Veri Madenciliği Süreç Modeli ile El Hareketlerinin Myoelektrik Kontrolü

Öz

Yüzey elektromiyogram (EMG) sinyali, zengin motor kontrol bilgilerini içeren bir non-ninvaziv ölçümdür. Myoelektrik sinyal olarak da adlandırılan bu sinyaller, Myoelektrik kontrol olarak bilinen güç protez kontrolü için önemli bir girdidir. Bu sinyaller durağan olmayan bir yapıya sahiptir. Bu nedenle bu sinyallerden anlamlı bir bilgi keşfi yapmak için iyi bir analiz yöntemine ihtiyaç vardır. Bu çalışmada, bu amaç için veri madenciliği tekniklerini kullanan bir karar destek sistemi geliştirilmiştir. Veri madenciliği metodolojisi olarak Çapraz Endüstri Standart Süreci (CRISP-DM) yaklaşımı kullanılmıştır. Veri hazırlama aşamasında entropi tabanlı öznitelikler kullanıldı. 8 kanal EMG sinyallerinin kullanıldığı çalışmada her kanaldan 8 entropi tabanlı öznitelik elde edildi. Modelleme aşamasında etkili ve hızlı bir sınıflandırma algoritması olan destek vektör makinesi (DVM) kullanılmıştır. Performans değerlendirme aşamasında sınıflandırma doğruluğu, kappa istatistik değeri, ortalama mutlak hata ve kök ortalama kare hatası ölçütleri kullanıldı. Deneysel sonuçlar, önerilen yöntem ile elde edilen sonuçların literatürdeki yöntemlerden daha iyi sonuçlar verdiğini göstermektedir. Geliştirilen bu sistem, ilgili alandaki uzman kişilere yardımcı olabilecek bir karar destek sistemi olarak kullanılabilir.

Anahtar Kelimeler: Veri madenciliği, karar destek sistemleri, myoelektrik kontrol, EMG sınıflandırma, CRISP-DM modeli

Anahtar Kelimeler

• Veri madenciliği, myoelektrik kontrol, EMG sınıflandırma, CRISP-DM modeli

Myoelectric Control of Hand Movements Using Data Mining Process Model

Öz

Surface electromyography (EMG) signal is a noninvasive measurement with rich motor control information. These signals which are also called as Myoelectric signal, is an important input for power prostheses control known as myoelectric control. These signals have non-stationary structure. Therefore, a good analysis method is required to make a meaningful knowledge discovery. In this study, a decision support system which uses data mining techniques has been developed for this purpose. Cross Industry Standard Process for Data Mining (CRISP-DM) approach has been used as data mining methodology. Entropy-based features have been used during data preparation stage. In the study in which 8-channel EMG signals are used, 8 entropy-based features have obtained from each channel. Support vector machine which is a fast and effective classification algorithm has used in the modeling phase. Classification accuracy, kappa statistic value, mean absolute error (MAE) ve root square mean error (RMSE) have been used in performance evaluation stage. Experimental results show that the results obtained with the proposed method are better than the results obtained with the methods in the literature. The developed system can be used as a decision support system that could help to the experts in related field.

Anahtar Kelimeler

• Data mining,myoelectric control,EMG classification,CRISP-DM model

Kaynakça

1. Bandt, C., & Pompe, B. (2002). Permutation Entropy: A Natural Complexity Measure for Time Series. Phys. Rev. Lett., 88(17), 174102. http://doi.org/10.1103/PhysRevLett.88.174102
2. Bronzino, J. D., & Peterson, D. R. (2015). The Biomedical Engineering Handbook, Fourth Edition: Four Volume Set (4 edition). Boca Raton, FL: CRC Press.
3. Cameron, J. R., & Skofronick, J. G. (1978). Medical Physics (1 edition). New York: Wiley.
4. Carreño, I. R., & Vuskovic, M. (2007). Wavelet Transform Moments for Feature Extraction from Temporal Signals. In J. Filipe, J.-L. Ferrier, J. A.
5. Cetto, & M. Carvalho (Eds.), Informatics in Control, Automation and Robotics II (pp. 235–242). Dordrecht: Springer Netherlands. Retrieved from http://dx.doi.org/10.1007/978-1-4020-5626-0_28
6. Chan, A. D. C., & Green, G. C. (2007). G:Myoelectric control development toolbox. In In Conference of the CanadianMedical & Biological Engineering Society. Toronto;
7. Chan, F. H., Yang, Y. S., Lam, F. K., Zhang, Y. T., & Parker, P. A. (2000). Fuzzy EMG classification for prosthesis control. IEEE Transactions on Rehabilitation Engineering : A Publication of the IEEE Engineering in Medicine and Biology Society, 8(3), 305–311.
8. Clifton, C. (2014, November 28). data mining | computer science. Retrieved April 8, 2016, from http://global.britannica.com/technology/data-mining

