Electromyography and mechanomyography signal recognition: Experimental analysis using multi-way array decomposition methods

• Autorzy: Wołczowski A. , Zdunek R.

Identyfikatory

DOI

10.1016/j.bbe.2016.09.004

• Języki publikacji: EN

Abstrakty

EN

In this study, we considered the problem of controlling a prosthetic hand with noisy electromyography (EMG) and mechanomyography (MMG) signals. Several dimensionality reduction methods were analyzed to assess their efficiency at classifying these signals, which were registered during the performance of grasping movements with various objects. Using the cross-validation technique, we compared various dimensionality reduction methods, such as principal components analysis, nonnegative matrix factorization, and some tensor decomposition models. The experimental results demonstrated that the high-est classification accuracy (exceeding 95% for all subjects when classifying 11 grasping movements) and lowest computational complexity were obtained when higher-order singular value decomposition was applied to a multi-way array of multi-channel spectrograms, where the temporal EMG/MMG signals from all channels were concatenated.

Słowa kluczowe

EN

biosignal processing; electromyography; mechanomyography; multiarray decomposition method; supervised classification

PL

elektromiografia; mechanomiografia; metoda dekompozycji; klasyfikacja nadzorowana

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2017
• Tom: Vol. 37, no. 1
• Strony: 103--113
• Opis fizyczny: Bibliogr. 27 poz., rys., tab., wykr.

Twórcy

autor

Wołczowski A.

• Faculty of Electronics, Wroclaw University of Science and Technology, Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, Poland

autor

Zdunek R.

• Faculty of Electronics, Wroclaw University of Science and Technology, Wybrzeze Wyspianskiego 27, 50-370 Wroclaw, Poland

Bibliografia

• [1] Alkan A, Gunay M. Identification of EMG signals using discriminant analysis and SVM classifier. Expert Syst Appl 2012;39(1):44–7.
• [2] Carroll JD, Chang JJ. Analysis of individual differences in multidimensional scaling via an n-way generalization of Eckart-Young decomposition. Psychometrika 1970;35:283–319.
• [3] Cichocki A, Zdunek R, Phan AH, Amari S-I. Nonnegative matrix and tensor factorizations: applications to exploratory multi-way data analysis and blind source separation. Wiley and Sons; 2009.
• [4] De Lathauwer L, de Moor B, Vandewalle J. A multilinear singular value decomposition. SIAM J Matrix Anal Appl 2000;21:1253–78.
• [5] Gokgoz E, Subasi A. Comparison of decision tree algorithms for EMG signal classification using DWT. Biomed Signal Process Control 2015;18:138–44.
• [7] Harshman RA. Foundations of the PARAFAC procedure: Models and conditions for an ‘‘explanatory’’multimodal factor analysis.UCLA working papers in phonetics. vol. 16. 1970;p. 1–84.
• [8] Jiang N, Englehart KB, Parker PA. Extracting simultaneous and proportional neural control information for multiple- DOF prostheses from the surface electromyographic signal. IEEE Trans Biomed Eng 2009;56(4):1070–80.
• [9] Jolliffe IT. Principal component analysis. Springer series in statistics. 2nd ed. Springer; 2002.
• [10] Josse J, Husson F. Selecting the number of components in principal component analysis using cross-validation approximations. Comput Stat Data Anal 2012;56(6):1869–79.
• [11] Kim S, Kim M, Lee J, Park J. Robot hand synergy mapping using multi-factor model and EMG signal. Proc. 14-th International Symposium on Experimental Robotics (ISER 2014), volume 109 of Springer Tracts in Advanced Robotics; 2016. pp. 671–83.
• [12] Kolda TG, Bader BW. Tensor decompositions and applications. SIAM Rev 2009;51(3):455–500.
• [13] Kurzynski M, Krysmann M, Trajdos P, Wolczowski A. Multiclassifier system with hybrid learning applied to the control of bioprosthetic hand. Comput Biol Med 2016;69 (1):286–97.
• [14] Lee DD, Seung HS. Learning the parts of objects by non- negative matrix factorization. Nature 1999;401:788–91.
• [15] Lee J, Kim J, Park J. Classification of grip configuration using surface EMG. Proc. 13th International Conference on Control, Automation and Systems (ICCAS 2013); 2013. pp. 671–83.
• [16] Lucas M-F, Gaufriau A, Pascual S, Doncarli C, Farina D. Multi-channel surface EMG classification using support vector machines and signal-based wavelet optimization. Biomed Signal Process Control 2008;3(2):169–74.
• [17] Niegowski M, Zivanovic M. ECG-EMG separation by using enhanced non-negative matrix factorization.. Proc. 36-th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). August 2014. pp. 4212–5.
• [18] Oliveira AS, Gizzi L, Farina D, Kersting UG. Motor modules of human locomotion: influence of EMG averaging, concatenation and number of gait cycles. Front Hum Neurosci 2014;8(335).
• [19] Phan AH, Cichocki A. Tensor decompositions for feature extraction and classification of high dimensional datasets. IEICE Nonlinear Theory Appl 2010;1(1):37–68.
• [20] Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Syst Appl 2012;39(8):7420–31.
• [21] Stephen M. EMG-EMG coherence analysis on the elbow and shoulder muscles (Master's thesis). Saint Louis, Missouri: Washington University in St. Louis; December 2013.
• [22] Theis FJ, Garcia GA. On the use of sparse signal decomposition in the analysis of multi-channel surface electromyograms. Signal Process 2006;86(3):603–23.
• [23] Timmerman ME, Kiers HAL. Three mode principal components analysis: choosing the numbers of components and sensitivity to local optima. Br J Math Stat Psychol 2000;53(1):1–16.
• [24] Tucker LR. Some mathematical notes on three-mode factor analysis. Psychometrika 1966;31:279–311.
• [25] Ulfarsson MO, Solo V. Selecting the number of principal components with SURE. IEEE Signal Process Lett 2015;22 (2):239–43.
• [26] Wolczowski A, Kurzynski M. Human-machine interface in bioprosthesis control using EMG signal classification. Expert Syst 2010;27(1):53–70.
• [27] Xie P, Song Y. Multi-domain feature extraction from surface EMG signals using nonnegative tensor factorization. Proc. 2013 IEEE International Conference on Bioinformatics and Biomedicine; 2013. pp. 322–5.
• [28] Yazama Y, Mitsukura Y, Fukumi M, Akamatsu N. Recognition system for EMG signals by using non-negative matrix factorization. Proc. International Joint Conference on Neural Networks, vol. 3; 2003. pp. 2130–3.

Uwagi

PL

W opisie bibliograficznym brak pozycji nr 6.

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).