A COMPARATIVE-ANALYSIS OF VARIOUS EMG PATTERN-RECOGNITION METHODS

Identification of motions of the neck and shoulders using the electrom yographic (EMG) signal was investigated in this study. Three discrimin ation methods, the Euclidean distance measure (EDM), the weighted dist ance measure (WDM) and the modified maximum likelihood method (MMLM), were used to compare the conventional autoregressive (AR) and cepstral coefficients with closely positioned (C-type) and separately located (S-type) electrode arrangements. Surface electrodes were bilaterally l ocated on and between the sternocleidomastoid and the upper trapezius ius muscles. The EMG signals obtained during 20 repetitions of to moti ons were analysed for each subject. Results from nine subjects showed that the mean recognition rate of the cepstral coefficients was at lea st 5% better than that of the AR coefficients for the S-type signals, while the improvement was less obvious for the C-type signals. The MML M obtained the best discrimination results of the three discrimination methods. The S-type signals achieved higher recognition rates than th e C-type signals in most cases. Among the various combinations of feat ure sets, classifiers and electrode arrangements proposed in this stud y, tile combination of the cepstral coefficients and the MMLM with the S-type arrangement achieved the best discrimination efficiency. The p roper choice of five of 10 motions raised the recognition rate to more than 97%. Copyright (C) 1996 Elsevier Science Ltd for IPEMB.