Multivariate AR modeling of electromyography for the classification of upper arm movements

Design of Digital-Twin Human-Machine Interface Sensor with Intelligent Finger Gesture Recognition

In this study, the design of a Digital-twin human-machine interface sensor (DT-HMIS) is proposed. This is a digital-twin sensor (DT-Sensor) that can meet the demands of human-machine automation collaboration in Industry 5.0. The DT-HMIS allows users/patients to add, modify, delete, query, and restore their previously memorized DT finger gesture mapping model and programmable logic controller (PLC) logic program, enabling the operation or access of the programmable controller input-output (I/O) interface and achieving the extended limb collaboration capability of users/patients. The system has two main functions: the first is gesture-encoded virtual manipulation, which indirectly accesses the PLC through the DT mapping model to complete control of electronic peripherals for extension-limbs ability by executing logic control program instructions. The second is gesture-based virtual manipulation to help non-verbal individuals create special verbal sentences through gesture commands to improve their expression ability. The design method uses primitive image processing and eight-way dual-bit signal processing algorithms to capture the movement of human finger gestures and convert them into digital signals. The system service maps control instructions by observing the digital signals of the DT-HMIS and drives motion control through mechatronics integration or speech synthesis feedback to express the operation requirements of inconvenient work or complex handheld physical tools. Based on the human-machine interface sensor of DT computer vision, it can reflect the user's command status without the need for additional wearable devices and promote interaction with the virtual world. When used for patients, the system ensures that the user's virtual control is mapped to physical device control, providing the convenience of independent operation while reducing caregiver fatigue. This study shows that the recognition accuracy can reach 99%, demonstrating practicality and application prospects. In future applications, users/patients can interact virtually with other peripheral devices through the DT-HMIS to meet their own interaction needs and promote industry progress.

Development of Sign Language Motion Recognition System for Hearing-Impaired People Using Electromyography Signal

Sign languages are developed around the world for hearing-impaired people to communicate with others who understand them. Different grammar and alphabets limit the usage of sign languages between different sign language users. Furthermore, training is required for hearing-intact people to communicate with them. Therefore, in this paper, a real-time motion recognition system based on an electromyography signal is proposed for recognizing actual American Sign Language (ASL) hand motions for helping hearing-impaired people communicate with others and training normal people to understand the sign languages. A bilinear model is applied to deal with the on electromyography (EMG) data for decreasing the individual difference among different people. A long short-term memory neural network is used in this paper as the classifier. Twenty sign language motions in the ASL library are selected for recognition in order to increase the practicability of the system. The results indicate that this system can recognize these twenty motions with high accuracy among twenty participants. Therefore, this system has the potential to be widely applied to help hearing-impaired people for daily communication and normal people to understand the sign languages.

The analysis of hand movement distinction based on relative frequency band energy method

For the purpose of successfully developing a prosthetic control system, many attempts have been made to improve the classification accuracy of surface electromyographic (SEMG) signals. Nevertheless, the effective feature extraction is still a paramount challenge for the classification of SEMG signals. The relative frequency band energy (RFBE) method based on wavelet packet decomposition was proposed for the prosthetic pattern recognition of multichannel SEMG signals. Firstly, the wavelet packet energy of SEMG signals in each subspace was calculated by using wavelet packet decomposition and the RFBE of each frequency band was obtained by the wavelet packet energy. Then, the principal component analysis (PCA) and the Davies-Bouldin (DB) index were used to perform the feature selection. Lastly, the support vector machine (SVM) was applied for the classification of SEMG signals. Our results demonstrated that the RFBE approach was suitable for identifying different types of forearm movements. By comparing with other classification methods, the proposed method achieved higher classification accuracy in terms of the classification of SEMG signals.

