Combined influence of forearm orientation and muscular contraction on EMG pattern recognition

• Published in: Expert systems with applications Vol. 61; pp. 154 - 161
• Main Authors: Khushaba, Rami N., Al-Timemy, Ali, Kodagoda, Sarath, Nazarpour, Kianoush
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.11.2016
• Subjects: Accelerometer; Classification; Dynamics; EMG; Forearm; Generalizability; Movements; Muscles; Orientation; Pattern recognition; Wrist; Accelerometer; Pattern recognition; Generalizability; EMG
• ISSN: 0957-4174; 1873-6793
• DOI: 10.1016/j.eswa.2016.05.031

•Multiple dynamic factors can significantly degrade the accuracy of EMG pattern recognition.•The impact of many of these factors has been studied in isolation.•We investigated the combined effect of forearm orientation and muscle contraction levels.•Twelve intact-limbed and one bilateral trans-radial amputee participated in the experiment.•Features that quantify the angular similarity can mitigate the problem. The performance of intelligent electromyogram (EMG)-driven prostheses, functioning as artificial alternatives to missing limbs, is influenced by several dynamic factors including: electrode position shift, varying muscle contraction level, forearm orientation, and limb position. The impact of these factors on EMG pattern recognition has been previously studied in isolation, with the combined effect of these factors being understudied. However, it is likely that a combination of these factors influences the accuracy. We investigated the combined effect of two dynamic factors, namely, forearm orientation and muscle contraction levels, on the generalizability of the EMG pattern recognition. A number of recent time- and frequency-domain EMG features were utilized to study the EMG classification accuracy. Twelve intact-limbed and one bilateral transradial (below-elbow) amputee subject were recruited. They performed six classes of wrist and hand movements at three muscular contraction levels with three forearm orientations (nine conditions). Results indicate that a classifier trained by features that quantify the angle, rather than amplitude, of the muscle activation patterns perform better than other feature sets across different contraction levels and forearm orientations. In addition, a classifier trained with the EMG signals collected at multiple forearm orientations with medium muscular contractions can generalize well and achieve classification accuracies of up to 91%. Furthermore, inclusion of an accelerometer to monitor wrist movement further improved the EMG classification accuracy. The results indicate that the proposed methodology has the potential to improve robustness of myoelectric pattern recognition.