically used, and its expression is:

[0082]

[0083] Among them, y i The predicted distribution of the test samples, To determine the true distribution of the activation gesture template samples.

[0084] The frame signals of activated gestures are designated as positive samples, while those of other gestures are designated as negative samples. During training, the same number of positive pairs (positive sample - positive sample, labeled 1) and negative pairs (negative sample - positive sample, labeled 0) are used to ensure sample balance. During testing, the electromyographic (EMG) signal features of the test samples and the pre-stored EMG signal feature templates of activated gestures are input into two symmetrical structures of the conjoint network, respectively. The posterior probability of the EMG signal features is obtained, representing the similarity between the EMG signal feature and the EMG feature of the activated gesture, ranging from 0 to 1. A suitable threshold is set for binarization, i.e., determining whether the frame is an activated or inactive frame.

[0085] In practical applications, the user's electromyography (EMG) signals are collected in sleep mode, and the EMG signals are subjected to sliding window framing, preprocessing, active segment detection, and feature extraction.

[0086] The features of each frame of electromyography (EMG) signal extracted are input into the connected network of the mode switching unit to calculate the similarity with the pre-stored EMG features of the activated gesture; based on a preset threshold, it is determined whether the acquired EMG signal is an activated frame.

[0087] Specifically, in this embodiment, five frames are accumulated for a mode decision. If more than three of the five frames are identified as active frames, the gesture is determined to be an active gesture; otherwise, it is an inactive gesture.

[0088] Furthermore, there are five categories of gestures in the daily control mode: activation gestures (gesture 1) and four daily control gestures (gestures 2-5). Gesture recognition algorithms can be modeled using existing classification algorithms. The signal preprocessing, sliding window framing, preprocessing, active segment detection, and feature extraction processes are the same as described above.

[0089] Specifically, this embodiment uses a variant of the recurrent neural network structure as the basic structure of the deep learning model for recognizing everyday control gestures, constructing a stacked LSTM model consisting of two LSTM layers and one bidirectional LSTM layer. The model's input is all features of a single frame of electromyography (EMG) signal. The first LSTM layer is set to 64 nodes, with dropout, recurrent dropout, and return sequences parameters of 0.1, 0.5, and True, respectively. Batch normalization is performed on the output of this layer. Then, the second LSTM layer is set to 64 nodes, with the activation function 'ReLU', a dropout rate of 0.1, a recurrent dropout rate of 0.5, and return sequences set to True. Batch normalization is performed again on the output of this layer. The third layer is a bidirectional LSTM layer with 64 nodes, the activation function 'ReLU', a dropout rate of 0.1, and a recurrent dropout rate of 0.5. The output of this layer after batch normalization is sent to the output layer, which uses the sigmoid function as its activation function and outputs the predicted probabilities of five gestures (gesture 1 to gesture 5). The model's loss function is defined as the classification cross-entropy function, and the error is backpropagated using the rmsprop optimizer.

[0090] When building a deep learning model for recognizing everyday control gestures, we also optimize the model by using residual connections, regularization, Dropout, batch normalization, activation functions, etc., to improve model performance.

[0091] The data in the daily control electromyography dataset were divided into training, testing, and validation sets. After training the model using the data in the training set, the model parameters were iteratively adjusted using the validation set. First, the model was allowed to overfit, then regularization and other optimization methods were added. This iterative optimization process continued until the set of hyperparameters that performed best on the validation set was selected as the final test model.

[0092] Furthermore, the electromyography-to-text (EMG-to-text) unit performs EMG-to-text recognition (ETR), converting electromyographic signals into text sequences. Due to the unique nature of ETR, its smallest recognition unit differs from the phonemes, syllables, characters, or words of Automatic Speech Recognition (ASR), or the words or sentences of Facial Speech EMG-to-text Recognition. The smallest recognition unit of ETR is a discrete, single-character gesture, i.e., lowercase English characters and punctuation marks. These characters can be combined to form arbitrary words, phrases, and sentences.

[0093] The electromyography text conversion unit in this embodiment includes a pre-trained electromyography model (EM) and a language model (LM).

