logo Idiap Research Institute        
 [BibTeX] [Marc21]
On the Challenge of Classifying 52 Hand Movements from Surface Electromyography
Type of publication: Conference paper
Citation: Kuzborskij_EMBC_2012
Publication status: Published
Booktitle: 34th Annual Conference of the IEEE Engineering in Medicine & Biology Society
Year: 2012
Abstract: The level of dexterity of myoelectric hand prostheses depends to large extent on the feature representation and subsequent classification of surface electromyography signals. This work presents a comparison of various feature extraction and classification methods on a large-scale surface electromyography database containing 52 different hand movements obtained from 27 subjects. Results indicate that simple feature representations as Mean Absolute Value and Waveform Length can achieve similar performance to the computationally more demanding marginal Discrete Wavelet Transform. With respect to classifiers, the Support Vector Machine was found to be the only method that consistently achieved top performance in combination with each feature extraction method.
Projects Idiap
Authors Kuzborskij, Ilja
Gijsberts, Arjan
Caputo, Barbara
Added by: [UNK]
Total mark: 0
  • Kuzborskij_EMBC_2012.pdf