Electromyography Pattern Recognition Research Articles

Application of a self-enhancing classification method to electromyography pattern recognition for multifunctional prosthesis control

BackgroundThe nonstationary property of electromyography (EMG) signals usually makes the pattern recognition (PR) based methods ineffective after some time in practical application for multinational prosthesis. The conventional EMG PR, which is accomplished in two separate steps: training and testing, ignores the mismatch between training and testing conditions and often discards the useful information in testing dataset.MethodThis paper presents a novel self-enhancing approach to improve the classification performance of the electromyography (EMG) pattern recognition (PR). The proposed self-enhancing method incorporates the knowledge beyond the training condition to the classifiers from the testing data. The widely-used linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) are extended to self-enhancing LDA (SELDA) and self-enhancing QDA (SEQDA) by continuously updating their model parameters such as the class mean vectors, the class covariances and the pooled covariance. Autoregressive (AR) and Fourier-derived cepstral (FC) features are adopted. Experimental data in two different protocols are used to evaluate performance of the proposed methods in short-term and long-term application respectively.ResultsIn protocol of short-term EMG, based on AR and FC, the recognition accuracy of SEQDA and SELDA is 2.2% and 1.6% higher than conventional that of QDA and LDA respectively. The mean results of SEQDA(C) and SEQDA (M) are improved by 2.2% and 0.75% for AR, and 1.99% and 1.1% for FC respectively when compared to QDA. The mean results of SELDA(C) and SELDA (M) are improved by 0.48% and 1.55% for AR, and 0.67% and 1.22% for FC when compared to LDA. In protocol of long-term EMG, the mean result of SEQDA is 3.15% better than that of QDA.ConclusionThe experimental results show that the self-enhancing classifiers significantly outperform the original versions using both AR and FC coefficient feature sets. The performance of SEQDA is superior to SELDA. In addition, preliminary study on long-term EMG data is conducted to verify the performance of SEQDA.

A feasibility study on the use of anthropometric variables to make muscle–computer interface more practical

High classification accuracy has been achieved for muscle–computer interfaces (MCIs) based on surface electromyography (EMG) recognition in many recent works with an increasing number of discriminated movements. However, there are many limitations to use these interfaces in the real-world contexts. One of the major problems is compatibility. Designing and training the classification EMG system for a particular individual user is needed in order to reach high accuracy. If the system can calibrate itself automatically/semi-automatically, the development of standard interfaces that are compatible with almost any user could be possible. Twelve anthropometric variables, a measurement of body dimensions, have been proposed and used to calibrate the system in two different ways: a weighting factor for a classifier and a normalizing value for EMG features. The experimental results showed that a number of relationships between anthropometric variables and EMG time-domain features from upper-limb muscles and movements are statistically strong (average r=0.71−0.80) and significant (p<0.05). In this paper, the feasibility to use anthropometric variables to calibrate the EMG classification system is shown obviously and the proposed calibration technique is suggested to further improve the robustness and practical use of MCIs based on EMG pattern recognition.

Discriminant Analysis for Human Arm Motion Prediction and Classifying

The EMG signal which is generated by the muscles activity diffuses to the skin surface of human body. This paper presents a pattern recognition system based on Linear Discriminant Analysis (LDA) algorithm for the classification of upper arm motions; where this algorithm was mainly used in face recognition and voice recognition. Also a comparison between the Linear Discriminant Analysis (LDA) and k-Nearest Neighbor (k-NN) algorithm is made for the classification of upper arm motions. The obtained results demonstrate superior performance of LDA to k-NN. The classification results give very accurate classification with very small classification errors. This paper is organized as follows: Muscle Anatomy, Data Classification Methods, Theory of Linear Discriminant Analysis, k-Nearest Neighbor (kNN) Algorithm, Modeling of EMG Pattern Recognition, EMG Data Generator, Electromyography Feature Extraction, Implemented System Results and Discussions, and finally, Conclusions. The proposed structure is simulated using MATLAB.

