A sparse Bayesian learning based scheme for multi-movement recognition using sEMG
- 218 Downloads
This paper proposed a feature extraction scheme based on sparse representation considering the non-stationary property of surface electromyography (sEMG). Sparse Bayesian learning was introduced to extract the feature with optimal class separability to improve recognition accuracy of multi-movement patterns. The extracted feature, sparse representation coefficients (SRC), represented time-varying characteristics of sEMG effectively because of the compressibility (or weak sparsity) of the signal in some transformed domains. We investigated the effect of the proposed feature by comparing with other fourteen individual features in offline recognition. The results demonstrated the proposed feature revealed important dynamic information in the sEMG signals. The multi-feature sets formed by the SRC and other single feature yielded more superior performance on recognition accuracy, compared with the single features. The best average recognition accuracy of 94.33 % was gained by using SVM classifier with the multi-feature set combining the feature SRC, Williston amplitude (WAMP), wavelength (WL) and the coefficients of the fourth order autoregressive model (ARC4) via multiple kernel learning framework. The proposed feature extraction scheme (known as SRC + WAMP + WL + ARC4) is a promising method for multi-movement recognition with high accuracy.
KeywordsSurface electromyography (sEMG) Feature extraction Non-stationarity Sparse representation Temporal MMV sparse Bayesian learning (T-MSBL)
We thank S. L. Fang, C. Y. Zhang, C. C. Yu, Y. C. Liu, S. X. Cheng and T. Z. Xia for discussions and assistance with this work.
Compliance with ethical standards
Conflict of interest
No conflict of interest.
- 4.Pang M, Guo S, Song Z (2012) A surface EMG signals-based realtime continuous recognition for the upper limb multi-motion. In: IEEE international conference on mechatronics and automation (ICMA), pp 1984–1989Google Scholar
- 17.Maoqi C, Ping Z (2015) A novel framework based on fastICA for high density surface EMG decomposition. IEEE Trans Neural Syst Rehabil, EngGoogle Scholar
- 19.Boudjellal A, Abed-Meraim K, Aissa-El-Bey A, Belouchrani A (2014) Sparsity-based algorithms for blind separation of convolutive mixtures with application to EMG signals. In: 2014 IEEE workshop on statistical signal processing (SSP)Google Scholar
- 21.Shokrollahi M, Sridhar K (2012) Sleep EMG analysis using sparse signal representation and classification. In: Engineering in Medicine and Biology Society (EMBC), 2012 annual international conference of the IEEE, pp 3480–3483Google Scholar
- 22.Salman A, Allstot EG, Chen AY, Dixon AM, Gangopadhyay D, Allstot DJ (2011) Compressive sampling of EMG bio-signals. In: Circuits and systems (ISCAS), 2011 IEEE international symposium on, pp 2095–2098Google Scholar
- 24.Naik GR, Acharyya A, Nguyen HT (2014) Classification of finger extension and flexion of EMG and Cyberglove data with modified ICA weight matrix. In: Engineering in Medicine and Biology Society (EMBC), 2014 36th annual international conference of the IEEE, pp 3829–3832Google Scholar
- 27.Kameoka H, Ono N, Kashino K, Sagayama S (2009) Complex NMF: a new sparse representation for acoustic signals. In: Acoustics, speech and signal processing, ICASSP 2009. IEEE international conference on pp 3437–3440Google Scholar
- 28.Tipping ME (2001) Sparse Bayesian learning and the relevance vector machine. J Mach Learn Res 1:211–244Google Scholar
- 31.Lu ZN, Zeng QX, Li CY, Yu SZ (2002) Practical electromyography. People’s Medical Publishing House, BeijingGoogle Scholar
- 33.Eldar YC, Kutyniok G (eds) (2012) Compressed sensing: theory and applications. Cambridge University Press, Oxford cityGoogle Scholar
- 35.Zhang Z, Rao BD (2011) Clarify some issues on the sparse Bayesian learning for sparse signal recovery University of California, San Diego, Tech. RepGoogle Scholar
- 37.Sobahi NM (2011) Denoising of EMG signals based on Wavelet transform. Asian Trans Eng 1:17–23Google Scholar
- 38.Phinyomark A, Hirunviriya S, Nuidod A, Phukpattaranont P, Limsakul C (2011) Evaluation of EMG feature extraction for movement control of upper limb prostheses based on class separation index. In: International conference on biomedical engineering, pp 750–754Google Scholar
- 39.Oskoei MA, Hu H, Gan JQ (2013) Feature-channel subset selection for optimising myoelectric human-machine interface design. Int J Biomech Biomed Robot 2:195–208Google Scholar
- 41.Ibrahimy MI, Ahsan MR, Khalifa OO (2013) Design and performance analysis of artificial neural network for hand motion detection from EMG signals. World Appl Sci J 23:751–758Google Scholar
- 43.Rakotomamonjy A, Bach FR, Canu S, Grandvalet Y (2008) SimpleMKL. J Mach Learn Res 9:2491–2521Google Scholar