Abstract
Non-parametric classification procedures based on a certainty measure and nearest neighbour rule for motor unit potential classification (MUP) during electromyographic (EMG) signal decomposition were explored. A diversity-based classifier fusion approach is developed and evaluated to achieve improved classification performance. The developed system allows the construction of a set of non-parametric base classifiers and then automatically chooses, from the pool of base classifiers, subsets of classifiers to form candidate classifier ensembles. The system selects the classifier ensemble members by exploiting a diversity measure for selecting classifier teams. The kappa statistic is used as the diversity measure to estimate the level of agreement between base classifier outputs, i.e., to measure the degree of decision similarity between base classifiers. The pool of base classifiers consists of two kinds of classifiers: adaptive certainty-based classifiers (ACCs) and adaptive fuzzy k-NN classifiers (AFNNCs) and both utilize different types of features. Once the patterns are assigned to their classes, by the classifier fusion system, firing pattern consistency statistics for each class are calculated to detect classification errors in an adaptive fashion. Performance of the developed system was evaluated using real and simulated EMG signals and was compared with the performance of the constituent base classifiers and the performance of the fixed ensemble containing the full set of base classifiers. Across the EMG signal data sets used, the diversity-based classifier fusion approach had better average classification performance overall, especially in terms of reducing classification errors.
Similar content being viewed by others
References
Alexandre LA, Campilho AC, Kamel M (2001) On combining classifiers using sum and product rules. Pattern Recogn Lett 22:1283–1289
Atiya AF (1992) Recognition of multiunit neural signals. IEEE Trans Biomed Eng 39(7):723–729
Chauvet E, Fokapu O, Hogrel J-Y, Gamet D, Duchêne J (2003) Automatic identification of motor unit action potential trains from electromyographic signals using fuzzy techniques. Med Biol Eng Comput 41:646–653
Chi Z, Yan H, Pham T (1996) Fuzzy algorithms: with applications to image processing and pattern recognition, World Scientific, Singapore
Sung-Bae Cho (1997) Neural-network classifiers for recognizing totally unconstrained handwritten numerals. IEEE Trans Neural Netw 8(1):43–53
Cho SB, Kim JH (1995) Combining multiple neural networks by fuzzy integral for robust classification. IEEE Trans Syst Man Cybern 25(2):380–384
Sung-Bae Cho, Kim JH (1995) Multiple network fusion using fuzzy logic. IEEE Trans Neural Netw 6(2):497–501
Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20(2):37–46
Duda RO, Hart PE, Stork DG (2001) Pattern classification, 2nd edn. Wiley, New York
Duin RPW (2002) The combining classifier: to train or not to train? In: Proceedings of the 16th international conference on pattern recognition, vol 2, pp 765–770
Duin RPW, Taz DMJ (2000) Experiments with classifier combining rules. In: Kittler J, Roli F (eds) Multiple classifier systems. Lecture Notes in Computer Science, vol 1857. Springer, Gagliari, pp 16–29
Fang J, Agarwal GC, Shahani BT (1997) Decomposition of EMG signal by wavelet spectrum matching. In: Proceedings of the 19th annual international conference of the IEEE engineering in medicine and biology society, pp 1253–1256
Fang J, Agarwal GC, Shahani BT (1999) Decomposition of multiunit electromyogram signals. IEEE Trans Biomed Eng 46(6):685–697
Farina D, Colombo RA, Merletti R, Olsen HB (2001) Evaluation of intra-muscular EMG signal decomposition algorithms. J Electromyogr Kinesiol 11:175–187
Farina D, Crosetti A, Merletti R (2001) A model for the generation of synthetic intramuscular EMG signals to test decomposition algorithms. IEEE Trans Biomed Eng 48(1):66–77
Fleiss JL, Levin B, Paik MC (2003) Statistical methods for rates and proportions, 3rd edn. Wiley, New York
Giacinto G, Roli F (2001) An approach to the automatic design of multiple classifier systems. Pattern Recogn Lett 22:25–33