[0094] The electromyography (EMG) model is trained using a pre-built EMG text conversion dataset. It is used to extract features and classify the EMG signals corresponding to each gesture, and obtain the predicted probability of each character corresponding to each gesture.

[0095] The language model is used to perform character search based on the character prediction probability corresponding to each gesture output by the electromyography model, and obtain the converted text.

[0096] The electromyography (EM) and language models in this section are used for validation and deployment. EM relies on a data-augmented EMG database and requires comprehensive character-written EMG data, including handwritten characters, words, and sentences. The time-spectrum of discrete character EMG sequences is extracted as features, and a convolutional neural network (CNN) is used as the EM in this embodiment. LM relies on a text library to describe the connection frequencies between characters. It is constructed using a large amount of text and a string search model is used as the LM in this embodiment. In practical applications, features of each character's EMG sequence are extracted, and the EMG signals are decoded and searched using EM and LM, finally transforming them into grammatically correct text sequences with semantic information.

[0097] Specifically, the training of the electromyography model includes:

[0098] Multiple dynamic gesture electromyography (EMG) signals were collected from multiple users using an EMG signal detection sensor. The dynamic gesture EMG signals included the corresponding EMG signals obtained by controlling wrist movements to perform writing actions of multiple English letters and punctuation marks.

[0099] The collected electromyographic signals were amplified to construct an electromyographic text conversion dataset;

[0100] The electromyography (EMG) text conversion dataset is input into a deep separable convolutional network model, and the EMG model is obtained by iteratively updating the loss function.

[0101] Specifically, deep learning-based electromyography (EMG) models typically require a large amount of data for training, while the data acquisition capabilities for EMG-to-text conversion tasks are very limited. First, the number of gesture categories in this task is large. If the data acquisition methods used for everyday control gesture recognition are still followed, it will require a significant amount of time and effort. Second, static gestures in everyday control modes can be recognized through frame signals, while dynamic gestures in EMG-to-text conversion can only be recognized through complete EMG signals from handwritten characters, which greatly limits the amount of usable data. Therefore, data augmentation methods are needed to expand the amount of handwritten EMG data to improve model performance. This embodiment addresses the problem of insufficient EMG data for EMG-to-text conversion, leading to unsatisfactory training results, by employing various data augmentation methods to increase the amount of training data and achieve more accurate EMG-to-text conversion results.

[0102] Specifically, data augmentation methods include:

[0103] Waveform augmentation: When performing dynamic gestures, the speed and force of each execution are different. Therefore, multiple forces can be simulated by scaling the amplitude of the signal, and different execution speeds can be simulated by scaling the time scale of the original signal. Multiplying the sampled value of the original signal by a fixed ratio achieves amplitude variation, and interpolating and downsampling the original signal achieves speed variation, resulting in augmented samples.

[0104] Data augmentation is achieved by perturbing the detection results: After obtaining the complete electromyographic signal activity segment using the Active Segment Detection (EAD) method, multiple different activity segments can be obtained by moving the detection window left and right. Each activity segment has a different start and end point, but all correspond to a complete gesture. Furthermore, changing the EAD parameters affects the detection results. For example, increasing the activity segment judgment threshold reduces the activity segment length, while decreasing the threshold increases it. Therefore, data augmentation can be performed by adjusting the EAD parameters.

[0105] Data augmentation by modifying the spectra: The method of data augmentation by altering the spectra through time warping, frequency masking, and temporal masking has been shown to greatly improve the performance of automatic speech recognition networks; this method can also be used for data augmentation of electromyographic signals.

[0106] Extensive experiments have demonstrated that data augmentation methods that perturb the detection results are more effective. In this embodiment, by moving the active segment window left and right, the results of the electromyographic active segment detection are expanded to 12 times, thus increasing the size of the entire dataset to 12 times its original size.

