Predicting optimal surface electromyographic control of human-machine interface devices in individuals with motor impairments
Dr. Cara Stepp, Assistant Professor at the Department of Speech, Language & Hearing Sciences of Boston University (USA), will visit Delsys on Friday October 27th to present her research “Predicting optimal surface electromyographic control of human-machine interface devices in individuals with motor impairments”.
Surface electromyography (sEMG) provides a promising alternative access solution to assistive technology devices for those with limited movement capabilities. However, placing sEMG sensors in an optimal configuration is a complex task even in healthy individuals, requiring trial-and-error by an expert. Sensor configuration grows more challenging when recording from facial musculature likely to be spared in individuals with neurological impairments: not only do the small muscles of the face interdigitate and overlap, but these individuals may have difficulty in volitionally activating these muscles in isolation. Therefore, we sought to reduce sEMG sensor configuration complexity by using quantitative signal features extracted from a short calibration process to predict human-machine interface (HMI) performance. Five sEMG sensors were placed over distinct facial regions and mapped to the following computer cursor actions: move left, move right, move up, move down, and click. Eighteen healthy individuals activated the specific sEMG-targeted muscles to control an onscreen cursor and navigate a target selection task across a range of sensor configurations. Signal features were extracted from the calibration of each configuration and examined via a principle component factor analysis in order to predict HMI performance during subsequent target selection tasks. Results suggest that non-experts can configure sEMG sensors in the vicinity of usable muscle sites and healthy individuals will rapidly learn to efficiently control the HMI system. Similar methodology is currently being implemented in individuals with motor impairments; results will elucidate features to improve the clinical applicability of using sEMG as an access modality.
About Dr. Cara Stepp
Cara Stepp, Ph.D., directs the STEPP Lab for Sensorimotor Rehabilitation Engineering and is Assistant Professor in the Departments of Speech, Language & Hearing Sciences, Otolaryngology – Head and Neck Surgery, and Biomedical Engineering at Boston University. She received the S.B. in Engineering Science from Smith College, S.M. in Electrical Engineering and Computer Science from Massachusetts Institute of Technology, and Ph.D. in Biomedical Engineering from the Harvard-MIT Division of Health Sciences & Technology. Prior to joining Boston University, she completed postdoctoral training in Computer Science & Engineering and Rehabilitation Medicine at the University of Washington. Dr. Stepp’s research uses engineering tools to improve the assessment and rehabilitation of sensorimotor disorders of voice and speech.
About Jennifer Vojtech
Jennifer Vojtech is a doctoral student in Biomedical Engineering at Boston University. Her current research involves developing computational methods to improve the clinical assessment of voice disorders and applying quantitative techniques to enhance augmentative and alternative communication (AAC) device access. In 2017, Jenny was awarded the NSF Graduate Research Fellowship to optimize the functionality of AAC device speech synthesis.