Toward attenuating the impact of arm positions on electromyography pattern-recognition based motion classification in transradial amputees

BackgroundElectromyography (EMG) pattern-recognition based control strategies for multifunctional myoelectric prosthesis systems have been studied commonly in a controlled laboratory setting. Before these myoelectric prosthesis systems are clinically viable, it will be necessary to assess the effect of some disparities between the ideal laboratory setting and practical use on the control performance. One important obstacle is the impact of arm position variation that causes the changes of EMG pattern when performing identical motions in different arm positions. This study aimed to investigate the impacts of arm position variation on EMG pattern-recognition based motion classification in upper-limb amputees and the solutions for reducing these impacts.MethodsWith five unilateral transradial (TR) amputees, the EMG signals and tri-axial accelerometer mechanomyography (ACC-MMG) signals were simultaneously collected from both amputated and intact arms when performing six classes of arm and hand movements in each of five arm positions that were considered in the study. The effect of the arm position changes was estimated in terms of motion classification error and compared between amputated and intact arms. Then the performance of three proposed methods in attenuating the impact of arm positions was evaluated.ResultsWith EMG signals, the average intra-position and inter-position classification errors across all five arm positions and five subjects were around 7.3% and 29.9% from amputated arms, respectively, about 1.0% and 10% low in comparison with those from intact arms. While ACC-MMG signals could yield a similar intra-position classification error (9.9%) as EMG, they had much higher inter-position classification error with an average value of 81.1% over the arm positions and the subjects. When the EMG data from all five arm positions were involved in the training set, the average classification error reached a value of around 10.8% for amputated arms. Using a two-stage cascade classifier, the average classification error was around 9.0% over all five arm positions. Reducing ACC-MMG channels from 8 to 2 only increased the average position classification error across all five arm positions from 0.7% to 1.0% in amputated arms.ConclusionsThe performance of EMG pattern-recognition based method in classifying movements strongly depends on arm positions. This dependency is a little stronger in intact arm than in amputated arm, which suggests that the investigations associated with practical use of a myoelectric prosthesis should use the limb amputees as subjects instead of using able-body subjects. The two-stage cascade classifier mode with ACC-MMG for limb position identification and EMG for limb motion classification may be a promising way to reduce the effect of limb position variation on classification performance.

CLASSIFICATION OF sEMG SIGNALS USING INTEGRATED NEURAL NETWORK WITH SMALL SIZED TRAINING DATA

The sEMG (Surface electromyography) signals detected from activated muscles can be used as a control source for prosthesis. So an efficient and accurate method for the classification of sEMG signal patterns has become a hot research in recent years. Artificial neural network is a popular used method in this field, however, most neural networks require large numbers of samples in the training stage to obtain the potential relationships between input feature vectors and the outputs.In this paper, Integrated back propagation neural network (IBPNN) is used to classify sEMG signals acquired during five different hand motions. The correct classification rates of IBPNN for the five hand movements are significantly higher than that of BPNN and Elman neural network. This reveals that IBPNN achieves the best performance with a small sized training data and can be used in control systems on prosthetic hands and other robotic devices based on electromyography pattern recognition.

The Effects of Weight and Inertia of the Prosthesis on the Sensitivity of Electromyographic Pattern Recognition in Relax State

The Effects of Weight and Inertia of the Prosthesis on the Sensitivity of Electromyographic Pattern Recognition in Relax State

Myoelectric hand prosthesis with novel adaptive grasping and self-locking

This paper presents a novel hand prosthesis controlled by electromyography (EMG) signals. Using an underactuated approach, the hand allows four fingers to flex independently with one actuator, plus the fingers and phalanges provide adaptation with respect to the shape of an object. An innovative self-lock is also embedded in the metacarpophalangeal joint to prevent back-driving when external forces act on the fingers. The thumb is designed to perform flexion/extension and abduction/adduction with one actuator, while the wrist is driven in a differential manner using two actuators. As a result, the hand has eighteen degrees of freedom with only four actuators. Furthermore, it is controlled in real-time by the previously proposed EMG pattern recognition method.13 Ten kinds of hand motions are classified from four channel EMG signals with a high accuracy and corresponding motion commands are generated for hand control. Experimental results demonstrate the effectiveness of the hand design and validity of the EMG-based hand control.

