Maximizing Performance with Minimal Resources for Real-Time Transition Detection

TL;DR

This paper introduces a real-time transition detection method for assistive devices that uses activity-specific thresholds to significantly improve processing speed while maintaining high accuracy, validated across multiple systems and participants.

Contribution

The paper presents a novel threshold-based approach for real-time activity transition detection that outperforms traditional machine learning methods in processing speed.

Findings

Up to 11 times faster processing performance.

High accuracy in transition detection.

Validated robustness across different measurement systems.

Abstract

Assistive devices, such as exoskeletons and prostheses, have revolutionized the field of rehabilitation and mobility assistance. Efficiently detecting transitions between different activities, such as walking, stair ascending and descending, and sitting, is crucial for ensuring adaptive control and enhancing user experience. We here present an approach for real-time transition detection, aimed at optimizing the processing-time performance. By establishing activity-specific threshold values through trained machine learning models, we effectively distinguish motion patterns and we identify transition moments between locomotion modes. This threshold-based method improves real-time embedded processing time performance by up to 11 times compared to machine learning approaches. The efficacy of the developed finite-state machine is validated using data collected from three different measurement systems. Moreover, experiments with healthy participants were conducted on an active pelvis orthosis to validate the robustness and reliability of our approach. The proposed algorithm achieved high accuracy in detecting transitions between activities. These promising results show the robustness and reliability of the method, reinforcing its potential for integration into practical applications.