The effect of attentional focusing strategies on EMG-based classification.

Earlier studies showed that external focusing enhances motor performance and reduces muscular activity compare to internal one. However, low activity is not always desired especially in case of Human-Machine Interface applications. This study is based on investigating the effects of attentional focusing preferences on EMG based control systems. For the EMG measurements via biceps brachii muscles, 35 subjects were asked to perform weight-lifting under control, external and internal focus conditions. The difference between external and internal focusing was found to be significant and internal focus enabled higher EMG activity. Besides, six statistical features, namely, RMS, maximum, minimum, mean, standard deviation, and variance were extracted from both time and frequency domains to be used as inputs for Artificial Neural Network classifiers. The results found to be 87.54% for ANN1 and 82.69% for ANN2, respectively. These findings showed that one's focus of attention would be predicted during the performance and unlike the literature, internal focusing could be also useful when it is used as an input for HMI studies. Therefore, attentional focusing might be an important strategy not only for performance improvement to human movement but also for advancing the study of EMG-based control mechanisms.