Hand gesture recognition with deep residual network using Semg signal

Abid Saeed Khattak; Azlan Bin Mohd Zain; Rohayanti Binti Hassan; Fakhra Nazar; Muhammad Haris; Bilal Ashfaq Ahmed

doi:10.1515/bmt-2023-0208

Hand gesture recognition with deep residual network using Semg signal

Biomed Tech (Berl). 2024 Mar 8. doi: 10.1515/bmt-2023-0208. Online ahead of print.

Authors

Abid Saeed Khattak^{1

2}, Azlan Bin Mohd Zain¹, Rohayanti Binti Hassan¹, Fakhra Nazar³, Muhammad Haris^{1

2}, Bilal Ashfaq Ahmed¹

Affiliations

¹ Faculty of Computing, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia.
² Department of Computer Science & Bioinformatics, Khushal Khan Khattak University Karak, 27200, Karak, Khyber Pakhtunkhwa, Pakistan.
³ Department of Computer Sciences & Information, Faculty of Basic and Applied Sciences Technology, University of Poonch Rawalakot, Shamsabad, Azad Jammu and Kashmir, India.

PMID: 38456275
DOI: 10.1515/bmt-2023-0208

Abstract

Objectives: To design and develop a classifier, named Sewing Driving Training based Optimization-Deep Residual Network (SDTO_DRN) for hand gesture recognition.

Methods: The electrical activity of forearm muscles generates the signals that can be captured with Surface Electromyography (sEMG) sensors and includes meaningful data for decoding both muscle actions and hand movement. This research develops an efficacious scheme for hand gesture recognition using SDTO_DRN. Here, signal pre-processing is done through Gaussian filtering. Thereafter, desired and appropriate features are extracted. Following that, effective features are chosen using SDTO. At last, hand gesture identification is accomplished based on DRN and this network is effectively fine-tuned by SDTO, which is a combination of Sewing Training Based Optimization (STBO) and Driving Training Based Optimization (DTBO). The datasets employed for the implementation of this work are MyoUP Dataset and putEMG: sEMG Gesture and Force Recognition Dataset.

Results: The designed SDTO_DRN model has gained superior performance with magnificent results by delivering a maximum accuracy of 0.943, True Positive Rate (TPR) of 0.929, True Negative Rate (TNR) of 0.919, Positive Predictive Value (PPV) of 0.924, and Negative Predictive Value (NPV) of 0.924.

Conclusions: The hand gesture recognition using the proposed model is accurate and improves the effectiveness of the recognition.

Keywords: Deep Residual Network (DRN); Driving Training Based Optimization (DTBO); Gaussian filter; Sewing Training Based Optimization (STBO); Surface Electromyography (sEMG) signals.