The role of muscle synergies in myoelectric control: trends and challenges for simultaneous multifunction control

Myoelectric control is filled with potential to significantly change human-robot interaction due to the ability to non-invasively measure human motion intent. However, current control schemes have struggled to achieve the robust performance that is necessary for use in commercial applications. As demands in myoelectric control trend toward simultaneous multifunctional control, multi-muscle coordinations, or synergies, play larger roles in the success of the control scheme. Detecting and refining patterns in muscle activations robust to the high variance and transient changes associated with surface electromyography is essential for efficient, user-friendly control. This article reviews the role of muscle synergies in myoelectric control schemes by dissecting each component of the scheme with respect to associated challenges for achieving robust simultaneous control of myoelectric interfaces. Electromyography recording details, signal feature extraction, pattern recognition and motor learning based control schemes are considered, and future directions are proposed as steps toward fulfilling the potential of myoelectric control in clinically and commercially viable applications.

The analysis of surface EMG signals with the wavelet-based correlation dimension method

Many attempts have been made to effectively improve a prosthetic system controlled by the classification of surface electromyographic (SEMG) signals. Recently, the development of methodologies to extract the effective features still remains a primary challenge. Previous studies have demonstrated that the SEMG signals have nonlinear characteristics. In this study, by combining the nonlinear time series analysis and the time-frequency domain methods, we proposed the wavelet-based correlation dimension method to extract the effective features of SEMG signals. The SEMG signals were firstly analyzed by the wavelet transform and the correlation dimension was calculated to obtain the features of the SEMG signals. Then, these features were used as the input vectors of a Gustafson-Kessel clustering classifier to discriminate four types of forearm movements. Our results showed that there are four separate clusters corresponding to different forearm movements at the third resolution level and the resulting classification accuracy was 100%, when two channels of SEMG signals were used. This indicates that the proposed approach can provide important insight into the nonlinear characteristics and the time-frequency domain features of SEMG signals and is suitable for classifying different types of forearm movements. By comparing with other existing methods, the proposed method exhibited more robustness and higher classification accuracy.

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

BACKGROUND

The 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.

METHOD

This 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.

RESULTS

In 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.

CONCLUSION

The 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.

Classification of surface electromyographic signals by means of multifractal singularity spectrum

In order to effectively control a prosthetic system, considerable attempts have been made in recent years to improve the classification accuracy of surface electromyographic (SEMG) signals. However, the extraction of effective features is still a primary challenge for the classification of SEMG signals. This study tried to solve the problem by applying the multifractal analysis. It was found that the SEMG signals were characterized by multifractality during forearm movements and different types of forearm movements were related to different multifractal singularity spectra. To quantitatively evaluate the multifractal singularity spectra of the SEMG signals, the areas of the singularity spectrum curves were calculated by integrating the spectrum curves with respect to the singularity strengths. Our results showed that there were several separate clusters resulting from singularity spectrum areas of different forearm movements when two channels of SEMG signals were used in this experimental research, which demonstrated that the multifractal analysis approach was suitable for identifying different types of forearm movements. By comparing with other feature extraction techniques, the multifractal singularity spectrum approach provided higher classification accuracy in terms of the classification of SEMG signals.

Preliminary results of online classification of upper limb motions from around-shoulder muscle activities

Recently, detecting upper-limb motion intention for prosthetic control purpose attracted growing research attention. In most of the studies, recordings of forearm muscle activities were used as the signal sources, from which the intention of wrist and hand motions were detected using pattern recognition technology. However, most daily-life upper limb activities need coordination of the shoulder-arm-hand complex. The disadvantage of relying only on the local information to recognize a whole body coordinated motion is that misrecognition could easily happen, so that steady and reliable continuous motions could not be realized. Moreover, using forearm muscle activities would limit the use of the system for higher level amputation patients. Therefore, in this study we aimed to explore the feasibility of using an online classification algorithm to test the intention detection in real time. Experiments were conducted to record around-shoulder muscle activity using EMG and acceleration sensors. Then, a neural network was trained using these data, and finally tested online in a set of tests. Results showed that, from 5 channels of Electromyogram (EMG) and 4 channels of accelerometers, it is possible to discriminate 3 different grips and 5 reaching direction of arm.