9. Coifman, R. R., & Wickerhauser, M. V. (1992). Entropy-based algorithms for best basis selection. IEEE Transactions on Information Theory, 38(2), 713–718. http://doi.org/10.1109/18.119732
10. Cortes, C., & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20(3), 273–297. http://doi.org/10.1023/A:1022627411411
11. Du, S., & Vuskovic, M. (2004). Temporal vs. spectral approach to feature extraction from prehensile EMG signals. In Proceedings of the 2004 IEEE International Conference on Information Reuse and Integration, 2004. IRI 2004 (pp. 344–350). http://doi.org/10.1109/IRI.2004.1431485
12. Englehart, K., Hudgin, B., & Parker, P. A. (2001). A wavelet-based continuous classification scheme for multifunction myoelectric control. IEEE Transactions on Biomedical Engineering, 48(3), 302–311. http://doi.org/10.1109/10.914793
13. Englehart, K., & Hudgins, B. (2003). A robust, real-time control scheme for multifunction myoelectric control. IEEE Transactions on Bio-Medical Engineering, 50(7), 848–854. http://doi.org/10.1109/TBME.2003.813539
14. Geethanjali, P., & Ray, K. K. (2011). Identification of motion from multi-channel EMG signals for control of prosthetic hand. Australasian Physical & Engineering Sciences in Medicine / Supported by the Australasian College of Physical Scientists in Medicine and the Australasian Association of Physical Sciences in Medicine, 34(3), 419–427. http://doi.org/10.1007/s13246-011-0079-z
15. Geethanjali, P., & Ray, K. K. (2013). Statistical Pattern Recognition Technique For Improved Real-time Myoelectric Signal Classification. Biomedical Engineering: Applications, Basis and Communications, 25(02), 1350026. http://doi.org/10.4015/S1016237213500269
16. Hannaford, B., & Lehman, S. (1986). Short Time Fourier Analysis of the Electromyogram: Fast Movements and Constant Contraction. IEEE Transactions on Biomedical Engineering, BME-33(12), 1173–1181. http://doi.org/10.1109/TBME.1986.325697
17. Huang, H.-P., Liu, Y.-H., & Wong, C.-S. (2003). Automatic EMG feature evaluation for controlling a prosthetic hand using supervised feature mining method: an intelligent approach. In Robotics and Automation, 2003. Proceedings. ICRA ’03. IEEE International Conference on (Vol. 1, pp. 220–225 vol.1). http://doi.org/10.1109/ROBOT.2003.1241599
18. Hudgins, B., Parker, P., & Scott, R. N. (1993). A new strategy for multifunction myoelectric control. IEEE Transactions on Bio-Medical Engineering, 40(1), 82–94. http://doi.org/10.1109/10.204774
19. Karlsson, S., Yu, J., & Akay, M. (2000). Time-frequency analysis of myoelectric signals during dynamic contractions: a comparative study. IEEE Transactions on Biomedical Engineering, 47(2), 228–238. http://doi.org/10.1109/10.821766
20. Khushaba, R. N., Al-Ani, A., & Al-Jumaily, A. (2010). Swarm Based Fuzzy Discriminant Analysis for Multifunction Prosthesis Control. In F. Schwenker & N. Gayar (Eds.), Artificial Neural Networks in Pattern Recognition: 4th IAPR TC3 Workshop, ANNPR 2010, Cairo, Egypt, April 11-13, 2010. Proceedings (pp. 197–206). Berlin, Heidelberg: Springer Berlin Heidelberg. Retrieved from http://dx.doi.org/10.1007/978-3-642-12159-3_18
21. Khushaba, R. N., Al-Jumaily, A., & Al-Ani, A. (2009). Evolutionary fuzzy discriminant analysis feature projection technique in myoelectric control. Pattern Recognition Letters, 30(7), 699 – 707. http://doi.org/http://dx.doi.org/10.1016/j.patrec.2009.02.004
22. Khushaba, R. N., AlSukker, A., Al-Ani, A., Al-Jumaily, A., & Zomaya, A. Y. (2009). A novel swarm based feature selection algorithm in multifunction myoelectric control. Journal of Intelligent & Fuzzy Systems, 20(4-5), 175–185. http://doi.org/10.3233/IFS-2009-0426
23. Kiguchi, K., Esaki, R., Tsuruta, T., Watanabe, K., & Fukuda, T. (2003). An exoskeleton for human elbow and forearm motion assist. In Intelligent Robots and Systems, 2003. (IROS 2003). Proceedings. 2003 IEEE/RSJ International Conference on (Vol. 4, pp. 3600–3605 vol.3). http://doi.org/10.1109/IROS.2003.1249714
24. Liu, J. (2015). Adaptive myoelectric pattern recognition toward improved multifunctional prosthesis control. Medical Engineering & Physics, 37(4), 424 – 430. http://doi.org/http://dx.doi.org/10.1016/j.medengphy.2015.02.005
25. Merletti, R., Bottin, A., Cescon, C., Farina, D., Gazzoni, M., Martina, S., …