Gut R, Moschytz GS (2000) High-precision EMG signal decomposition using communication techniques. IEEE Trans Signal Process 48(9):2487–2494
Hamilton-Wright A, Stashuk DW (2005) Physiologically based simulation of clinical EMG signals. IEEE Trans Biomed Eng 52(2):171–183
Hassoun MH, Wang C, Spitzer R (1994) NNERVE: Neural network extraction of repetitive vectors for electromyography—part i: algorithm. IEEE Trans Biomed Eng 41(11):1039–1052
Hassoun MH, Wang C, Spitzer R (1994) NNERVE: neural network extraction of repetitive vectors for electromyography—part ii: performance analysis. IEEE Trans Biomed Eng 41(11):1053–1061
Ho TK, Hull JJ, Srihari SN (1994) Decision combination in multiple classifier systems. IEEE Trans Pattern Anal Mach Intell 16(1):66–75
Keller JM, Gader P, Tahani H, Chiang J-H,Mohamed M (1994) Advances in fuzzy integration for pattern recognition. Fuzzy Sets Syst 65:273–283
Keller JM, Gray MR, JA Givens JR (1985) A fuzzy k-nearest neighbor algorithm. IEEE Trans Syst Man Cybern 15(4):580–585
Keller JM, Osborn J (1996) Advances in fuzzy integration for pattern recognition. Int J Approxim Reason 15(1):1–24
Kittler JM, Hatef M, Duin RPV, Matas J (1998) On combining classifiers. IEEE Trans Pattern Anal Mach Intell 20(3):955–966
Kuncheva LI, Whitacker CJ (2003) Measure of divesity in classifier ensembles and their relationship with the ensemble accuracy. Mach Learn 51:181–207
Kuncheva LI, Whitaker CJ, Shipp CA, Duin RPW (2001) Is independence good for combining classifiers? In: Proceedings of the 15th international conference on pattern recognition, vol 2, pp 168–171
Lam L (2000) Classifier combinations: implementations and theoretical issues. In: Kittler J, Roli F (eds) Multiple classifier systems. Lecture Notes in Computer Science, vol 1857. Springer, Cagliari, pp 77–86
Lam L, Suen CY (1997) Application of majority voting to pattern recognition: an analysis of its behavior and performance. IEEE Trans Syst Man Cybern Part A Syst Hum 27(5):553–568
LeFever RS, De Luca CJ (1982) A procedure for decomposing the myoelectric signal into its constituent action potentials—part i: technique, theory, and implementation. IEEE Trans Biomed Eng 29(3):149–157
Loudon GH, Jones NB, Sehmi AS (1992) New signal processing techniques for the decompositon of EMG signals. Med Biol Eng Comput 30(11):591–599
De Luca CJ (1989) Reflections on EMG signal decomposition. In: Desmedt JE (ed) Computer-aided electromyography and expert systems. Elsevier, Amesterdam, pp 33–37
McGill KC (1984) A method for quantitating the clinical electromyogram. PhD Dissertation, Stanford University, Stanford
McGill KC, Cummins K, Dorfman LJ (1985) Automatic decomposition of the clinical electromyogram. IEEE Trans Biomed Eng 32(7):470–477
Mikenina L, Zimmermann H-J (1999) Improved feature selectin and classification by the 2-additive fuzzy measure. Fuzzy Sets Syst 107:197–218
Mirfakhraei K, Horch K (1997) Recognition of temporally changing action potentials in multiunit neural recordings. IEEE Trans Biomed Eng 44(2):123–131
Hamid Nawab S, Wotiz R, De Luca CJ (2004) Improved resolution of pulse superpositions in a knowledge-based system EMG decomposition. In: Proceedings of the 26th annual international conference of the IEEE engineering in medicine and biology society, vol 1, pp 69–71
Nikolic M, Sørensen JA, Dahl K, Krarup C (1997) Detailed analysis of motor unit activity. In: Proceedings of the 19th annual international conference of the IEEE engineering in medicine and biology society conference, pp 1257–1260
Paoli GM (1993) Estimating certainty in classification of motor unit action potentials. Master’s Thesis, University of Waterloo, Waterloo
Partridge D, Griffith N (2002) Multiple classifier systems: software engineered, automatically modular leading to a taxonomic overview. Pattern Anal Appl 5:180–188
Perrone MP (1995) Averaging/modular techniques for neural networks. In: Arbib MA (ed) The handbook of brain theory and neural networks. MIT Press, Cambridge, pp 126–129
Pham TD (2002) Combination of multiple classifiers using adaptive fuzzy integral. In: Proceedings of the 6th IEEE international conference on electronics, circuits and systems ICECS ’99, pp 50–55