Noninvasive intracranial pressure assessment based on a data-mining approach using a nonlinear mapping function

The current gold standard to determine intracranial pressure (ICP) involves an invasive procedure for direct access to the intracranial compartment. The risks associated with this invasive procedure include intracerebral hemorrhage, infection, and discomfort. We previously proposed an innovative data-mining framework of noninvasive ICP (NICP) assessment. The performance of the proposed framework relies on designing a good mapping function. We attempt to achieve performance gain by adopting various linear and nonlinear mapping functions. Our results demonstrate that a nonlinear mapping function based on the kernel spectral regression technique significantly improves the performance of the proposed data-mining framework for NICP assessment in comparison to other linear mapping functions.

Classification of upper limb motions from around-shoulder muscle activities: hand biofeedback

Mining information from EMG signals to detect complex motion intention has attracted growing research attention, especially for upper-limb prosthetic hand applications. In most of the studies, recordings of forearm muscle activities were used as the signal sources, from which the intention of wrist and hand motions were detected using pattern recognition technology. However, most daily-life upper limb activities need coordination of the shoulder-arm-hand complex, therefore, relying only on the local information to recognize the body coordinated motion has many disadvantages because natural continuous arm-hand motions can’t be realized. Also, achieving a dynamical coupling between the user and the prosthesis will not be possible. This study objective was to investigate whether it is possible to associate the around-shoulder muscles’ Electromyogram (EMG) activities with the different hand grips and arm directions movements. Experiments were conducted to record the EMG of different arm and hand motions and the data were analyzed to decide the contribution of each sensor, in order to distinguish the arm-hand motions as a function of the reaching time. Results showed that it is possible to differentiate hand grips and arm position while doing a reaching and grasping task. Also, these results are of great importance as one step to achieve a close loop dynamical coupling between the user and the prosthesis.

Feasibility of building robust surface electromyography-based hand gesture interfaces

This study explored the feasibility of building robust surface electromyography (EMG)-based gesture interfaces starting from the definition of input command gestures. As a first step, an offline experimental scheme was carried out for extracting user-independent input command sets with high class separability, reliability and low individual variations from 23 classes of hand gestures. Then three types (same-user, multi-user and cross-user test) of online experiments were conducted to demonstrate the feasibility of building robust surface EMG-based interfaces with the hand gesture sets recommended by the offline experiments. The research results reported in this paper are useful for the development and popularization of surface EMG-based gesture interaction technology.

Application of least square method for muscular strength estimation in hand motion recognition using surface EMG

In this study, we describe the application of least square method for muscular strength estimation in hand motion recognition based on surface electromyogram (SEMG). Although the muscular strength can consider the various evaluation methods, a grasp force is applied as an index to evaluate the muscular strength. Today, SEMG, which is measured from skin surface, is widely used as a control signal for many devices. Because, SEMG is one of the most important biological signal in which the human motion intention is directly reflected. And various devices using SEMG are reported by lots of researchers. Those devices which use SEMG as a control signal, we call them SEMG system. In SEMG system, to achieve high accuracy recognition is an important requirement. Conventionally SEMG system mainly focused on how to achieve this objective. Although it is also important to estimate muscular strength of motions, most of them cannot detect power of muscle. The ability to estimate muscular strength is a very important factor to control the SEMG systems. Thus, our objective of this study is to develop the estimation method for muscular strength by application of least square method, and reflecting the result of measured power to the controlled object. Since it was known that SEMG is formed by physiological variations in the state of muscle fiber membranes, it is thought that it can be related with grasp force. We applied to the least-squares method to construct a relationship between SEMG and grasp force. In order to construct an effective evaluation model, four SEMG measurement locations in consideration of individual difference were decided by the Monte Carlo method.

Use of the discriminant Fourier-derived cepstrum with feature-level post-processing for surface electromyographic signal classification

Myoelectrical pattern classification is a crucial part in multi-functional prosthesis control. This paper investigates a discriminant Fourier-derived cepstrum (DFC) and feature-level post-processing (FLPP) to discriminate hand and wrist motions using the surface electromyographic signal. The Fourier-derived cepstrum takes advantage of the Fourier magnitude or sub-band power energy of signals directly and provides flexible use of spectral information changing with different motions. Appropriate cepstral coefficients are selected by a proposed separability criterion to construct DFC features. For the post-processing, FLPP which combines features from several analysis windows is used to improve the feature performance further. In this work, two classifiers (a linear discriminant classifier and quadratic discriminant classifier) without hyper-parameter optimization are employed to simplify the training procedure and avoid the possible bias of feature evaluation. Experimental results of the 11-motion problem show that the proposed DFC feature outperforms traditional features such as time-domain statistics and autoregressive-derived cepstrum in terms of the classification accuracy, and it is a promising method for the multi-functionality and high-accuracy control of myoelectric prostheses.

