EMG gesture signal analysis towards diagnosis of upper limb using dual-pathway convolutional neural network
Gespeichert in:
| Titel: | EMG gesture signal analysis towards diagnosis of upper limb using dual-pathway convolutional neural network |
|---|---|
| Autoren: | Hafiz Ghulam Murtza Qamar, Muhammad Farrukh Qureshi, Zohaib Mushtaq, Zubariah Zubariah, Muhammad Zia ur Rehman, Nagwan Abdel Samee, Noha F. Mahmoud, Yeong Hyeon Gu, Mohammed A. Al‐masni |
| Quelle: | Mathematical Biosciences and Engineering, Vol 21, Iss 4, Pp 5712-5734 (2024) Qamar, H G M, Qureshi, M F, Mushtaq, Z, Zubariah, Z, Rehman, M Z U, Samee, N A, Mahmoud, N F, Gu, Y H & Al-Masni, M A 2024, 'EMG gesture signal analysis towards diagnosis of upper limb using dual-pathway convolutional neural network', Mathematical Biosciences and Engineering, vol. 21, no. 4, pp. 5712-5734. https://doi.org/10.3934/mbe.2024252 |
| Verlagsinformationen: | American Institute of Mathematical Sciences (AIMS), 2024. |
| Publikationsjahr: | 2024 |
| Schlagwörter: | Male, electromyography, Artificial intelligence, log mel spectrogram, convolutional neural network, 02 engineering and technology, Surface EMG, Pattern recognition (psychology), Epilepsy Detection, EEG Analysis, 0302 clinical medicine, Engineering, Cognitive psychology, 0202 electrical engineering, electronic engineering, information engineering, Psychology, Gestures, Life Sciences, Signal Processing, Computer-Assisted, Neural Interface Technology, Middle Aged, Brain-Computer Interfaces in Neuroscience and Medicine, FOS: Psychology, Analysis of Electromyography Signal Processing, Physical Sciences, nina pro, Medicine, Female, Algorithms, Biotechnology, Adult, Cognitive Neuroscience, Biomedical Engineering, Convolutional neural network, upper limb, Speech recognition, FOS: Medical engineering, Upper Extremity, Young Adult, 03 medical and health sciences, Cellular and Molecular Neuroscience, Amputees, QA1-939, Humans, Deep Learning for EEG, gesture recognition, Electromyography, Reproducibility of Results, Computer science, Musculoskeletal Modeling, Physical medicine and rehabilitation, Recall, Neural Networks, Computer, TP248.13-248.65, Mathematics, Neuroscience |
| Beschreibung: | 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. |
| Publikationsart: | Article Other literature type |
| Dateibeschreibung: | application/pdf |
| ISSN: | 1551-0018 |
| DOI: | 10.3934/mbe.2024252 |
| DOI: | 10.60692/v5ztk-e1717 |
| DOI: | 10.60692/tspwt-fan37 |
| Zugangs-URL: | https://pubmed.ncbi.nlm.nih.gov/38872555 https://doaj.org/article/9d76c19912c04629a23aa47278da8f07 https://vbn.aau.dk/ws/files/708673610/10.3934_mbe.2024252.pdf http://www.scopus.com/inward/record.url?scp=85191355753&partnerID=8YFLogxK https://vbn.aau.dk/da/publications/55d5565c-7538-426b-9b88-92f480607225 https://doi.org/10.3934/mbe.2024252 |
| Dokumentencode: | edsair.doi.dedup.....65bd6e564a9e659d9714f5e6257d2995 |
| Datenbank: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | 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. |
|---|---|
| ISSN: | 15510018 |
| DOI: | 10.3934/mbe.2024252 |