[0107] In this embodiment, the electromyography (EMG) model uses a depthwise separable convolutional layer (SepConv2D) as the core network. The model input is the time spectrum of a 1-second EMG signal. A SepConv2D layer is added to the model, with 64 filters, a 3x3 filter space dimension, and 'reLU' as the activation function. The output of the SepConv2D layer is batch normalized and then pooled with a 3x3 kernel. A flattening operation is then performed, followed by a dropout operation at a ratio of 0.5. Two dense layers are then added to the model, with 80 and 10 network nodes respectively, both using 'reLU' as the activation function. The output of each dense layer is batch normalized and then dropout is performed at a ratio of 0.5. Finally, an output layer with 29 nodes and a softmax activation function is added to output the predicted probability of each character gesture. During model compilation, classification cross-entropy is selected as the loss function, and the rmsprop optimizer is chosen as the backpropagation algorithm. The convergence point EMG model is obtained through iterative updates.

[0108] Furthermore, this embodiment proposes a string search model to construct the language model in ETR, which is used to perform character search based on the character prediction probability corresponding to each gesture output by the electromyography model, and obtain the converted text. The purpose is to correct the output results of the electromyography model.

[0109] Save the top m characters with the highest predicted probability for each gesture;

[0110] If no electromyographic signal is detected within a preset time, it is considered a space, and all characters between the spaces are taken as a prediction combination; in this embodiment, the preset time is set to 3 seconds.

[0111] Based on the order of predicted probabilities from largest to smallest, the first m predicted characters corresponding to the first gesture in the space-space string are taken as the root node. Based on the order of each gesture and the predicted probabilities of the first m predicted characters corresponding to each gesture, the predicted characters corresponding to each gesture are combined and used as child nodes. A search tree is built in sequence, and each branch of the search tree is a group of prediction combinations. The prediction combinations are matched in the corpus.

[0112] If a predicted combination exists in the corpus, it is identified as the final word recognition result, and the search tree construction is terminated; otherwise, the search tree continues to be built and the search continues until all possible combinations have been searched; if none of the obtained combinations appear in the corpus, the maximum predicted probability of each character is taken as the final prediction result of the string.

[0113] Specifically, the EAD (Electromyography) is first used to detect the resting period duration. If no electromyography signal is detected for more than 3 seconds, it is considered a space between words, and all characters before and after the space are taken as a single word. In this embodiment, if the word length is greater than 6, only the first 6 characters are extracted. Otherwise, all characters are retained.

[0114] Save the first 5 EM prediction results for each character corresponding to a dynamic electromyographic gesture.

[0115] An ordered string search tree is constructed. For each prediction result of the first character in the string, a search tree is constructed sequentially according to the order of prediction probability from largest to smallest, and the order in which the characters corresponding to each electromyographic gesture appear. A total of five search trees can be generated. One branch of each search tree is a set of predicted word combinations used for matching in a corpus. In this embodiment, the COCA corpus is used for word matching. In practical applications, different corpora can be used depending on the application domain to achieve more accurate search results.

[0116] Each branch of the string search tree is matched against words in the corpus in descending order of predicted probability. If a predicted combination exists in the corpus, it is determined as the final recognition result of the string, and the construction of the string search tree is terminated. Otherwise, the search tree continues to be built and searched until all possible combinations have been searched. If none of these combinations appear in the corpus, the maximum predicted probability of each character is taken as the final prediction result of the string. In this embodiment, words longer than 6 in the corpus are also truncated to match the output of the string search tree. If the string matches successfully and the word lengths are equal, the original word with the truncated word is taken as the recognition result.

[0117] Furthermore, the intelligent prosthetic limb system of this embodiment also includes an authentication function, implemented through an authentication unit. The authentication unit includes a pre-trained authentication model used to authenticate the user wearing the intelligent prosthetic limb before use; the training of the authentication model includes:

[0118] Obtain the electromyographic signals of authorized users’ password gestures and construct a training dataset of password gesture electromyographic signals. The training dataset includes N sets of password gesture electromyographic signals of authorized users and corresponding user labels.

[0119] The single-classification model is trained using the training data of each authorized user in the training dataset, and a threshold is set to obtain the identity model of each user.

[0120] The process of verifying the identity of users wearing smart prosthetics includes:

[0121] The electromyography (EMG) signals of a user wearing a smart prosthesis are acquired, preprocessed, and then the preprocessed EMG signals are subjected to active segment detection and feature extraction. The extracted feature data is then input into an identity verification model.