A comparison of the effects of electrode implantation and targeting on pattern classification accuracy for prosthesis control

The use of surface versus intramuscular electrodes as well as the effect of electrode targeting on pattern-recognition-based multifunctional prosthesis control was explored. Surface electrodes are touted for their ability to record activity from relatively large portions of muscle tissue. Intramuscular electromyograms (EMGs) can provide focal recordings from deep muscles of the forearm and independent signals relatively free of crosstalk. However, little work has been done to compare the two. Additionally, while previous investigations have either targeted electrodes to specific muscles or used untargeted (symmetric) electrode arrays, no work has compared these approaches to determine if one is superior. The classification accuracies of pattern-recognition-based classifiers utilizing surface and intramuscular as well as targeted and untargeted electrodes were compared across 11 subjects. A repeated-measures analysis of variance revealed that when only EMG amplitude information was used from all available EMG channels, the targeted surface, targeted intramuscular, and untargeted surface electrodes produced similar classification accuracies while the untargeted intramuscular electrodes produced significantly lower accuracies. However, no statistical differences were observed between any of the electrode conditions when additional features were extracted from the EMG signal. It was concluded that the choice of electrode should be driven by clinical factors, such as signal robustness/stability, cost, etc., instead of by classification accuracy.

Hidden Markov multivariate autoregressive (HMM-mAR) modeling framework for surface electromyography (sEMG) data

Surface electromyographic (sEMG) analysis is complicated by the fact that the data are inherently non-stationary. To deal with this and to determine muscle activity patterns during reaching movements, we proposed modeling sEMG with a hidden Markov model-multivariate autoregressive (HMM-mAR) framework. The classification between healthy and stroke subjects was performed using structural features extracted from HMM-mAR models. Both the raw and carrier data produced excellent classification performance. The proposed method represents a fundamental departure from most existing methods where only the amplitude is analyzed or the mAR coefficients are directly used for classification. In contrast, our analysis shows that structural features of the multivariate sEMG carrier data or the residuals after model fitting can enhance the classification of reaching movements.

Development of the hand motion recognition system based on surface EMG using suitable measurement channels for pattern recognition

Conventional research on motion recognition using surface electromyogram (SEMG) is mainly focused on how to process with the signals for pattern recognition. However, it is of much consequence to the motion recognition that measurement channels position including useful information about SEMG pattern recognition is selected. In this paper, we present two topics for the hand motion recognition system based on SEMG. First described is the method to select the suitable measurement channels position of multichannel SEMG for the recognition of hand motion, and the second described is an applied systems based on our proposed method. About channel selection, we use a multichannel matrix-type surface electrode attached to the forearm in order to measure the SEMG generated from many active muscles during hand motions. From those electrodes, system decided the number of measurement channels and the position of measurement channels. This can be achieved by using the Monte Carlo method. The recognition experiments of 18 hand motions show that the average rate was measured to be greater than 96%. And the number of selected channels ranged from 4 to 7. About applied systems, our developed system works as an input interface for the computer (keyboard and pointing device) and a robot hand.

Development of the human interface equipment based on surface EMG employing channel selection method

In this paper, we describe the human-interface equipment using surface electromyogram (SEMG) based on optimal measurement channels for each subject. In case the SEMG is used as a control signal, individual differences of SEMG are important issue to obtain high accuracy recognition of motions. To solve this problem, we propose a channel selection method of the suitable measurement channels for the recognition of motions. We use a 96-channel matrix-type (6 x 16) surface electrode attached to the forearm in order to measure the SEMG generated from many active muscles during hand motions. From those 96 electrodes, our system decided the number of measurement channels and the position of measurement channels. This can be achieved by using the Monte Carlo method. Our system generates 10,000 sets of randomly selected channels, and these sets are evaluated by the recognition rate of hand motions. One set that records a highest recognition rate is selected from 10,000 sets for an optimal set of measurement channels. And the one set with the smallest number of measurement channels which fulfil the recognition rate above 90% or the maximum recognition rate above 95% is used for real-time recognition. Six normal subjects were experimentally tested using our system. The recognition rates of 18 hand motions, including 10 finger movements, were assessed for every subject. We were able to distinguish all the motions, and the average recognition rate in the real-time experiment was measured to be greater than 95%. And the number of selected channels ranged from 4 to 7.