Pattern recognition control of multifunction myoelectric prostheses by patients with congenital transradial limb defects

Electromyography (EMG) pattern recognition offers the potential for improved control of multifunction myoelectric prostheses. However, it is unclear whether this technology can be successfully used by congenital amputees. The purpose of this investigation was to assess the ability of congenital transradial amputees to control a virtual multifunction prosthesis using EMG pattern recognition and compare their performance to that of acquired amputees from a previous study. Preliminary cross-sectional study. Four congenital transradial amputees trained and tested a linear discriminant analysis (LDA) classifier with four wrist movements, five hand movements, and a no-movement class. Subjects then tested the classifier in real time using a virtual arm. Performance metrics for the residual limb were poorer than those with the intact limb (classification accuracy: 52.1% ± 15.0% vs. 93.2% ± 15.8%; motion-completion rate: 49.0%± 23.0% vs. 84.0% ± 9.4%; motion-completion time: 2.05 ± 0.75 s vs. 1.13 ± 0.05 s, respectively). On average, performance with the residual limb by congenital amputees was reduced compared to that reported for acquired transradial amputees. However, one subject performed similarly to acquired amputees. Pattern recognition control may be a viable option for some congenital amputees. Further study is warranted to determine success factors.

Determining delay created by multifunctional prosthesis controllers

I am writing to express a concern that my colleagues from previous laboratories at Northwestern University/Rehabilitation Institute of Chicago (RIC) and I have shared for a number of years related to multifunctional prosthesis control. Previous investigations have used a variety of analysis window attributes for their multifunctional prosthesis controllers [1-8]. Researchers have varied the length of the analysis window, the amount of overlap between consecutive windows, and the number of majority votes used in the post-processing of the classifier decisions. However, believe that many researchers have made decisions about these attributes with little regard for the overall delay created in the real-time system. (Note that the term classifier typically refers to an element of the controller that uses the inputs provided to it, e.g., electromyographic [EMG] signals, force sensor data, and position sensor data to decide which joint(s) of the prosthesis should be actuated.) For example, Peleg et al. performed decisions on data up to 1.4 seconds after the onset of the contraction [9]. This classifier would require its user to wait on the order of seconds for Peleg et al.'s prosthesis to respond, which would likely be quite frustrating for the user. We are not suggesting that new algorithms should not be explored simply because they may create substantial delays. However, do believe that these delays should be considered and discussed in each article that is published on this topic. While a particular classifier may create a 1 percent increase in accuracy, if it cannot add this increase in in a reasonable amount of time, it may be a nonstarter. Continuing in this vein, would like to discuss some findings that believe will allow prosthesis controller designers to better understand how their controllers will behave in real time. (For the purpose of this editorial, further use of we and our indicates my colleagues and me.) This editorial focuses on analysis window issues from the perspective of EMG-based multifunctional prosthesis control. However, the work described can be extended to other forms of window-based biosignal classifiers, such as brain machine interfaces that use neural spike-counting algorithms for intracortical data [10-12] or those that use electroencephalogram recordings [13-14]. BACKGROUND AND VARIABLE DEFINITION Many readers may be familiar with multifunctional prosthesis classifiers, but I would like to provide a brief introduction for those who are new to the area. Many multifunctional prosthesis controllers analyze EMG signals collected from the residual limb in an attempt to determine the intended movement of the user. These controllers use EMG data to decide which degree of freedom will be actuated and then produce motor-drive signals for the corresponding joint of the prosthesis. Classifiers typically make these decisions by comparing data collected in real time to data collected during a training session. Generally, the movement of the prosthesis whose training data best match the current real-time data sample is then selected as the output of the classifier. These class decisions can then be used for determining the classification accuracy of a classifier, which is defined as the percentage of the time that the output of the controller matches the intended movement of the user. Huang et al. provide a detailed description of the various steps of the process [15]. Some previous work has shown that increases when EMG feature extraction and pattern recognition are performed on larger data windows [1]. However, when more EMG data are collected for analysis, more time is required to collect and then process the larger data set. This collection and processing time increases the delay between the user producing a command and the controller responding appropriately. If this delay becomes excessive, it can make the prosthesis feel sluggish and unresponsive to the user. …