[0122] Retrieve the pre-established identity model of the authorized user to be matched, and determine whether the user to be verified is an authorized user or an unauthorized user based on a pre-set threshold.

[0123] Specifically, the first step is to collect electromyographic signals of the password gestures and then construct a training dataset.

[0124] Electrode pads are attached to the authorized user's arm to collect electromyographic (EMG) signals from the user's arm surface. This embodiment of the intelligent prosthetic system can be used not only for user authentication but also in conventional authentication scenarios, replacing fingerprint and facial recognition methods. This embodiment involves at least 20 users and sets at least 3 password gestures. Gestures can be open palms, complex static gestures, or dynamic gestures such as wrist rotation. Each signal acquisition requires collecting all password gestures for each user, with each gesture executed at least 10 times, collecting 10 sets of EMG signals. Each password gesture lasts approximately 3 seconds. All signals are used for subsequent identity modeling.

[0125] After acquiring the electromyographic signals, signal preprocessing is required. Specifically, the raw electromyographic signals can be filtered out by a Butterworth 4th order 30-500Hz bandpass filter to remove baseline drift and motion artifacts, and then filtered out by a 50Hz notch filter to remove power frequency interference.

[0126] Then, active segment detection is performed. Active segment detection is performed on each channel of the multi-channel surface electromyography signal. The signal is divided into frames through a 128ms window with a movement step of 64ms. The root mean square (RMS) of the signal in each window is calculated.

[0127] To further determine the threshold, statistical methods were used to sort the RMS values ​​of all frame signals to find a suitable RMS threshold. Signal segments below the threshold represent resting electromyographic signals. Then, a two-round segmentation was performed. In the first round, resting frames and active frames were labeled, with 0 representing resting frames and 1 representing active frames. In the second round, the length of consecutive active frames was determined. If the duration did not exceed 1 second, it was considered noise and classified as a resting frame; if the duration exceeded 1 second, it was considered an active segment and its active frame label was retained. This dual detection method ensures the accuracy of active segment detection.

[0128] Further feature extraction is performed by splicing consecutive activity frames into electromyographic activity segments corresponding to the complete hand gesture execution through activity segment detection. Each activity segment signal serves as the unit for feature extraction. This embodiment employs two types of feature extraction techniques: intra-channel features and inter-channel features. Intra-channel features calculate the characteristics of a single-channel signal, including three main categories: time-domain features, frequency-domain features, and autoregressive coefficients. Time-domain features typically include root mean square (RMS), waveform length, short-time zero-crossing rate, mean absolute value, and rate of change of slope sign. Frequency-domain features include mean amplitude spectrum, median frequency, and mean power frequency. Autoregressive coefficients are generally selected from 1st to 4th order autoregressive coefficients. Inter-channel features calculate the characteristics between pairs of channels. Inter-channel features include mutual information and Pearson correlation coefficients.

[0129] After extracting the electromyographic signal features, they can be used for model training. This embodiment uses the training data of each authorized user in the training dataset to train a single-classification model, obtaining an identity model for each user, including:

[0130] N sets of training data from authorized users are used as positive class training samples, and the positive class training sample data are mapped from the original space to the feature space through a nonlinear transformation function.

[0131] Using the support vector description algorithm, a minimum hypersphere is trained based on the training data of each authorized user mapped to the feature space. The data of all users are input into the identity verification model to obtain the distance of each user's data to the surface of the minimum hypersphere. A threshold is set based on the distance to obtain the corresponding user identity model.

[0132] Specifically, for identity verification, all users other than authorized users are considered imposters. Since it's impossible to collect data from all imposters when building the model, this embodiment uses a one-class classifier for modeling, as it only uses data from authorized users as positive class samples for training. Specifically, Support Vector Data Description (SVDD) can be used as the one-class classifier, also known as a One-class Support Vector Machine (OCSVM), which can distinguish between target and non-target samples. For a set of positive class training data (i.e., electromyography data from authorized users) x∈R... n×dWhere n is the number of samples and d is the feature dimension. First, the sample data is mapped from the original space to the feature space using a nonlinear transformation function Φ:x→F. Then, a hypersphere with the smallest possible volume is found in the feature space to contain as much feature data as possible within the smallest possible hypersphere. This means that the radius of the hypersphere needs to be constrained during its construction; furthermore, this hypersphere needs to have a certain degree of fault tolerance, allowing some outlier data to fall outside the hypersphere. To construct such a minimum hypersphere, the following constrained optimization problem is modeled using SVDD:

