When One Sensor Fails: Tolerating Dysfunction in Multi-Sensor Prototypes

TL;DR

This paper presents a framework for enhancing the reliability of multi-sensor sEMG systems by identifying crucial sensors and enabling fail-safe operation, demonstrated through gesture recognition experiments.

Contribution

It introduces a systematic method to rank sensor importance and implement fail-safe mechanisms in multi-sensor sEMG systems, improving robustness.

Findings

FDR analysis effectively ranks sensor importance.

Multi-layer perceptron validates the robustness of the approach.

Sensor ablation studies show system resilience with redundant sensors.

Abstract

Surface electromyography (sEMG) sensors are widely used in human-computer interaction, yet the failure of a single sensor can compromise system usability. We propose a methodological framework for implementing a fail-safe mechanism in multi-sensor sEMG systems. Using arm sEMG recordings of rock-paper-scissors gestures, we extracted hand-crafted features and quantified class separability via the maximum Fisher discriminant ratio (FDR). A multi-layer perceptron validated our approach, consistent with prior findings and physiological evidence. Systematic sensor ablations and FDR analysis produced a ranking of crucial versus replaceable sensors. This ranking informs robust device design, sensor redundancy, and reliability in clinical and practical applications.