Vision-based segmentation of continuous mechanomyographic grasping sequences

In detecting motor related activity from mechanomyographic (MMG) recordings, the acquisition of long, continuous streams of MMG signals is typically preferred over the painstaking collection of individual, isolated contractions. However, a major challenge with continuous collection is the subsequent separation of the MMG data stream into segments representing individual contractions. This paper proposes a method for segmenting continuously recorded MMG data streams using computer vision while providing a highly reduced set of key images for rapid human expert verification. Transverse plane video recordings of functional grasp sequences were synchronized with the acquisition of MMG signals from the forearm. An automatic, vision-based algorithm exploiting skin color detection, motion estimation, and template matching provided segmentation cues for MMG signals arising from multiple grips. The automatic segmentation method tolerated extraneous hand movements, differentiated among multiple grips and estimated grip transition times. Our implementation segmented two grips with an average accuracy of 97.8 -/+ 4%, and up to seven grips with an accuracy of 73 -/+ 20%. The automatically extracted contraction initiation and termination times were within 173 -/+ 133 ms of the times obtained via manual segmentation. It is suggested that the proposed method would be particularly conducive to the assembly of large collections of signals for training MMG-driven prostheses.

A Method of Recognizing Finger Motion Using Wavelet Transform of Surface EMG Signal

In this paper, an identification method of finger motions using the wavelet transform of multi-channel electromyography (EMG) signal is presented. The first step of this method is to analyze surface EMG signal detected from the subject's upper arm using the multi-resolution of wavelet transform, and extract features using the variance, maximum and mean absolute value of the wavelet coefficients. In this way, a new feature space is established by wavelet coefficients. The second step is to import the feature values into an Artificial Neural Network (ANN) to identify the finger motion. Based on the results of experiments, it is concluded that this method is effective in identification of finger motion. Thus, it provides an alternative approach to use the surface EMG in controlling the finger motion of a multi-fingered prosthetic hand.

Signal-dependent wavelets for electromyogram classification

In the study, an efficient method to perform supervised classification of surface electromyogram (EMG) signals is proposed. The method is based on the choice of a relevant representation space and its optimisation with respect to a training set. As EMG signals are the summation of compact-support waveforms (the motor unit action potentials), a natural tool for their representation is the discrete dyadic wavelet transform. The feature space was thus built from the marginals of a discrete wavelet decomposition. The mother wavelet was designed to minimise the probability of classification error estimated on the learning set (supervised classification). As a representative example, the method was applied to simulate surface EMG signals generated by motor units with different degrees of short-term synchronisation. The proposed approach was able to distinguish surface EMG signals with degrees of synchronisation that differed by 10%, with a misclassification rate of 8%. The performance of a spectral-based classification (error rate approximately 33%) and of the classification with Daubechies wavelet (21%) was significantly poorer than with the proposed wavelet optimisation. The method can be used for a number of different application fields of surface EMG classification, as the feature space is adapted to the characteristics of the signal that discriminate between classes.

Quantitative multichannel EEG measure predicting the optimal weaning from ventilator in ICU patients with acute respiratory failure

OBJECTIVE

The objective of this study was to develop a novel quantitative multichannel EEG (qEEG) based analysis method, called Global Field Damping Time (GFDT), in order to detect potential EEG changes of patients admitted to the ICU with acute respiratory failure, and correlate them to the patients' recovery outcome predicting the optimal time-point to disconnect the patient from mechanical ventilation.

