Regression of Hand Movements from sEMG Data with Recurrent Neural Networks

Philipp Koch, Mark Dreier, Anna Larsen, Tim J. Parbs, Marco Maass, Huy Phan, Alfred Mertins


Most wearable human-machine interfaces concerning hand movements only focus on classifying a limited number of hand gestures. With the introduction of deep learning, surface electromyography based hand gesture classification systems improved drastically. Therefore, it is worth investigating whether the classification can be replaced by a movement regression of all the different movable hand parts. As recurrent neural networks based approaches have proven their abilities of solving the classification problem we also choose them for the regression problem. Experiments were conducted with multiple different network architectures on several databases. Furthermore, due to the lack of a reliable measure to compare different gesture regression approaches we propose an interpretable and reproducible new error measure that can even handle noisy ground truth data. The results reveal the general possibility of regressing detailed hand movements. Even with the relatively simple networks the hand gestures can be regressed quite accurately.

Original languageEnglish
Title of host publication2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)
Number of pages5
Publication date07.2020
Article number9176278
ISBN (Print)978-1-7281-1991-5
ISBN (Electronic)978-1-7281-1990-8
Publication statusPublished - 07.2020
Event42nd Annual International Conferences of the IEEE Engineering in Medicine and Biology Society - Montreal, Canada
Duration: 20.07.202024.07.2020
Conference number: 162693


Dive into the research topics of 'Regression of Hand Movements from sEMG Data with Recurrent Neural Networks'. Together they form a unique fingerprint.

Cite this