Adaptive Semi-Supervised Intent Inferral to Control a Powered Hand Orthosis for Stroke
Preprint
Abstract
In order to provide therapy in a functional context, controls for wearable robotic orthoses need to be robust and intuitive. We have previously introduced an intuitive, user-driven, EMG-based method to operate a robotic hand orthosis, but the process of training a control that is robust to concept drift (changes in the input signal) places a substantial burden on the user. In this paper, we explore semi-supervised learning as a paradigm for controlling a powered hand orthosis for stroke subjects. To the best of our knowledge, this is the first use of semi-supervised learning for an orthotic application. Specifically, we propose a disagreement-based semi-supervision algorithm for handling intrasession concept drift based on multimodal ipsilateral sensing. We evaluate the performance of our algorithm on data collected from five stroke subjects. Our results show that the proposed algorithm helps the device adapt to intrasession drift using unlabeled data and reduces the training burden placed on the user. We also validate the feasibility of our proposed algorithm with a functional task; in these experiments, two subjects successfully completed multiple instances of a pick-and-handover task.Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- Multimodal Sensing and Interaction for a Robotic Hand OrthosisIEEE Robotics and Automation Letters, 2018
- Self-Correcting Pattern Recognition System of Surface EMG Signals for Upper Limb Prosthesis ControlIEEE Transactions on Biomedical Engineering, 2013
- A Training Strategy for Learning Pattern Recognition Control for Myoelectric ProsthesesJPO Journal of Prosthetics and Orthotics, 2013
- Involuntary paretic wrist/finger flexion forces and EMG increase with shoulder abduction load in individuals with chronic strokeClinical Neurophysiology, 2012
- Subject-Specific Myoelectric Pattern Classification of Functional Hand Movements for Stroke SurvivorsIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2010
- Adaptive Pattern Recognition of Myoelectric Signals: Exploration of Conceptual Framework and Practical AlgorithmsIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2009
- Surface EMG in advanced hand prostheticsBiological Cybernetics, 2008
- Motor learning: its relevance to stroke recovery and neurorehabilitationCurrent Opinion in Neurology, 2006
- Tri-training: exploiting unlabeled data using three classifiersIEEE Transactions on Knowledge and Data Engineering, 2005
- Changes in upper limb joint torque patterns and EMG signals with fatigue following a strokeDisability and Rehabilitation, 2002