Neuromuscular basis of finger coordination

Abstract

Fingertip force coordination is crucial to the success of grasp-and-lift tasks. In the development of motor prosthesis for daily applications, the ability to accurately predict the desired grasp-and-lift from multi-channel surface electromyography (sEMG) is essential. In order to extract accurate indicators for fingertip force coordination, we searched an extensive set of sEMG features for the optimal subset of relevant features. Using mutual information based feature selection we found that a subset of not more than 10 sEMG features selected from over seven thousand, could effectively classify object weights in grasp-and-lift tasks. Average classification accuracies of 82.53% in the acceleration phase and 88.61% in the isometric contraction phase were achieved. Besides, sEMG features associated with object weights and common across individuals were identified. These time-domain features (entropy, meanmedian absolute deviation, pNNx) can be calculated efficiently, providing possible new indicators in sEMG classification. Furthermore, in real-time fingertip force prediction, with a simple linear model trained only by 60 seconds, an average correlation coefficient of 0.87 was achieved in predicting grip force and 0.84 in load force, both using less than 20 features. In conclusion, this feature extraction and selection framework is effective and can be extended to more general applications.