[0133]

[0134]

[0135] Where R is the radius of the hypersphere, a is the center of the sphere, ξ is the relaxation factor, C is the penalty parameter balancing the hypersphere and the error rate, and x i This represents the i-th feature data of the electromyography signal mapped to the feature space for a specific authorized user. In this embodiment, the Radial Basis Function (RBF) is selected as the nonlinear transformation function Φ:x→F for SVDD. SVDD trains each user's individual data into an identity model belonging to that user, used for identity verification during model deployment.

[0136] In the application of SVDD for authentication, through nonlinear mapping, if the image of a user's electromyography (EMG) signal sample point in the feature space falls within the optimal hypersphere, the sample is considered a normal point, i.e., an authorized user's sample; if it falls outside the optimal hypersphere, the sample is considered an outlier. The output of SVDD is the distance between the sample and the surface of the optimal hypersphere. Therefore, it is necessary to determine a decision threshold for the identity model for each user to determine whether the accessing user is an authorized or unauthorized user.

[0137] For each authorized user's SVDD identity model, the collected electromyography (EMG) data of other users is input, resulting in a set of distance-based outputs. The more similar the input EMG data is to the data used in modeling the authorized user's identity model, the smaller the absolute value of the output; conversely, the less similar the input EMG data is to the data used in modeling the authorized user's identity model, the larger the absolute value of the output. Based on multiple distance-based outputs, a threshold is set for the authorized user's identity model; when the absolute value of the output is less than this threshold, the user is determined to be an authorized user; otherwise, the user is considered an unauthorized user.

[0138] In practical applications, when any user accesses the system, they first select a pre-stored authorized user identity model corresponding to their access. Then, they wear electrode pads and perform a password gesture, each gesture lasting approximately 3 seconds. During this time, the electromyography (EMG) signal detection sensor continuously collects EMG signals and transmits them to the EMG signal recognition control module. This module first performs real-time filtering and framing of the signals, using the RMS threshold determined during identity modeling to detect active segments. Once a complete active segment is detected, its features are calculated, forming a feature vector, which is then fed into the SVDD identity model. The SVDD identity model outputs the distance between the feature vector of the current EMG sample and the selected pre-stored authorized user identity model. Based on the pre-determined identity model threshold, it determines the current user's identity type. If the distance between the current sample and the pre-stored authorized user identity model is less than the threshold, verification is successful, and the device is unlocked; otherwise, verification fails, and the user is asked to retry. If three consecutive verification failures are detected, the system automatically locks the device for a certain period, during which no user access is permitted.

[0139] The hardware architecture of the intelligent prosthetic system in this embodiment includes two subsystems, such as... Figure 4 The diagram shows the signal acquisition subsystem and the signal processing subsystem. The signal acquisition subsystem mainly consists of three modules: a signal acquisition module, a power management module, and a Bluetooth master control module. The power module is responsible for powering the entire system, powered by a 3.7V lithium battery, and then the voltage is converted to provide the required voltage to other modules of the system through a buck-boost circuit and a voltage regulator circuit. This invention uses the nRF52832 as the Bluetooth master control chip. The low-power, 24-bit analog front-end chip ADS1298 for physiological signal measurement is controlled via the SPI communication protocol to acquire 8-channel surface electromyography signals at the corresponding location. The signals are then preprocessed and packaged by the corresponding analog front-end, and then transmitted to the host computer via serial port (wired transmission) or Bluetooth (wireless transmission) through the nRF52832 processor. The host computer used in this invention is a Cortex-A72 (ARM v8) 64-bit SoC@1.5GHz Raspberry Pi 4B / 8GB platform. An authentication method is embedded in this platform to collect the signals of visiting users in real time and output the confirmation result, displaying whether access is allowed or denied.

