Adaptive Lower Limb Pattern Recognition for Multi-Day Control

Rob Schulte*, Erik C. Prinsen*, Jaap Hilbert Buurke, Mannes Poel

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

1 Downloads (Pure)

Abstract

Pattern recognition in EMG-based control systems suffer from increase in error rate over time, which could lead to unwanted behavior. This so-called concept drift in myoelectric control systems could be caused by fatigue, sensor replacement and varying skin conditions. To circumvent concept drift, adaptation strategies could be used to retrain a pattern recognition system, which could lead to comparable error rates over multiple days. In this study, we investigated the error rate development over one week and compared three adaptation strategies to reduce the error rate increase. The three adaptation strategies were based on entropy, on backward prediction and a combination of backward prediction and entropy. Ten able-bodied subjects were measured on four measurement days while performing gait-related activities. During the measurement electromyography and kinematics were recorded. The three adaptation strategies were implemented and compared against the baseline error rate and against adaptation using the ground truth labels. It can be concluded that without adaptation the baseline error rate increases significantly from day 1 to 2, but plateaus on day 2, 3 and 7. Of the three tested adaptation strategies, entropy based adaptation showed the smallest increase in error rate over time. It can be concluded that entropy based adaptation is simple to implement and can be considered a feasible adaptation strategy for lower limb pattern recognition.
Original languageEnglish
Article number6351
JournalSensors
Volume22
Issue number17
Early online date24 Aug 2022
DOIs
Publication statusPublished - Sep 2022

Keywords

  • Electromyography (EMG)
  • Machine learning (ML)
  • Lower limb
  • Pattern recognition
  • Multi-day

Fingerprint

Dive into the research topics of 'Adaptive Lower Limb Pattern Recognition for Multi-Day Control'. Together they form a unique fingerprint.

Cite this