Surface EMG pattern recognition for real-time control of a wrist exoskeleton

BackgroundSurface electromyography (sEMG) signals have been used in numerous studies for the classification of hand gestures and movements and successfully implemented in the position control of different prosthetic hands for amputees. sEMG could also potentially be used for controlling wearable devices which could assist persons with reduced muscle mass, such as those suffering from sarcopenia. While using sEMG for position control, estimation of the intended torque of the user could also provide sufficient information for an effective force control of the hand prosthesis or assistive device. This paper presents the use of pattern recognition to estimate the torque applied by a human wrist and its real-time implementation to control a novel two degree of freedom wrist exoskeleton prototype (WEP), which was specifically developed for this work.MethodsBoth sEMG data from four muscles of the forearm and wrist torque were collected from eight volunteers by using a custom-made testing rig. The features that were extracted from the sEMG signals included root mean square (rms) EMG amplitude, autoregressive (AR) model coefficients and waveform length. Support Vector Machines (SVM) was employed to extract classes of different force intensity from the sEMG signals. After assessing the off-line performance of the used classification technique, the WEP was used to validate in real-time the proposed classification scheme.ResultsThe data gathered from the volunteers were divided into two sets, one with nineteen classes and the second with thirteen classes. Each set of data was further divided into training and testing data. It was observed that the average testing accuracy in the case of nineteen classes was about 88% whereas the average accuracy in the case of thirteen classes reached about 96%. Classification and control algorithm implemented in the WEP was executed in less than 125 ms.ConclusionsThe results of this study showed that classification of EMG signals by separating different levels of torque is possible for wrist motion and the use of only four EMG channels is suitable. The study also showed that SVM classification technique is suitable for real-time classification of sEMG signals and can be effectively implemented for controlling an exoskeleton device for assisting the wrist.

Study of stability of time-domain features for electromyographic pattern recognition

BackgroundSignificant progress has been made towards the clinical application of human-machine interfaces (HMIs) based on electromyographic (EMG) pattern recognition for various rehabilitation purposes. Making this technology practical and available to patients with motor deficits requires overcoming real-world challenges, such as physical and physiological changes, that result in variations in EMG signals and systems that are unreliable for long-term use. In this study, we aimed to address these challenges by (1) investigating the stability of time-domain EMG features during changes in the EMG signals and (2) identifying the feature sets that would provide the most robust EMG pattern recognition.MethodsVariations in EMG signals were introduced during physical experiments. We identified three disturbances that commonly affect EMG signals: EMG electrode location shift, variation in muscle contraction effort, and muscle fatigue. The impact of these disturbances on individual features and combined feature sets was quantified by changes in classification performance. The robustness of feature sets was evaluated by a stability index developed in this study.ResultsMuscle fatigue had the smallest effect on the studied EMG features, while electrode location shift and varying effort level significantly reduced the classification accuracy for most of the features. Under these disturbances, the most stable EMG feature set with combination of four features produced at least 16.0% higher classification accuracy than the least stable set. EMG autoregression coefficients and cepstrum coefficients showed the most robust classification performance of all studied time-domain features.ConclusionsSelecting appropriate EMG feature combinations can overcome the impact of the studied disturbances on EMG pattern classification to a certain extent; however, this simple solution is still inadequate. Stabilizing electrode contact locations and developing effective classifier training strategies are suggested to further improve the robustness of HMIs based on EMG pattern recognition.

Using EMG for Real-time Prediction of Joint Angles to Control a Prosthetic Hand Equipped with a Sensory Feedback System

All commercially available upper limb prosthesis controllers only allow the hand to be commanded in an open and close fashion without any sensory feedback to the user. Here evaluation of a multi-degree of freedom hand controlled using a real-time EMG pattern recognition algorithm and incorporating a sensory feedback system is reported. The hand prosthesis, called SmartHand, was controlled in real-time by using 16 myoelectric signals from the residual limb of a 25-year old male transradial amputee in a two day long evaluation session, Initial training of the EMG pattern recognition algorithm was performed with a dataglove fitted to the contralateral hand recording joint angle positions of the fingers and mapping joint angles of the fingers to EMG data. In the following evaluation sessions, the myoelectric signals were classified using local approximation and lazy learning, producing finger joint angle outputs and consequently controlling the prosthetic hand. Sensory information recorded from force sensors in the artificial hand was relayed to actuators, integrated in the socket of the prosthesis. continuously delivering force sensory feedback stimulations to the stump of the amputee. The participant was able to perform several dextrous movements as well as functional grip tasks after only two hours of training and increased his controllability during the two day session, In the final evaluation session a mean

Genetic algorithm based optimization for EMG pattern recognition system

The paper presents the concept of genetic algorithm based optimization for the EMG pattern recognition system controlling the hand prosthesis. The recognition of EMG signals for determining the hand movements is made by a linear neural network discriminating between five predefined grasps. The input feature vector for the classification was established using AR model, and its coefficients became the features. The genetic algorithms are used to optimize the number of elements in the input feature vector and simultaneously maintain the recognition efficiency at the same level. Experimental results show a good efficiency in the optimization method maintaining the performance of the recognition system for the studied grasp movements’ repertoire.

