Yıl 2019,
Cilt: 31 Sayı: 2, 443 - 451, 27.09.2019
Ali Arı
,
Furkan Ayaz
Davut Hanbay
Kaynakça
- [1] V. K. Mishra, V. Bajaj, A. Kumar, D. Sharma, and G. K. Singh (2017). An efficient method for analysis of EMG signals using improved empirical mode decomposition. AEU - Int. J. Electron. Commun., 72, 200–209.[2] A. Subasi (2012). Classification of EMG signals using combined features and soft computing techniques. Appl. Soft Comput. J., vol. 12, no. 8, pp. 2188–2198.[3] A. Subasi (2013). Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput. Biol. Med., vol. 43, no. 5, pp. 576–586.[4] R. N. Khushaba, A. Al-Timemy, S. Kodagoda, and K. Nazarpour (2016). Combined influence of forearm orientation and muscular contraction on EMG pattern recognition. Expert Syst. Appl., vol. 61, pp. 154–161, 2016.[5] V. Bajaj, Y. Guo, A. Sengur, S. Siuly, and O. F. Alcin (2017). A hybrid method based on time–frequency images for classification of alcohol and control EEG signals. Neural Comput. Appl., vol. 28, no. 12, pp. 3717–3723.[6] Ö. F. Ertuğrul, Y. Kaya, and R. Tekin (2015). A novel approach for SEMG signal classification with adaptive local binary patterns. Med. Biol. Eng. Comput., pp. 1137–1146.[7] S. M. Mane, R. A. Kambli, F. S. Kazi, and N. M. Singh (2015). Hand motion recognition from single channel surface EMG using wavelet & artificial neural network. Procedia Comput. Sci., vol. 49, no. 1, pp. 58–65.[8] Shie Qian and Dapang Chen (1999). Joint time-frequency analysis. IEEE Signal Process. Mag., vol. 16, no. 2, pp. 52–67.[9] L. Cohen (1995). Time-frequency Analysis.[10] B. S. Shaik, G. V. S. S. K. R. Naganjaneyulu, T. Chandrasheker, and A. V. Narasimhadhan (2015). A Method for QRS Delineation Based on STFT Using Adaptive Threshold. Procedia Comput. Sci., vol. 54, pp. 646–653.[11] A. Ari and D. Hanbay (2016). Detection of Brain Tumor from the MR Images by Using Hybrid Features. International Conference on Natural Science and Engineering (ICNASE’16).[12] C. Zhao, S. Qiao, J. Sun, R. Zhao, and W. Wu (2016). Sparsity-based shrinkage approach for practicability improvement of H-LBP-based edge extraction. Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 825, pp. 1–5.[13] Y. Kaya, Ö. F. Ertugrul, and R. Tekin (2015). Two novel local binary pattern descriptors for texture analysis. Appl. Soft Comput. J., vol. 34, pp. 728–735.[14] A. Şengür, Y. Guo, and Y. Akbulut (2016). Time–frequency texture descriptors of EEG signals for efficient detection of epileptic seizure. Brain Informatics, vol. 3, no. 2, pp. 101–108.[15] P. M. Arabi, G. Joshi, and N. Vamsha Deepa (2016). Performance evaluation of GLCM and pixel intensity matrix for skin texture analysis. Perspect. Sci., vol. 8, pp. 203–206.[16] R. M. Haralick and K. Shanmugam (1973), Textural Features for Image Classification. IEEE Trans. Systems, Man, and Cybernetics, 3, 610-621.[17] L. K. Soh and C. Tsatsoulis (1999). Texture analysis of sar sea ice imagery using gray level co-occurrence matrices. IEEE Trans. Geosci. Remote Sens., vol. 37, no. 2 I, pp. 780–795.[18] M. C. Colak, C. Colak, H. Kocatürk, S. Sağiroğlu, and I. Barutçu (2008). Predicting coronary artery disease using different artificial neural network models. Anadolu Kardiyol. Derg., vol. 8, no. 4, pp. 249–54.[19] D. Hanbay, I. Turkoglu, and Y. Demir (2010). Modeling switched circuits based on wavelet decomposition and neural networks. J. Franklin Inst., vol. 347, no. 3, pp. 607–617.[20] C. Sapsanis, G. Georgoulas, A. Tzes, and D. Lymberopoulos (2013). Improving EMG based classification of basic hand movements using EMD. Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, pp. 5754–5757.[21] C. Sapsanis (2013). Recognition of basic hand movements using electromyography. 2013.