26. Enck, P. (2004). Multichannel surface EMG for the non-invasive assessment of the anal sphincter muscle. Digestion, 69(2), 112–122. http://doi.org/10.1159/000077877
27. Momen, K., Krishnan, S., & Chau, T. (2007). Real-time classification of forearm electromyographic signals corresponding to user-selected intentional movements for multifunction prosthesis control. IEEE Transactions on Neural Systems and Rehabilitation Engineering : A Publication of the IEEE Engineering in Medicine and Biology Society, 15(4), 535–542. http://doi.org/10.1109/TNSRE.2007.908376
28. Naik, G. R., Kumar, D. K., & Jayadeva. (2010). Twin SVM for Gesture Classification Using the Surface Electromyogram. IEEE Transactions on Information Technology in Biomedicine, 14(2), 301–308. http://doi.org/10.1109/TITB.2009.2037752
29. Oskoei, M. A., & Hu, H. (2008). Support Vector Machine-Based Classification Scheme for Myoelectric Control Applied to Upper Limb. IEEE Transactions on Biomedical Engineering, 55(8), 1956–1965. http://doi.org/10.1109/TBME.2008.919734
30. Özmen, G., Özbay, Y., & Ekmekçi, A. H. (2014). EMG sinyallerinde kas yorgunluğunun YSA ile sınıflandırılması (pp. 279–282). Presented at the Tıp Teknolojileri Ulusal Kongresi, Kapadokya.
31. Parker, P., Englehart, K., & Hudgins, B. (2006). Myoelectric signal processing for control of powered limb prostheses. Journal of Electromyography and Kinesiology : Official Journal of the International Society of Electrophysiological Kinesiology, 16(6), 541–548. http://doi.org/10.1016/j.jelekin.2006.08.006
32. Peleg, D., Braiman, E., Yom-Tov, E., & Inbar, G. F. (2002). Classification of finger activation for use in a robotic prosthesis arm. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 10(4), 290–293. http://doi.org/10.1109/TNSRE.2002.806831
33. PhD, R. A. R., & Tanner, G. A. (2003). Medical Physiology (Second edition). Philadelphia: LWW.
34. Pincus, S. M. (1991). Approximate entropy as a measure of system complexity. Proceedings of the National Academy of Sciences of the United States of America, 88(6), 2297–2301.
35. Rekhi, N. S., Arora, A. S., Singh, S., & Singh, D. (2009). Multi-Class SVM Classification of Surface EMG Signal for Upper Limb Function. In Bioinformatics and Biomedical Engineering , 2009. ICBBE 2009. 3rd International Conference on (pp. 1–4). http://doi.org/10.1109/ICBBE.2009.5163093
36. Rényi, A. (1961). On Measures of Entropy and Information. In Proceedings of the Fourth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Contributions to the Theory of Statistics (pp. 547–561). Berkeley, Calif.: University of California Press. Retrieved from http://projecteuclid.org/euclid.bsmsp/1200512181
37. Richman, J. S., & Moorman, J. R. (2000). Physiological time-series analysis using approximate entropy and sample entropy. American Journal of Physiology. Heart and Circulatory Physiology, 278(6), H2039–2049.
38. Rodriguez-Carreño, I., & Vuskovic, M. (2005). Wavelet-Based Feature Extraction from Prehensile EMG Signals. In NBC. Sweden.
39. Rosso, O. A., Blanco, S., Yordanova, J., Kolev, V., Figliola, A., Schürmann,
40. M., & Başar, E. (2001). Wavelet entropy: a new tool for analysis of short duration brain electrical signals. Journal of Neuroscience Methods, 105(1), 65 – 75. http://doi.org/http://dx.doi.org/10.1016/S0165-0270(00)00356-3
41. Santa-Cruz, M. C., Riso, R., & Sepulveda, F. (2001). Optimal selection of time series coefficients for wrist myoelectric control based on intramuscular recordings. In Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE (Vol. 2, pp. 1384–1387 vol.2). http://doi.org/10.1109/IEMBS.2001.1020458
42. Shannon, C. E., & Weaver, W. (1964). The Mathematical Theory of Communication (First Edition). Urbana: University of Illinois Press.
43. Shearer, C. (2000). The CRISP-DM Model: The new blueprint for data mining. Journal of Data Warehousing, 5(4), 13–22.
44. Vuskovic, M., & Du, S. (2006). Marko Vuskovic and Sijiang Du Spectral Moments for Feature Extraction from Temporal Signals Spectral Moments for Feature Extraction from Temporal Signals.
45. Yazama, Y., Fukumi, M., Mitsukura, Y., & Akamatsu, N. (2003). Feature analysis for the EMG signals based on the class distance. In Computational Intelligence in Robotics and Automation, 2003. Proceedings. 2003 IEEE International Symposium on (Vol. 2, pp. 860–863 vol.2). http://doi.org/10.1109/CIRA.2003.1222292