An Efficient Feature Extraction Technique and Novel Normalization Method to Improve EMG Signal Classification

Advancements in neural network approaches have enhanced the effectiveness of surface Electromyography (sEMG)-based hand gesture recognition when measuring muscle activity. However, current deep learning architectures struggle to achieve good generalization and robustness, often demanding significant computational resources. The goal of this paper was to develop a robust model that can quickly adapt to new users using Transfer Learning. We propose a Multi-Scale Convolutional Neural Network (MSCNN), pre-trained with various strategies to improve inter-subject generalization. These strategies include domain adaptation with a gradient-reversal layer and self-supervision using triplet margin loss. We evaluated these approaches on several benchmark datasets, specifically the NinaPro databases. This study also compared two different Transfer Learning frameworks designed for user-dependent fine-tuning. The second Transfer Learning framework achieved a 97% F1 Score across 14 classes with an average of 1.40 epochs, suggesting potential for on-site model retraining in cases of performance degradation over time. The findings highlight the effectiveness of Transfer Learning in creating adaptive, user-specific models for sEMG-based prosthetic hands. Moreover, the study examined the impacts of rectification and window length, with a focus on real-time accessible normalizing techniques, suggesting significant improvements in usability and performance.

show abstract

Fused Multi-Domains and Adaptive Variational Mode Decomposition ECG Feature Extraction for Lightweight Bio-Inspired Key Generation and Encryption

Agbehadji,

Millham,

Freeman

et al. 2024

Sensors

View full text Add to dashboard Cite

Security is one of the increasingly significant issues given advancements in technology that harness data from multiple devices such as the internet of medical devices. While protecting data from unauthorized user access, several techniques are used including fingerprints, passwords, and others. One of the techniques that has attracted much attention is the use of human features, which has proven to be most effective because of the difficulties in impersonating human-related features. An example of a human-related attribute includes the electrical signal generated from the heart, mostly referred to as an Electrocardiogram (ECG) signal. The methods to extract features from ECG signals are time domain-based; however, the challenge with relying only on the time-domain or frequency-domain method is the inability to capture the intra-leading relationship of Variational Mode Decomposition signals. In this research, fusing multiple domains ECG feature and adaptive Variational Mode Decomposition approaches are utilized to mitigate the challenge of losing the intra-leading correlations of mode decompositions, which might reduce the robustness of encryption algorithms. The features extracted using the reconstructed signal have a mean (0.0004), standard deviation (0.0391), skewness (0.1562), and kurtosis (1.2205). Among the lightweight encryption methods considered, Chacha20 has a total execution time of 27µs. The study proposes a lightweight encryption technique based on the fused vector representation of extracted features to provide an encryption scheme in addition to a bio-inspired key generation technique for data encryption.

show abstract

An Efficient Feature Extraction Technique and Novel Normalization Method to Improve EMG Signal Classification

Cited by 3 publications

References 18 publications

A Comprehensive Review on - Machine Learning in Bio-Signal Analysis for Chronic Pain Research

A Comprehensive Review on - Machine Learning in Bio-Signal Analysis for Chronic Pain Research

A Multi-Scale CNN for Transfer Learning in sEMG-Based Hand Gesture Recognition for Prosthetic Devices

Fused Multi-Domains and Adaptive Variational Mode Decomposition ECG Feature Extraction for Lightweight Bio-Inspired Key Generation and Encryption

Contact Info

Product

Resources

About