A Strategy for Identifying Locomotion Modes Using Surface Electromyography

This study investigated the use of surface electromyography (EMG) combined with pattern recognition (PR) to identify user locomotion modes. Due to the nonstationary characteristics of leg EMG signals during locomotion, a new phase-dependent EMG PR strategy was proposed for classifying the user's locomotion modes. The variables of the system were studied for accurate classification and timely system response. The developed PR system was tested on EMG data collected from eight able-bodied subjects and two subjects with long transfemoral (TF) amputations while they were walking on different terrains or paths. The results showed reliable classification for the seven tested modes. For eight able-bodied subjects, the average classification errors in the four defined phases using ten electrodes located over the muscles above the knee (simulating EMG from the residual limb of a TF amputee) were 12.4% +/- 5.0%, 6.0% +/- 4.7%, 7.5% +/- 5.1%, and 5.2% +/- 3.7%, respectively. Comparable results were also observed in our pilot study on the subjects with TF amputations. The outcome of this investigation could promote the future design of neural-controlled artificial legs.

Mutual adaptation among man and machine by using f-MRI analysis

A prosthetic device for disabled people requires new and reliable robotics technology. This paper describes the interesting reaction of our brain to an adaptable prosthetic system. The adaptable prosthetic system is composed of an EMG signal controlled robot hand with an EMG pattern recognition learning function for Transradial (below elbow) prostheses. The mutual adaptation between the system and the human body is analyzed using functional magnetic resonance imaging (f-MRI) in order to clarify the plasticity of the motor and sensory cortex area according to the changes in the prosthetic system. The developed prosthetic hand has 13 DOF: three motors on the thumb, two motors for each finger, and two motors for the wrist. The tactile feedback is applied by using surface electrical stimulus. The f-MRI data shows the process of replacement from a phantom limb image to the prosthetic hand image.

An Analysis of EMG Electrode Configuration for Targeted Muscle Reinnervation Based Neural Machine Interface

Targeted muscle reinnervation (TMR) is a novel neural machine interface for improved myoelectric prosthesis control. Previous high-density (HD) surface electromyography (EMG) studies have indicated that tremendous neural control information can be extracted from the reinnervated muscles by EMG pattern recognition (PR). However, using a large number of EMG electrodes hinders clinical application of the TMR technique. This study investigated a reduced number of electrodes and the placement required to extract sufficient neural control information for accurate identification of user movement intents. An electrode selection algorithm was applied to the HD EMG recordings from each of four TMR amputee subjects. The results show that when using only 12 selected bipolar electrodes the average accuracy over subjects for classifying 16 movement intents was 93.0 (+/-3.3)%, just 1.2% lower than when using the entire HD electrode complement. The locations of selected electrodes were consistent with the anatomical reinnervation sites. Additionally, a practical protocol for clinical electrode placement was developed, which does not rely on complex HD EMG experiment and analysis while maintaining a classification accuracy of 88.7+/-4.5%. These outcomes provide important guidelines for practical electrode placement that can promote future clinical application of TMR and EMG PR in the control of multifunctional prostheses.

A Supervised Feature-Projection-Based Real-Time EMG Pattern Recognition for Multifunction Myoelectric Hand Control

Electromyographic (EMG) pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study was to develop an efficient feature- projection method for EMG pattern recognition. To this end, a linear supervised feature projection is proposed that utilizes a linear discriminant analysis (LDA). First, a wavelet packet transform (WPT) is performed to extract a feature vector from four-channel EMG signals. To dimensionally reduce and cluster the WPT features, an LDA, then, incorporates class information into the learning procedure, and identifies a linear matrix to maximize the class separability for the projected features. Finally, a multilayer perceptron classifies the LDA-reduced features into nine hand motions. To evaluate the performance of the LDA for WPT features, the LDA is compared with three other feature-projection methods. From a visualization and quantitative comparison, it is shown that the LDA produces a better performance for the class separability, plus the LDA-projected features improve the classification accuracy with a short processing time. A real-time pattern-recognition system is then implemented for a multifunction myoelectric hand. Experiments show that the proposed method achieves a 97.4% recognition accuracy, and all processes, including the generation of control commands for the myoelectric hand, are completed within 97 ms. Consequently, these results confirm that the proposed method is applicable to real-time EMG pattern recognition for multifunction myoelectric hand control.

