Feature reduction and selection for EMG signal classification

Feature extraction is a significant method to extract the useful information which is hidden in surface electromyography (EMG) signal and to remove the unwanted part and interferences. To be successful in classification of the EMG signal, selection of a feature vector ought to be carefully considered. However, numerous studies of the EMG signal classification have used a feature set that have contained a number of redundant features. In this study, most complete and up-to-date thirty-seven time domain and frequency domain features have been proposed to be studied their properties. The results, which were verified by scatter plot of features, statistical analysis and classifier, indicated that most time domain features are superfluity and redundancy. They can be grouped according to mathematical property and information into four main types: energy and complexity, frequency, prediction model, and time-dependence. On the other hand, all frequency domain features are calculated based on statistical parameters of EMG power spectral density. Its performance in class separability viewpoint is not suitable for EMG recognition system. Recommendation of features to avoid the usage of redundant features for classifier in EMG signal classification applications is also proposed in this study.     

EMG pattern classification using SOFMs for hand signal recognition

 We propose a method of pattern classification of electromyographic (EMG) signals using a set of self- organizing feature maps (SOFMs). The proposed method is simple to apply in that the EMG signals are directly input to the SOFMs without preprocessing. Experimental results are presented that show the effectiveness of the SOFM based classifier for the recognition of the hand signal version of the Korean alphabet from EMG signal patterns.     

On pattern classification of EMG signals for walking motions

We present a method to calssify electromyogram (EMG) signals which are utilized as control signals for a patient-responsive walker-supported system for paraplegics. Patterns of EMG signals for different walking motions are classified via adequate filtering, real EMG signal extraction, AR-modeling, and a modified self-organizing feature map (MSOFM). In particular, a data-reducing extraction algorithm is employed for real EMG signals. Moreover, MSOFM classifies and determines the results automatically using a fixed map. Finally, the experimental results are presented for validation.