1. bookVolume 12 (2012): Issue 3 (June 2012)
Journal Details
License
Format
Journal
eISSN
1335-8871
First Published
07 Mar 2008
Publication timeframe
6 times per year
Languages
English
Open Access

Application of Linear Discriminant Analysis in Dimensionality Reduction for Hand Motion Classification

Published Online: 28 May 2012
Volume & Issue: Volume 12 (2012) - Issue 3 (June 2012)
Page range: 82 - 89
Journal Details
License
Format
Journal
eISSN
1335-8871
First Published
07 Mar 2008
Publication timeframe
6 times per year
Languages
English
Application of Linear Discriminant Analysis in Dimensionality Reduction for Hand Motion Classification

The classification of upper-limb movements based on surface electromyography (EMG) signals is an important issue in the control of assistive devices and rehabilitation systems. Increasing the number of EMG channels and features in order to increase the number of control commands can yield a high dimensional feature vector. To cope with the accuracy and computation problems associated with high dimensionality, it is commonplace to apply a processing step that transforms the data to a space of significantly lower dimensions with only a limited loss of useful information. Linear discriminant analysis (LDA) has been successfully applied as an EMG feature projection method. Recently, a number of extended LDA-based algorithms have been proposed, which are more competitive in terms of both classification accuracy and computational costs/times with classical LDA. This paper presents the findings of a comparative study of classical LDA and five extended LDA methods. From a quantitative comparison based on seven multi-feature sets, three extended LDA-based algorithms, consisting of uncorrelated LDA, orthogonal LDA and orthogonal fuzzy neighborhood discriminant analysis, produce better class separability when compared with a baseline system (without feature projection), principle component analysis (PCA), and classical LDA. Based on a 7-dimension time domain and time-scale feature vectors, these methods achieved respectively 95.2% and 93.2% classification accuracy by using a linear discriminant classifier.

Keywords

Merletti, R., Hermens, H. (2004). Detection and conditioning of the surface EMG signal. In Merletti R., Parker, P. (eds.) Electromyography: Physiology, Engineering, and Noninvasive Applications. New Jersey: John Wiley & Sons, 107-132.10.1002/0471678384.ch5Search in Google Scholar

Oskoei, M.A., Hu, H. (2007). Myoelectric control systems—A survey. Biomed. Signal Process. Control, 2 (4), 275-294.10.1016/j.bspc.2007.07.009Search in Google Scholar

Parker, P.A., Englehart, K.B., Hudgins, B.S. (2004). Control of powered upper limb prostheses. In Merletti, R., Parker, P. (eds.) Electromyography: Physiology, Engineering, and Noninvasive Applications. New Jersey: John Wiley & Sons, 453-476.10.1002/0471678384.ch18Search in Google Scholar

Phinyomark, A., Phukpattaranont, P., Limsakul, C. (2011). A review of control methods for electric power wheelchairs based on electromyography (EMG) signals with special emphasis on pattern recognition. IETE Technical Review, 28 (4), 316-326.10.4103/0256-4602.83552Search in Google Scholar

Jacobson, S.C., Knutti, D.F., Johnson, R.T., Shears, H.H. (1982). Development of the Utah artificial arm. IEEE Trans. Biomed. Eng., 29 (4), 249-269.10.1109/TBME.1982.325033Search in Google Scholar

Hudgins, B., Parker, P., Scott, R.N. (1993). A new strategy for multifunction myoelectric control. IEEE Trans. Biomed. Eng., 40 (1), 82-94.10.1109/10.204774Search in Google Scholar

Light, C.M., Chappell, P.H. (2000). Development of a lightweight and adaptable multiple-axis hand prosthesis. Med. Eng. Phys., 22 (10), 679-684.10.1016/S1350-4533(01)00017-0Search in Google Scholar

Englehart, K., Hudgin, B., Parker, P.A., Stevenson, M. (1999). Classification of the myoelectric signal using time-frequency based representations. Med. Eng. Phys., 21 (6-7), 431-438.10.1016/S1350-4533(99)00066-1Search in Google Scholar

Khezri, M., Jahed, M. (2009). An exploratory study to design a novel hand movement identification system. Comput. Biol. Med., 39 (5), 433-442.10.1016/j.compbiomed.2009.02.00119342012Search in Google Scholar

Artemiadis, P.K., Kyriakopoulos, K.J. (2010). EMG-based control of a robot arm using low-dimensional embeddings. IEEE Trans. Robotics, 26 (2), 393-398.10.1109/TRO.2009.2039378Search in Google Scholar

Rivera-Alvidrez, Z., Kalmar, R.S., Ryu, S.I., Shenoy, K.V. (2010). Low-dimensional neural features predict muscle EMG signals. In Annual Internal Conference of the IEEE Engineering in Medicine and Biology Society, 31 Aug. - 4 Sept. 2010. IEEE, 6027-6033.10.1109/IEMBS.2010.562760421097116Search in Google Scholar

