Classification of electromyography signals using relevance vector machines and fractal dimension
- 371 Downloads
Surface electromyography (EMG) signals have been studied extensively in the last years aiming at the automatic classification of hand gestures and movements as well as the early identification of latent neuromuscular disorders. In this paper, we investigate the potentials of the conjoint use of relevance vector machines (RVM) and fractal dimension (FD) for automatically identifying EMG signals related to different classes of limb motion. The adoption of FD as the mechanism for feature extraction is justified by the fact that EMG signals usually show traces of self-similarity. In particular, four well-known FD estimation methods, namely box-counting, Higuchi’s, Katz’s and Sevcik’s methods, have been considered in this study. With respect to RVM, besides the standard formulation for binary classification, we also investigate the performance of two recently proposed variants, namely constructive mRVM and top-down mRVM, that deal specifically with multiclass problems. These classifiers operate solely over the features extracted by the FD estimation methods, and since the number of such features is relatively small, the efficiency of the classifier induction process is ensured. Results of experiments conducted on a publicly available dataset involving seven distinct types of limb motions are reported whereby we assess the performance of different configurations of the proposed RVM+FD approach. Overall, the results evidence that kernel machines equipped with the FD feature values can be useful for achieving good levels of classification performance. In particular, we have empirically observed that the features extracted by the Katz’s method is of better quality than the features generated by other methods.
KeywordsEMG signal classification Relevance vector machines Fractal dimension Feature extraction
The first and second authors acknowledge the sponsorship from the Brazilian National Council for Research and Development (CNPq) via grants #475406/2010-9, #308816/2012-9, and #304603/2012-0. The third author thanks the financial support of São Paulo Research Foundation (FAPESP/ Brazil)—process number 2011/04608-8.
- 6.Chan AD, Green GC (2007) Myoelectric control development toolbox. In: Proceedings of 30th conference of the Canadian medical & biological engineering societyGoogle Scholar
- 10.Damoulas T, Girolami M, Ying Y, Campbell C (2008) Inferring sparse kernel combinations and relevance vectors: An application to subcellular localization of proteins. In: Proceedings of the 7th International Conference in Machine Learning Applications, pp 577–582Google Scholar
- 15.Englehart K, Hudgins B, Chan ADC (2003) Continuous multifunction myoelectric control using pattern recognition. Technol Disabil 15(2):95–103Google Scholar
- 17.Goge A, Chan A (2004) Investigating classification parameters for continuous myoelectrically controlled prostheses. In: Proceedings of the 28th conference of the Canadian medical & biological engineering society, pp 141–144Google Scholar
- 32.Najarian K, Splinter R (2012) Biomedical signal and image processing, 2nd edn. CRC Press, Boca RatonGoogle Scholar
- 33.Nussbaum M A, Yassierli (2003) Assessment of localized muscle fatigue furing low-moderate static contractions using the fractal dimension of EMG. In: Proceedings of the XVth triennial congress of the international ergonomics association, Seoul, Korea, August 25–29Google Scholar
- 37.Riillo F, Quitadamo L, Cavrinia F, Gruppioni E, Pinto C, Pastò NC, Sbernini L, Albero L, Saggio G (2014) Optimization of EMG-based hand gesture recognition: supervised vs. unsupervised data preprocessing on healthy subjects and transradial amputees. Biomed Signal Process Control 14:117–125CrossRefGoogle Scholar
- 43.Tipping M, Faul A (2003) Fast marginal likelihood maximisation for sparse bayesian models. In: Proceedings of 9th AISTATS workshop, pp 3–6Google Scholar