A system concept for EMG classification from measurement to deployment
Conference: CNNA 2016 - 15th International Workshop on Cellular Nanoscale Networks and their Applications
08/23/2016 - 08/25/2016 at Dresden, Deutschland
Proceedings: CNNA 2016
Pages: 2Language: englishTyp: PDFPersonal VDE Members are entitled to a 10% discount on this title
Borbely, Bence J. (Faculty of Information Technology and Bionics, Pazmany Peter Catholic University, 1083 Budapest, Hungary)
Szolgay, Peter (Faculty of Information Technology and Bionics, Pazmany Peter Catholic University, 1083 Budapest, Hungary & Cellular Sensory and Optical Wave Computing Laboratory, Hungarian Academy of Sciences, 1111 Budapest, Hungary)
In this paper an overall concept of a classification system is presented using different hardware architectures for data measurement, classifier training and deployment. The system is designed for position estimation of human arm movements based on bioelectric signals of skeletal muscles (EMG) and utilizes model-based kinematics and deep neural networks at its core. As an example, measurement data from a multi-channel forearm EMG recording is presented from a task where a subject performed periodic wrist flexion and extension movements to show a novel automatic data labeling method.