Khushaba, R.N., Al-Jumaily, A., Al-Ani, A. (2007). Novel feature extraction method based on fuzzy entropy and wavelet packet transform for myoelectric control. In ISCIT '07 : International Symposium on Communications and Information Technologies, 17-19 October 2007. IEEE, 352-357.10.1109/ISCIT.2007.4392044Search in Google Scholar

Chu, J.-U., Moon, I., Mun, M.-S. (2006). A real-time EMG pattern recognition system based on linear-nonlinear feature projection for a multifunction myoelectric hand. IEEE Trans. Biomed. Eng., 53 (11), 2232-2239.Search in Google Scholar

Englehart, K., Hudgin, B., Parker, P.A. (2001). A wavelet-based continuous classification scheme for multifunction myoelectric control. IEEE Trans. Biomed. Eng., 48 (3), 302-311.10.1109/10.91479311327498Search in Google Scholar

Chu, J.-U., Moon, I., Lee, Y.-J., Kim, S.-K., Mun, M.-S. (2007). A supervised feature-projection-based real-time EMG pattern recognition for multifunction myoelectric hand control. IEEE-ASME Trans. Mechatron., 12 (3), 282-290.10.1109/TMECH.2007.897262Search in Google Scholar

Chan, A.D.C., Green, G.C. (2007). Myoelectric control development toolbox. In 30th Conference of the Canadian Medical & Biological Engineering Society, 16-19 June 2007. CMBES, M0100.Search in Google Scholar

Khushaba, R.N., Al-Ani, A., Al-Jumaily, A. (2010). Orthogonal fuzzy neighborhood discriminant analysis for multifunction myoelectric hand control. IEEE Trans. Biomed. Eng., 57 (6), 1410-1419.10.1109/TBME.2009.203948020172801Search in Google Scholar

Liu, Y.H., Huang, H.P., Weng, C.H. (2007). Recognition of electromyographic signals using cascaded kernel learning machine. IEEE-ASME Trans. Mechatron., 12 (3), 253-264.10.1109/TMECH.2007.897253Search in Google Scholar

Khushaba, R.N., Al-Jumaily, A., Al-Ani, A. (2009). Evolutionary fuzzy discriminant analysis feature projection technique in myoelectric control. Pattern Recognition Lett., 30 (7), 699-707.10.1016/j.patrec.2009.02.004Search in Google Scholar

Khezri, M., Jahed, M. (2011). A neuro-fuzzy inference system for sEMG-based identification of hand motion commands. IEEE Trans. Ind. Electron., 58 (5), 1952-1960.10.1109/TIE.2010.2053334Search in Google Scholar

Rafiee, J., Rafiee, M.A., Yavari, F., Schoen, M.P. (2011). Feature extraction of forearm EMG signals for prosthetics. Expert Syst. Appl., 38 (4), 4058-4067.10.1016/j.eswa.2010.09.068Search in Google Scholar

Phinyomark, A., Limsakul, C., Phukpattaranont, P. (2011). Application of wavelet analysis in EMG feature extraction for pattern classification. Meas. Sci. Rev., 11 (2), 45-52.10.2478/v10048-011-0009-ySearch in Google Scholar

Phinyomark, A., Nuidod, A., Phukpattaranont, P. Limsakul, C. (2012). Feature extraction and reduction of wavelet transform coefficients for EMG pattern classification. Electronics and Electrical Engineering, 122 (6), in press.10.5755/j01.eee.122.6.1816Search in Google Scholar

Fukunaka, K. (1990). Introduction to Statistical Pattern Recognition. Academic Press.Search in Google Scholar

Schafer, K.C., Balog, J., Szaniszlo, T., Szalay, D., Mezey, G., Denes, J., Bognar, L., Oertel, M., Takats, Z. (2011). Real time analysis of brain tissue by direct combination of ultrasonic surgical aspiration and sonic spray mass spectrometry. Analytical Chemistry, 83 (20) 7729-7735.10.1021/ac201251sSearch in Google Scholar

Belhumeour, P.N., Hespanha, J.P., Kriegman, D.J. (1997). Eigenfaces vs. fisherfaces: Recognition using class specific linear projection. IEEE Trans. Patt. Anal. Mach. Int., 19 (7), 711-720.Search in Google Scholar

Sakai, M., Kitaoka, N., Takeda, K. (2010). Acoustic feature transformation based on discriminant analysis preserving local structure for speech recognition. IEICE Trans. Inform. Syst., E93D (5), 1244-1252.10.1587/transinf.E93.D.1244Search in Google Scholar

Howland, P., Jeon, M., Park, H. (2003). Structure preserving dimension reduction for clustered text data based on the generalized singular value decomposition. SIAM J. Matrix Anal. Applicat., 25 (1), 165-179.10.1137/S0895479801393666Search in Google Scholar

Jin, Z., Yang, J.Y., Tang, Z.M., Hu, Z.S. (2001). A theorem on the uncorrelated optimal discriminant vectors. Patt. Recog., 34 (10), 2041-2047.10.1016/S0031-3203(00)00135-7Search in Google Scholar

