Evaluating different combinations of feature selection algorithms and cost functions applied to iPCA tuning in myoelectric control systems.

A myoelectric control system extracts information from electromyographic (EMG) signals and uses it to control different types of prostheses, so that people who suffered traumatisms, paralysis or amputations can use them to execute common movements. Recent research shows that the addition of a tuning stage, using the individual component analysis (iPCA), results in improved classification performance. We propose and evaluate a set of novel configurations for the iPCA tuning, based on a biologically inspired optimization procedure, the artificial bee colony algorithm. This procedure is implemented and tested using two different cost functions, the traditional classification error and the proposed correlation factor, which involves lower computational effort. We compare the tuned system's performance, in terms of correct classifications, to that of a system tuned using two standard algorithms, the sequential forward selection and the sequential floating forward selection. The statistical analyses of the results don't find a significant difference among the classification performances associated with the search algorithms (p < 0.01). On the other hand, they establish a significant difference among the classification performances related to the cost functions (p < 0.02).

Compression of EMG signals with wavelet transform and artificial neural networks.

This paper presents a hybrid adaptive algorithm for the compression of surface electromyographic (S-EMG) signals recorded during isometric and/or isotonic contractions. This technique is useful for minimizing data storage and transmission requirements for applications where multiple channels with high bandwidth data are digitized, such as telemedicine applications. The compression algorithm proposed in this work uses a discrete wavelet transform for spectral decomposition and an intelligent dynamic bit allocation scheme implemented by an approach using the Kohonen layer, which improves the bit allocation for sections of the S-EMG with different characteristics. Finally, data and overhead information are packed by entropy coding. The results for the compression of isometric EMG signals showed that this algorithm has a better performance than standard wavelet compression algorithms presented in the literature (presenting a decrease of at least 5% in per cent residual difference (PRD) for the same compression ratio), and a performance that is comparable with the performance of algorithms based on an embedded zero-tree wavelet. For isotonic EMG signals, its performance is better than the performance of the algorithms based on embedded zero-tree wavelets (presenting a decrease in PRD of about 3.6% for the same compression ratios, in the useful compression range).