Saved in:
Bibliographic Details
Main Authors: Wazir, Hafsa, Ahmad, Jawad, Khan, Muazzam A., Jan, Sana Ullah, Khan, Fadia Ali, Khan, Muhammad Shahbaz
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2503.09041
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929755522072576
author Wazir, Hafsa
Ahmad, Jawad
Khan, Muazzam A.
Jan, Sana Ullah
Khan, Fadia Ali
Khan, Muhammad Shahbaz
author_facet Wazir, Hafsa
Ahmad, Jawad
Khan, Muazzam A.
Jan, Sana Ullah
Khan, Fadia Ali
Khan, Muhammad Shahbaz
contents Electromyography (EMG) is extensively used in key biomedical areas, such as prosthetics, and assistive and interactive technologies. This paper presents a new hybrid neural network named ConSGruNet for precise and efficient hand gesture recognition. The proposed model comprises convolutional neural networks with smart skip connections in conjunction with a Gated Recurrent Unit (GRU). The proposed model is trained on the complete Ninapro DB1 dataset. The proposed model boasts an accuracy of 99.7\% in classifying 53 classes in just 25 milliseconds. In addition to being fast, the proposed model is lightweight with just 3,946 KB in size. Moreover, the proposed model has also been evaluated for the reliability parameters, i.e., Cohen's kappa coefficient, Matthew's correlation coefficient, and confidence intervals. The close to ideal results of these parameters validate the models performance on unseen data.
format Preprint
id arxiv_https___arxiv_org_abs_2503_09041
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Hybrid Neural Network with Smart Skip Connections for High-Precision, Low-Latency EMG-Based Hand Gesture Recognition
Wazir, Hafsa
Ahmad, Jawad
Khan, Muazzam A.
Jan, Sana Ullah
Khan, Fadia Ali
Khan, Muhammad Shahbaz
Cryptography and Security
Electromyography (EMG) is extensively used in key biomedical areas, such as prosthetics, and assistive and interactive technologies. This paper presents a new hybrid neural network named ConSGruNet for precise and efficient hand gesture recognition. The proposed model comprises convolutional neural networks with smart skip connections in conjunction with a Gated Recurrent Unit (GRU). The proposed model is trained on the complete Ninapro DB1 dataset. The proposed model boasts an accuracy of 99.7\% in classifying 53 classes in just 25 milliseconds. In addition to being fast, the proposed model is lightweight with just 3,946 KB in size. Moreover, the proposed model has also been evaluated for the reliability parameters, i.e., Cohen's kappa coefficient, Matthew's correlation coefficient, and confidence intervals. The close to ideal results of these parameters validate the models performance on unseen data.
title A Hybrid Neural Network with Smart Skip Connections for High-Precision, Low-Latency EMG-Based Hand Gesture Recognition
topic Cryptography and Security
url https://arxiv.org/abs/2503.09041