EMG Sinyallerinin Kısa Zamanlı Fourier Dönüşüm Özellikleri Kullanılarak Yapay Sinir Ağları ile Sınıflandırılması
Yıl 2019,
Cilt: 31 Sayı: 2, 443 - 451, 27.09.2019
Ali Arı
,
Furkan Ayaz
Davut Hanbay
Öz
EMG sinyali kasların kasılması sırasında oluşan elektriksel aktivasyonun ölçülmesi işlemidir. EMG sinyali, kasların nöral aktivasyonu ve dinamikleri hakkında bilgi sağlamaktadır. Bu nedenle EMG sinyallerinin işlenmesi; sinir hastalıkları teşhisi, protez cihazlar ve insan makine etkileşiminde olmak üzere birçok alanda giderek daha etkin olarak kullanılmaya başlanmıştır. Özellikle EMG sinyallerinden hareket tespiti ve EMG sinyallerinin sınıflandırılması bu çalışmalar için önem teşkil etmektedir. Bu amaçla yapılan çalışmada EMG sinyallerinden hareket tespiti yapılması amaçlanmıştır. İlk olarak 6 farklı harekete ait EMG sinyalleri alınmış ve bu sinyallere Kısa Zamanlı Fourier Dönüşümü (KZFD) uygulanmış ve sinyaller Zaman-Frekans (Z-F) düzleminde gösterilmiştir. Daha sonra bu Z-F gösterimlerinden öznitelik çıkarmak amacıyla gösterimler bölütlenmiş ve her bir pencereye ait istatistiksel öznitelikler, Yerel İkili Örüntü (YİÖ) değerleri ve Gri Seviye Eş oluşum Matrisi (GSEM) hesaplanarak EMG sinyaline ait öznitelikler çıkartılmıştır. Çıkarılan bu öznitelikler Yapay Sinir Ağı (YSA) ile sınıflandırılmış ve sistemin başarımı ölçülmüştür. Sistemin doğruluk başarımı ortalama %92 olarak hesaplanmıştır.
Kaynakça
- [1] V. K. Mishra, V. Bajaj, A. Kumar, D. Sharma, and G. K. Singh (2017). An efficient method for analysis of EMG signals using improved empirical mode decomposition. AEU - Int. J. Electron. Commun., 72, 200–209.[2] A. Subasi (2012). Classification of EMG signals using combined features and soft computing techniques. Appl. Soft Comput. J., vol. 12, no. 8, pp. 2188–2198.[3] A. Subasi (2013). Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput. Biol. Med., vol. 43, no. 5, pp. 576–586.[4] R. N. Khushaba, A. Al-Timemy, S. Kodagoda, and K. Nazarpour (2016). Combined influence of forearm orientation and muscular contraction on EMG pattern recognition. Expert Syst. Appl., vol. 61, pp. 154–161, 2016.[5] V. Bajaj, Y. Guo, A. Sengur, S. Siuly, and O. F. Alcin (2017). A hybrid method based on time–frequency images for classification of alcohol and control EEG signals. Neural Comput. Appl., vol. 28, no. 12, pp. 3717–3723.[6] Ö. F. Ertuğrul, Y. Kaya, and R. Tekin (2015). A novel approach for SEMG signal classification with adaptive local binary patterns. Med. Biol. Eng. Comput., pp. 1137–1146.[7] S. M. Mane, R. A. Kambli, F. S. Kazi, and N. M. Singh (2015). Hand motion recognition from single channel surface EMG using wavelet & artificial neural network. Procedia Comput. Sci., vol. 49, no. 1, pp. 58–65.[8] Shie Qian and Dapang Chen (1999). Joint time-frequency analysis. IEEE Signal Process. Mag., vol. 16, no. 2, pp. 52–67.[9] L. Cohen (1995). Time-frequency Analysis.[10] B. S. Shaik, G. V. S. S. K. R. Naganjaneyulu, T. Chandrasheker, and A. V. Narasimhadhan (2015). A Method for QRS Delineation Based on STFT Using Adaptive Threshold. Procedia Comput. Sci., vol. 54, pp. 646–653.[11] A. Ari and D. Hanbay (2016). Detection of Brain Tumor from the MR Images by Using Hybrid Features. International Conference on Natural Science and Engineering (ICNASE’16).[12] C. Zhao, S. Qiao, J. Sun, R. Zhao, and W. Wu (2016). Sparsity-based shrinkage approach for practicability improvement of H-LBP-based edge extraction. Nucl. Instruments Methods Phys. Res. Sect. A Accel. Spectrometers, Detect. Assoc. Equip., vol. 825, pp. 1–5.[13] Y. Kaya, Ö. F. Ertugrul, and R. Tekin (2015). Two novel local binary pattern descriptors for texture analysis. Appl. Soft Comput. J., vol. 34, pp. 728–735.[14] A. Şengür, Y. Guo, and Y. Akbulut (2016). Time–frequency texture descriptors of EEG signals for efficient detection of epileptic seizure. Brain Informatics, vol. 3, no. 2, pp. 101–108.[15] P. M. Arabi, G. Joshi, and N. Vamsha Deepa (2016). Performance evaluation of GLCM and pixel intensity matrix for skin texture analysis. Perspect. Sci., vol. 8, pp. 203–206.[16] R. M. Haralick and K. Shanmugam (1973), Textural Features for Image Classification. IEEE Trans. Systems, Man, and Cybernetics, 3, 610-621.[17] L. K. Soh and C. Tsatsoulis (1999). Texture analysis of sar sea ice imagery using gray level co-occurrence matrices. IEEE Trans. Geosci. Remote Sens., vol. 37, no. 2 I, pp. 780–795.[18] M. C. Colak, C. Colak, H. Kocatürk, S. Sağiroğlu, and I. Barutçu (2008). Predicting coronary artery disease using different artificial neural network models. Anadolu Kardiyol. Derg., vol. 8, no. 4, pp. 249–54.[19] D. Hanbay, I. Turkoglu, and Y. Demir (2010). Modeling switched circuits based on wavelet decomposition and neural networks. J. Franklin Inst., vol. 347, no. 3, pp. 607–617.[20] C. Sapsanis, G. Georgoulas, A. Tzes, and D. Lymberopoulos (2013). Improving EMG based classification of basic hand movements using EMD. Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, pp. 5754–5757.[21] C. Sapsanis (2013). Recognition of basic hand movements using electromyography. 2013.