Utilizing Data Quality Indices for Strategic Sensor Channel Selection to Enhance Performance of Hand Gesture Recognition Systems

TL;DR

This paper introduces a method to select the best sensor channels for hand gesture recognition using data quality indices, improving performance in wearable systems.

Contribution

The novelty lies in using data quality indices to strategically select sensor channels for enhanced gesture recognition accuracy.

Findings

ML-based channel selection achieved 76.36% accuracy for sEMG and 71.59% for pFMG on the UOW dataset.

Strategically selected sEMG-pFMG channels achieved 88.2% accuracy, comparable to a full eight-channel sEMG system.

The proposed methods outperformed random selection across multiple datasets.

Abstract

This study proposes a data quality-driven channel selection methodology to improve hand gesture recognition performance in multi-channel wearable Human–Machine Interface (HMI) systems. The methodology centers around calculating (i) five data quality indices for both surface electromyography (sEMG) and pressure-based force myography (pFMG) signals and (ii) establishing a relationship between these data quality indices and the accuracy of gesture recognition for applications typified by prosthetic hand control. Machine learning (ML)-based and correlation-based methods were used to select three optimal channel/pair configurations from an eight-channel/pair system. Evaluations on the UOW and Ninapro DB2 datasets showed that the proposed methods consistently outperformed random channel selection, with the ML-based approach achieving the best results (76.36% for sEMG, 71.59% for pFMG, and 88.2% for fused sEMG-pFMG on the UOW dataset and 70.28% on Ninapro DB2). Notably, using three pairs of strategically selected sEMG-pFMG channels generated 88.2%, which is comparable to the 88.38% accuracy obtained with a full eight-channel sEMG system on the UOW dataset, highlighting the efficacy of our channel selection methodologies. These results highlight the value of data quality indices for sensor selection and provide a foundation for developing more efficient wearable HMI systems.

Figures