EMG gesture signal analysis towards diagnosis of upper limb using dual-pathway convolutional neural network

• Published in: Mathematical biosciences and engineering : MBE Vol. 21; no. 4; pp. 5712 - 5734
• Main Authors: Qamar, Hafiz Ghulam Murtza, Qureshi, Muhammad Farrukh, Mushtaq, Zohaib, Zubariah, Zubariah, Rehman, Muhammad Zia ur, Samee, Nagwan Abdel, Mahmoud, Noha F., Gu, Yeong Hyeon, Al-masni, Mohammed A.
• Format: Journal Article
• Language: English
• Published: United States AIMS Press 24.04.2024
• Subjects: Adult; Algorithms; Amputees; convolutional neural network; electromyography; Electromyography - methods; Female; gesture recognition; Gestures; Humans; log mel spectrogram; Male; Middle Aged; Neural Networks, Computer; nina pro; Reproducibility of Results; Signal Processing, Computer-Assisted; Upper Extremity - physiology; upper limb; Young Adult; nina pro; upper limb; gesture recognition; log mel spectrogram; convolutional neural network; electromyography
• ISSN: 1551-0018; 1547-1063; 1551-0018
• DOI: 10.3934/mbe.2024252

This research introduces a novel dual-pathway convolutional neural network (DP-CNN) architecture tailored for robust performance in Log-Mel spectrogram image analysis derived from raw multichannel electromyography signals. The primary objective is to assess the effectiveness of the proposed DP-CNN architecture across three datasets (NinaPro DB1, DB2, and DB3), encompassing both able-bodied and amputee subjects. Performance metrics, including accuracy, precision, recall, and F1-score, are employed for comprehensive evaluation. The DP-CNN demonstrates notable mean accuracies of 94.93 ± 1.71% and 94.00 ± 3.65% on NinaPro DB1 and DB2 for healthy subjects, respectively. Additionally, it achieves a robust mean classification accuracy of 85.36 ± 0.82% on amputee subjects in DB3, affirming its efficacy. Comparative analysis with previous methodologies on the same datasets reveals substantial improvements of 28.33%, 26.92%, and 39.09% over the baseline for DB1, DB2, and DB3, respectively. The DP-CNN's superior performance extends to comparisons with transfer learning models for image classification, reaffirming its efficacy. Across diverse datasets involving both able-bodied and amputee subjects, the DP-CNN exhibits enhanced capabilities, holding promise for advancing myoelectric control.