THE CLASSIFICATION OF FOREARM ELECTROMYOGRAPHIC SIGNALS FOR MULTIFUNCTION PROSTHESIS HAND CONTROL

Yıl 2015, Cilt: 17 Sayı: 49, 35 - 46, 01.01.2015

Erkan Zeki Engin Deniz Taşan Mehmet Engin

Öz

Pattern recognition based prosthesis hand control algorithms have largely been used to produce artificial hand for handicapped people. This paper was investigated four classifiers (linear discriminant analysis, k-nearest neighbor, nearest neighbor and k-means) for multi-functional (six forearm movement: hand open, hand close, wrist flexion, wrist extension, ulnar deviation, and radial deviation) hand control by using EMG signals from forearm muscles. In training and testing of classifiers, EMG signal based RMS, variance, wavelet-based entropy, and zero-crossing rate features were used. As a result, linear discriminant analysis classifier has shown maximum accuracy for all subjects (%94,68 ± 3,96) and movements (%94,68 ± 3,58)

Anahtar Kelimeler

EMG, feature extraction, classifier, prosthesis hand

ÇOK İŞLEVLİ PROTEZ EL KONTROLÜ İÇİN ÖNKOL ELEKTROMİYOGRAFİ İŞARETLERİNİN SINIFLANDIRILMASI

Öz

Örüntü tanıma tabanlı el kontrol algoritmaları, özürlü kişiler için yapay el üretmek amacı ile kullanılmaktadır. Bu çalışmada; önkol kaslarındaki EMG (ElektroMiyoGrafi) işaretlerini kullanarak, çok işlevli (altı önkol hareketi: el açık, el kapalı, bileği bükme, bilek uzatma, dirsek sapma ve açısal sapma) el kontrolü için dört sınıflandırıcı (doğrusal ayrım analizi, k-en yakın komşuluğu, en yakın komşuluk ve k-ortalama) incelenmiştir. Sınıflandırıcıların eğitim ve testinde, EMG işareti tabanlı etkin değer, varyans, dalgacık tabanlı entropi ve sıfır geçiş oranı öznitelikleri kullanılmıştır. Sonuç olarak, doğrusal ayırma analizi sınıflandırıcısı tüm denekler (%94,68 ± 3,96) ve hareketler (%94,68 ± 3,58) için en fazla doğruluk göstermiştir

Anahtar Kelimeler

EMG, öznitelik çıkartımı, sınıflandırıcı, protez el

Kaynakça

• Chereon G, Draye JP, Bourgeios M, Libert G. “A Dynamic Neural Identification of Electromyogram and Arm Trajectory Relationship During Complex Movements”, IEEE Transactions on Biomedical Engineering, Cilt 43, s. 552-558, 1996.
• Englehart K, Hudgins B, Parker PA. “A Wavelet-based Continuous Classification Scheme for Multifunction Myoelectric Control”, IEEE Transactions on Biomedical Engineering, Cilt 48, s. 302-311, 2001.
• Chan FHY, Yang YS, Lam FK, Zhang YT, Parker PA. “Fuzzy EMG Classification for Prosthesis Control”, IEEE Transactions on Rehabilitation Engineering, Cilt 8, s. 305-311, 2000.
• Wojtczak P, Amaral TG, Dias OP, Wolczowski A, Kurzynski M. “Hand movement recognition based on biosignal analysis”, Engineering Applications of Artificial Intelligence, Cilt 22, s. 608–615, 2009.
• Khushaba RN, Kodagoda S, Takruri M, Dissanayake G. “Toward improved control of prosthetic fingers using surface electromyogram (EMG) signals”, Expert Systems with Applications, Cilt 39, s. 10731–10738, 2012.
• Zardoshti-Kermani M, Wheeler BC, Badie K, Hashemi RM. “EMG Feature Evalution for Movement Control of Upper Extremity Prosthesis”, IEEE Transactions on Rehabilitation Engineering, Cilt 3, s. 324-333, 1995.
• Englehart K, Hudgins B, Parker PA, Stevenson M. “Classification of the Myoelectric Signal Using Time-frequency Based Representations”, Medical Engineering & Physics, Cilt 21, s. 431-438, 1999.
• Chu JU, Maon I, Muu MS. “A Real-time EMG Pattern Recognition System Based on Linear and Non-linear Feature Projection for a Multifunction Myoelectric Hand”, IEEE Transactions on Biomedical Engineering, Cilt 53, s. 2232-2239, 2006.
• Xing K, Yang P, Huang J, Wang Y, Zhu Q. “A real-time EMG pattern recognition method for virtual myoelectric hand control”, Neurocomputing, Cilt 136, s. 345–355, 2014.
• Hoehn L, Niven I. “Averages on the Move”, Math. Mag., Cilt 58, s. 151-156, 1985.
• Rangayyan RM. Biomedical Signal Analysis: A Case-Study Approach, IEEE Press, NJ, 2004.
• Boostani R, Moradi MH.“Evaluation of the Forearm EMG Signal Features for the Control of a Prosthetic Hand”, Physiological Measurement, Cilt 24, s. 309-319, 2003.
• Engin M. “ECG Beat Classification Using Neuro-fuzzy Network”, Pattern Recogntion Letters, Cilt 25, s. 1715-1722, 2004.
• Thakor NV. “Multiresolution Wavelet Analysis of Evoked Potentials”, IEEE Transactions on Biomedical Engineering, Cilt 40, s. 1085-1093, 1993.
• Al-Nashash HA, Thakor NV. “Monitoring of Global Cerabral Ischmia Using Wavelet Entropy Rate of Change”, IEEE Transactions on Biomedical Engineering, Cilt 52, s. 2119- 2122, 2005.
• Yordano J, Kolev V, Rosso OA, Schürmann M, Sakowitz OW, Özgören M, Basar E. “Wavelet Entropy Analysis of Event-related Potentials Indicates Modality-independent Theta Dominance”, Journal of Neuroscience Methods, Cilt 117, s. 99-109, 2002.
• Ong S, Sridharan S, Yang CH, Moody MP. “Comparison of Four Distance Measures for Long Time Text-independant Speaker Identification”, International Symposium on Signal Processing and Its Applications – ISSPA, s. 369-372, 1996.
• Schaal S, Atkeson C. From Isolation to Cooperation: An Alternative View of a System of Experts In: D.S. Touretzky, M.C. Mozer, M.E. Hasselmo, eds., Advances in Neural Information Processing Systems, Cambridge: MIT Press, 1996.
• Duda RO, Hart PE, Stork DG. Pattern Classification, John Wiley & Sons Inc., 2001.