METHODS

Twenty-nine adult patients with acute respiratory failure out of 98 admitted to the Intensive Care Unit of Saint Paul General Hospital were enrolled, and among them only 15 completed the study. The patients were classified in 3 groups according to their outcome after 3 months follow-up. The patients were intubated with fraction of inspired oxygen (FiO2) of 100%. Neurological Deficit Scores (NDS) were measured 24 h after intubation to assess patients' neurological condition. Twenty-four hours after patient's intubation, FiO2 was decreased to 40% (weaning session), followed by a 5 min early recovery session, a 5 min recovery 1 session and a 5 min recovery 2 session. EEG recordings were performed during this experimental procedure. Multichannel EEG segments were processed and fitted into a multivariate autoregressive (mAR) model, and single channel EEG segments into a scalar autoregressive (sAR) model. The mAR and the sAR models of arbitrary order p were decomposed into mp and p oscillators and relaxators, respectively. Damping time of each oscillator and each relaxator, and the Global Field Damping Time (GFDT) as a weighted damping time were estimated for both mAR and sAR models.

RESULTS

A statistically significant increase of mAR model's GFDT during the weaning session was observed in the subjects of all groups. Comparing the 3 patients' groups, statistically significant differences for mAR model's GFDT were observed for the weaning and early recovery session. Linear regression analysis between NDS and mean mAR model's GFDT showed statistical significance during weaning session, early recovery session, and recovery 1 session. There was no statistical significance for SaO2 in the regression analysis with NDS. The sAR model's GFDT presented worst results in comparison with the mAR modelling GFDT in the identification of hypoxic conditions during weaning session and in the discrimination of patients with acute respiratory failure according to their neurological outcome.

CONCLUSIONS

Global Field Damping Time as correlated to the patients' neurological outcome appears to be a simple, compact, and substantial novel indicator of cerebral hypoxia and a potential predictor of the optimal time-point to disconnect the patient from the ventilator.

SIGNIFICANCE

Quantitative EEG seems to be an important tool for ICU clinicians assisting them to decide for the patients' optimal time-point to disconnect the patient from the ventilator.

A single-lead ECG enhancement algorithm using a regularized data-driven filter

We presented a novel way of deriving a subspace filter for enhancing a noisy electrocardiogram (ECG) signal contaminated by electromyogram (EMG). The new subspace filter was based on a multiple cycle prediction (MCP) modeling of a single-lead ECG. The adoption of an MCP model resulted in a data matrix more suitable for separating noise and signal subspaces than the linear prediction (LP) model that is implicitly assumed in many existing subspace filters. Alignment of ECG cycles of different length is required for MCP modeling and was handled by a dynamic time warping (DTW) algorithm. A run-time procedure was designed for automatically determining the signal space dimension adaptively. To validate the new filter in a quantitative way, 12 clean realistic ECG segments with different degrees of heart rate variability generated using the ECGSyn program were mixed with different realizations of EMG noise in the MIT-BIH Noise Stress Test Database and locally acquired EMG at a typical 10-dB signal-to-noise ratio. The performance of the proposed method was compared to three existing ECG enhancement algorithms and achieved encouraging results. In addition, various ECG recordings from MIT-Arrythmia database were also mixed with EMG noise and subjected to the same four filters resulting in a qualitative comparison of them.

A Classification Method of Hand Movements Using Multi Channel Electrode

In this study, we describe the classification method of hand movements using 96 channels matrix-type(16times6) of multi channel surface electrode. Today, there are many systems that use the EMG as a control signal. As for those ordinary systems, it has some problem like most of them require the definition of measuring position. We design the new system with multi channel electrode to solve some of those conventional problems. Our system that has 96 channels electrode does not need to select a particular electrode position. Only attaching this electrode, we can obtain correct EMG and this way means providing with a simple and easy way. The purpose of this study is development of the EMG pattern recognition method using multi channel electrode. From measured 96 channels EMG data, we chose one line (16channels) of this electrode with the smallest noise. The EMG signal is recognized by canonical discriminant analysis. In order to recognize the EMG signal, the first three eigenvectors are chosen to form a discriminant space. And Euclidean distance is applied to classify the EMG. From the experiment in this method, we can discriminate 12 movements of the hand including four finger movements. And the recognition rate that can be done in real-time was measured at 80 percent on the average.