[0140] In summary, the embodiments of this invention provide an intelligent prosthetic system for authentication and electromyography (EMG) text conversion. By acquiring and amplifying EMG signals from text characters, an EMG text conversion model combining an EMG model and a language model is constructed, achieving EMG-to-text sequence recognition. This invention can restore amputees' ability to input characters and, combined with gesture recognition, enable them to grasp everyday objects, maximizing the recovery of their self-care abilities. This invention enables the activation of wearable devices through EMG signals, allowing the devices to enter a low-power sleep mode when not in use, reducing power consumption and minimizing accidental gestures. This invention uses the SVDD model in an authentication method based on surface EMG signals. This model only needs to acquire signals from authorized users to distinguish all corresponding unauthorized users, making the method simple and efficient. It realizes a real-time portable authentication system based on surface EMG signals, providing a system solution that not only meets real-time requirements but also satisfies the security performance level of biometrics.

[0141] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware, and the program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0142] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. An intelligent prosthetic system for authentication and electromyographic text conversion, characterized in that, The intelligent prosthetic system includes an electromyography (EMG) signal detection sensor, an EMG signal recognition and control module, a motor drive device, and a bionic hand device, which are connected in sequence; wherein... The electromyography (EMG) signal detection sensor includes electrode pads for attaching to the surface of the residual limb wearing the smart prosthesis, for detecting EMG signals and sending them to the EMG signal recognition and control module; The electromyography (EMG) signal recognition and control module is used to recognize and process the received EMG signals, and to perform pattern conversion based on the EMG signal recognition results, thereby realizing identity verification, daily movement control, and EMG signal-to-text conversion. The EMG signal recognition and control module realizes the EMG signal-to-text conversion through an EMG-to-text conversion unit. The EMG-to-text conversion unit includes a pre-trained EMG model and a language model. The EMG model is trained through a pre-constructed EMG-to-text conversion dataset and is used to extract features and classify the EMG signals corresponding to each gesture, obtaining the predicted probability of each character corresponding to each gesture. The language model is used to perform character search based on the character prediction probability corresponding to each gesture output by the electromyography model, to obtain the converted text. This includes: saving the top m characters with the highest prediction probability for each gesture; if no electromyography signal is detected within a preset time, it is considered a space, and all characters between the spaces are taken as a prediction combination; according to the order of prediction probability from largest to smallest, using the top m predicted characters corresponding to the first gesture in the string between spaces as the root node, based on the order of each gesture and the prediction probability of the top m predicted characters corresponding to each gesture, the predicted characters corresponding to each gesture are combined and used as child nodes, and a search tree is built sequentially. Each branch of the search tree is a prediction combination, and the prediction combination is matched in the corpus; if a prediction combination exists in the corpus, it is identified as the final recognition result of the word, and the building of the search tree is terminated; otherwise, the search tree is built and the search continues until all possible combinations are searched; if none of the obtained combinations appear in the corpus, the maximum prediction probability of each character is taken as the final prediction result of the string. The motor drive device is used to control the bionic hand device to perform actions corresponding to electromyographic signals based on the recognition results of the electromyographic signal recognition and control module, thereby realizing daily movement control.

2. The intelligent prosthetic system for identity verification and electromyographic text conversion according to claim 1, characterized in that, The electromyography signal recognition and control module includes a mode switching unit, an identity verification unit, a daily control unit, and an electromyography text conversion unit; The mode switching unit is used to switch the working mode of the intelligent prosthetic system, including daily control mode and electromyography-text conversion mode. The authentication unit is used to identify whether the user to be authenticated is an authorized user in the authentication mode; The daily control unit is used to perform actions corresponding to electromyographic signals in the daily control mode; The electromyography-to-text conversion unit is used to convert electromyography signals into text in the electromyography-to-text conversion mode.

3. The intelligent prosthetic system for identity verification and electromyographic text conversion according to claim 1, characterized in that, The electromyography (EMG) model is based on a deep separable convolutional network, and the training of the EMG model includes: The electromyography (EMG) signal detection sensor is used to collect multiple dynamic gesture EMG signals from multiple users. The dynamic gesture EMG signals include the corresponding EMG signals obtained by controlling wrist movements to perform writing actions of multiple English letters and punctuation marks. The collected electromyographic signals were amplified to construct an electromyographic text conversion dataset; The electromyography (EMG) text conversion dataset is input into a depthwise separable convolutional network model, and the EMG model is obtained by iteratively updating the model through a loss function.