Ye, J. (2005). Characterization of a family of algorithms for generalized discriminant analysis on undersampled problems. Journal of Machine Learning Research, 6, 483-502.Search in Google Scholar

Ye, J., Li, Q. (2004). LDA/QR: An efficient and effective dimension reduction algorithm and its theoretical foundation. Patt. Recog., 37 (4), 851-854.10.1016/j.patcog.2003.08.006Search in Google Scholar

Krzanowski, W.J., Jonathan, P., McCarthy, W.V., Thomas, M.R. (1995). Discriminant analysis with singular covariance matrices: Methods and applications to spectroscopic data. J. Roy. Statist. Soc. Ser. C-Appl. Stat., 44 (1), 101-115.10.2307/2986198Search in Google Scholar

Baudat, G., Anouar, F. (2000). Generalized discriminant analysis using a kernel approach. Neural Comput., 12 (10), 2385-2404.10.1162/08997660030001498011032039Search in Google Scholar

Tao, X., Ye, J., Li, Q., Janardan, R., Cherkassky, V. (2004). Efficient Kernel discriminant analysis via QR decomposition. In NIPS 2004 : 18th Annual Conference on Neural Information Processing Systems, 13-18 December 2004. NIPS, 1529-1536.Search in Google Scholar

Phinyomark, A., Phukpattaranont, P., Limsakul, C., Phothisonothai, M. (2011). Electromyography (EMG) signal classification based on detrended fluctuation analysis. Fluctuation and Noise Lett., 10 (3), 281-301.10.1142/S0219477511000570Search in Google Scholar

Oskoei, M.A., Hu, H. (2008). Support vector machine-based classification scheme for myoelectric control applied to upper limb. IEEE Trans. Biomed. Eng., 55 (8), 1956-1965.10.1109/TBME.2008.91973418632358Search in Google Scholar

Kaufmann, P., Englehart, K., Platzner, M. (2010). Fluctuating EMG signals: Investigating long-term effects of pattern matching algorithms. In Annual Internal Conference of the IEEE Engineering in Medicine and Biology Society, 31 Aug. - 4 Sept. 2010. IEEE, 6357-6360.10.1109/IEMBS.2010.5627288Search in Google Scholar

Geethanjali, P., Ray, K.K. (2011). Identification of motion from multi-channel EMG signals for control of prosthesis hand. Australas. Phys. Eng. Sci. Med., 34 (3), 419-427.10.1007/s13246-011-0079-zSearch in Google Scholar

Du, Y.-C., Lin, C.-H., Shyu, L.-Y., Chen, T. (2010). Portable hand motion classifier for multi-channel surface electromyography recognition using grey relational analysis. Expert Syst. Appl., 37 (6), 4283-4291.10.1016/j.eswa.2009.11.072Search in Google Scholar

Khushaba, R.N., Al-Ani, A., Al-Jumaily, A. (2010). Orthogonal fuzzy neighborhood discriminant analysis for multifunction myoelectric hand control. IEEE Trans. Biomed. Eng., 57 (6), 1410-1419.10.1109/TBME.2009.2039480Search in Google Scholar

Yan, Z., Wang, Z., Xie, H. (2008). Joint application of rough set-based feature reduction and fuzzy LS-SVM classifier in motion classification. Med. Biol. Eng. Comput., 46 (6), 519-527.10.1007/s11517-007-0291-xSearch in Google Scholar

Yan, Z., Wang, Z., Xie, H. (2008). The application of mutual information-based feature selection and fuzzy LS-SVM-based classifier in motion classification. Comput. Method. Program. Biomed., 90 (3), 275-284.10.1016/j.cmpb.2008.01.003Search in Google Scholar

Clancy, E.A., Morin, E.L., Merletti, R. (2002). Sampling, noise-reduction and amplitude estimation issues in surface electromyography. J. Electromyograph. Kinesiol., 12 (1), 1-16.10.1016/S1050-6411(01)00033-5Search in Google Scholar

Naik, G.R., Kumar, D.K., Arjunan, S.P. (2010). Pattern classification of Myoelectrical signal during different Maximum Voluntary Contractions: A study using BSS techniques. Meas. Sci. Rev., 10 (1), 1-6.Search in Google Scholar

Boostani, R., Moradi, M.H. (2003). Evaluation of the forearm EMG signal features for the control of a prosthetic hand. Physiol. Meas., 24 (2), 309-319.10.1088/0967-3334/24/2/30712812417Search in Google Scholar

Phinyomark, A., Phukpattaranont, P., Limsakul, C. (2011). Wavelet-based denoising algorithm for robust EMG pattern recognition. Fluctuation and Noise Lett., 10 (2), 157-167.10.1142/S0219477511000466Search in Google Scholar

Hussain, M.S., Mamun, Md. (2012). Effectiveness of the wavelet transform on the surface EMG to understand the muscle fatigue during walk. Meas. Sci. Rev., 12 (1), 28-33.10.2478/v10048-012-0005-xSearch in Google Scholar

Recommended articles from Trend MD

Plan your remote conference with Sciendo