Pham TD, Yan H (1997) Fusion of handwritten numeral classifiers based on fuzzy and genetic algorithms. In: Proceedings of the 1997 annual meeting of the north american fuzzy information processing society NAFIPS’97, pp 257–262
Qu Y (1993) Automatic clustering of motor unit action potentials using shape and time information. Master’s Thesis, University of Waterloo, Waterloo
Rasheed S (2006) A multiclassifier approach to motor unit potential classification for EMG signal decomposition. PhD Dissertation, URL: http://www.etd.uwaterloo.ca/etd/srasheed2006.pdf, University of Waterloo, Waterloo
Rasheed S, Stashuk D, Kamel M (2004) Multi-classification techniques applied to EMG signal decomposition. In: Proceedings of the 2004 IEEE international conference on systems, man and cybernetics, SMC 04, vol 2, The Hugue, pp 1226–1231
Rasheed S, Stashuk D, Kamel M (2006) Adaptive certainty-based classification for decomposition of EMG signals. Med Biol Eng Comput 44(4):298–310
Rasheed S, Stashuk D, Kamel M (2006) Adaptive fuzzy k-NN classifier for EMG signal decomposition. Med Eng Phys J 28(7):694–709
Roli F, Giacinto G, Vernazza G (2001) Methods for designing multiple classifier systems. In: Kittler J, Roli F (eds) Proceedings of the 2nd international workshop on multiple classifier systems. Lecture Notes in Computer Science, vol 2096. Springer, Heidelberg, pp 78–87
Shipp CA, Kuncheva LI (2002) Relationships between combination methods and measures of diversity in combining classifiers. Inf Fus 3:135–148
Spitzer R, Hassoun MH (1993) NNERVE: neural network extraction of repetitive vectors for electrodiagnosis. In: Proceedings of 6th annual ieee symposium on computer-based medical systems, pp 171–176
Stashuk DW (1999) Decomposition and quantitative analysis of clinical electromyographic signals. Med Eng Phys 21:389–404
Stashuk DW (2001) EMG signal decomposition: how can it be accomplished and used? J Electromyogr Kinesiol 11:151–173
Stashuk DW, de Bruin H (1988) Automatic decomposition of selective needle-detected myoelectric signals. IEEE Trans Biomed Eng 35(1):1–10
Stashuk DW, Paoli GM (1998) Robust supervised classification of motor unit action potentials. Med Biol Eng Comput 36(1):75–82
Stashuk DW, Qu Y (1996) Adaptive motor unit action potential clustering using shape and time information. Med Biol Eng Comput 34(1):41–49
Stashuk DW, Qu Y (1996) Robust method for estimating motor unit firing-pattern statistics. Med Biol Eng Comput 34(1):50–57
Sugeno M (1974) Theory of fuzzy integrals and its applications. PhD Dissertation, Tokyo Institute of Technology, Tokyo
Sugeno M (1977) Fuzzy measures and fuzzy integrals—a survey. In: Fuzzy Automata and Decision Processes. North-Holland, Amsterdam, pp 89–102
Tahani H, Keller JM (1990) Information fusion in computer vision using the fuzzy integral. IEEE Trans Syst Man Cybern 20(3):733–741
Usaui S, Amidror I (1982) Digital low-pass differentiation for biological signal processing. IEEE Trans Biomed Eng 29(10):686–693
Wanas N (2003) Feature based architecture for decision fusion. PhD Dissertation, University of Waterloo, Waterloo
Wang D, Wang X, Keller JM (1997) Determining fuzzy integral densities using a genetic algorithm for pattern recognition. In: Proceedings of the 1997 Annual Meeting of the North American Fuzzy Information Processing Society NAFIPS ’97, pp 21–24
Zennaro D, Wellig P, Koch VM, Moschytz GS, Läubli T (2003) A software package for the decomposition of long-term multi-channel EMG signals using wavelet coefficients. IEEE Trans Biomed Eng 50(1):58–69
Zennaro D, Wellig P, Moschytz GS, Läubli T, Krueger H (2001) A decomposition software package for the decomposition of long-term multi-channel electromyographic signals. In: Proceedings of the 23th annual international conference of the IEEE engineering in medicine and biology society, Turkey, pp 1070–1073
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Rasheed, S., Stashuk, D.W. & Kamel, M.S. Diversity-based combination of non-parametric classifiers for EMG signal decomposition. Pattern Anal Applic 11, 385–408 (2008). https://doi.org/10.1007/s10044-008-0103-4
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-008-0103-4