4. The intelligent prosthetic system for identity verification and electromyographic text conversion according to claim 3, characterized in that, Data augmentation can be performed using any of the following methods: The waveform is altered to amplify the data, including: multiplying the sampled value of the acquired electromyographic signal by a preset ratio to change the amplitude; interpolating and downsampling the acquired electromyographic signal to change the velocity, thus obtaining the amplified electromyographic signal; Data augmentation is performed by perturbing the detection results, including: after obtaining the complete electromyographic activity segment of the electromyographic signal through the electromyographic activity segment detection method, obtaining different activity segments of the electromyographic signal by moving the detection window left and right to obtain the amplified electromyographic signal; or by increasing the judgment threshold of the activity segment to reduce the length of the activity segment; or by decreasing the judgment threshold of the activity segment to increase the length of the activity segment to obtain the amplified electromyographic signal. Data augmentation is achieved by modifying the spectrum, including altering the spectrum of the electromyographic signal through time warping, frequency masking, and temporal masking to obtain an amplified electromyographic signal.

5. The intelligent prosthetic system for identity verification and electromyographic text conversion according to claim 2, characterized in that, The authentication unit includes a pre-trained authentication model for authenticating users wearing smart prostheses; the training of the authentication model includes: Obtain the electromyographic signals of authorized users’ password gestures and construct a training dataset of password gesture electromyographic signals. The training dataset includes N sets of password gesture electromyographic signals of authorized users and corresponding user labels. The single-classification model is trained using the training data of each authorized user in the training dataset, and a threshold is set to obtain the identity model of each user. The process of verifying the identity of users wearing smart prosthetics includes: The electromyography (EMG) signals of a user wearing a smart prosthesis are acquired, preprocessed, and then the preprocessed EMG signals are subjected to active segment detection and feature extraction. The extracted feature data is then input into an identity verification model. Retrieve the pre-established identity model of the authorized user to be matched, and determine whether the user to be verified is an authorized user or an unauthorized user based on a pre-set threshold.

6. The intelligent prosthetic system for identity verification and electromyographic text conversion according to claim 5, characterized in that, The step of training a single-classification model using training data from each authorized user in the training dataset to obtain an identity model for each user includes: N sets of training data from authorized users are used as positive class training samples, and the positive class training sample data are mapped from the original space to the feature space through a nonlinear transformation function. Using the support vector description algorithm, a minimum hypersphere is trained based on the training data of each authorized user mapped to the feature space. The data of all users are input into the identity verification model to obtain the distance of each user's data to the surface of the minimum hypersphere. A threshold is set based on the distance to obtain the corresponding user identity model.

7. The intelligent prosthetic system for identity verification and electromyographic text conversion according to claim 2, characterized in that, The daily control unit is trained using a pre-built daily control electromyography dataset to identify electromyography signals of daily control gestures, and controls the bionic hand device to complete the corresponding daily control actions through the motor drive device.

8. The intelligent prosthetic system for identity verification and electromyographic text conversion according to claim 2, characterized in that, The mode switching unit is trained on the conjoined network based on the activated gesture electromyography (EMG) signal dataset. It is used to perform EMG wake-up or mode switching on the intelligent prosthesis in low-power sleep mode upon detection of the activated gesture EMG signal, including: The user's electromyography (EMG) signals are collected in sleep mode, and the EMG signals are sequentially subjected to sliding window framing, preprocessing, active segment detection, and feature extraction. The features of each frame of electromyography (EMG) signal extracted are input into the mode switching unit to calculate the similarity with the pre-stored EMG features of activated gestures; based on a preset threshold, it is determined whether the acquired EMG signal is an activated frame. Accumulate 5 frames and perform a mode decision. If more than 3 of the 5 frames are identified as active frames, then the gesture is considered an active gesture; otherwise, it is considered an inactive gesture.

Images