Real-time intelligent pattern recognition algorithm for surface EMG signals

BackgroundElectromyography (EMG) is the study of muscle function through the inquiry of electrical signals that the muscles emanate. EMG signals collected from the surface of the skin (Surface Electromyogram: sEMG) can be used in different applications such as recognizing musculoskeletal neural based patterns intercepted for hand prosthesis movements. Current systems designed for controlling the prosthetic hands either have limited functions or can only be used to perform simple movements or use excessive amount of electrodes in order to achieve acceptable results. In an attempt to overcome these problems we have proposed an intelligent system to recognize hand movements and have provided a user assessment routine to evaluate the correctness of executed movements.MethodsWe propose to use an intelligent approach based on adaptive neuro-fuzzy inference system (ANFIS) integrated with a real-time learning scheme to identify hand motion commands. For this purpose and to consider the effect of user evaluation on recognizing hand movements, vision feedback is applied to increase the capability of our system. By using this scheme the user may assess the correctness of the performed hand movement. In this work a hybrid method for training fuzzy system, consisting of back-propagation (BP) and least mean square (LMS) is utilized. Also in order to optimize the number of fuzzy rules, a subtractive clustering algorithm has been developed. To design an effective system, we consider a conventional scheme of EMG pattern recognition system. To design this system we propose to use two different sets of EMG features, namely time domain (TD) and time-frequency representation (TFR). Also in order to decrease the undesirable effects of the dimension of these feature sets, principle component analysis (PCA) is utilized.ResultsIn this study, the myoelectric signals considered for classification consists of six unique hand movements. Features chosen for EMG signal are time and time-frequency domain. In this work we demonstrate the capability of an EMG pattern recognition system using ANFIS as classifier with a real-time learning method. Our results reveal that the utilized real-time ANFIS approach along with the user evaluation provides a 96.7% average accuracy. This rate is superior to the previously reported result utilizing artificial neural networks (ANN) real-time method [1].ConclusionThis study shows that ANFIS real-time learning method coupled with mixed time and time-frequency features as EMG features can provide acceptable results for designing sEMG pattern recognition system suitable for hand prosthesis control.

실시간 근전도 패턴인식을 위한 특징투영 기법에 관한 연구

EMG pattern recognition is essential for the control of a multifunction myoelectric hand. The main goal of this study is to develop an efficient feature projection method for EMC pattern recognition. To this end, we propose a linear supervised feature projection that utilizes linear discriminant analysis (LDA). We first perform wavelet packet transform (WPT) to extract the feature vector from four channel EMC signals. For dimensionality reduction and clustering of the WPT features, the LDA incorporates class information into the learning procedure, and finds a linear matrix to maximize the class separability for the projected features. Finally, the multilayer perceptron classifies the LDA-reduced features into nine hand motions. To evaluate the performance of LDA for the WPT features, we compare LDA with three other feature projection methods. From a visualization and quantitative comparison, we show that LDA has better performance for the class separability, and the LDA-projected features improve the classification accuracy with a short processing time. We implemented a real-time pattern recognition system for a multifunction myoelectric hand. In experiment, we show that the proposed method achieves 97.2% recognition accuracy, and that all processes, including the generation of control commands for myoelectric hand, are completed within 97 msec. These results confirm that our method is applicable to real-time EMG pattern recognition far myoelectric hand control.

EMG pattern recognition based on artificial intelligence techniques.

This paper presents an electromyographic (EMG) pattern recognition method to identify motion commands for the control of a prosthetic arm by evidence accumulation based on artificial intelligence with multiple parameters. The integral absolute value, variance, autoregressive (AR) model coefficients, linear cepstrum coefficients, and adaptive cepstrum vector are extracted as feature parameters from several time segments of EMG signals. Pattern recognition is carried out through the evidence accumulation procedure using the distances measured with reference parameters. A fuzzy mapping function is designed to transform the distances for the application of the evidence accumulation method. Results are presented to support the feasibility of the suggested approach for EMG pattern recognition.