RAHİME CEYLAN

Intelligent Systems and Applications in Engineering Advanced Technology and Science

Feature extraction that is detection of effective features is one of the phases of biomedical signal classification. In feature extraction phase, the detection of features that increase performance of classification is very important in terms of diagnosis of disease. Due to this reason, the using of an effective algorithm for feature extraction increases classification accuracy and also it decreases processing time of classifier. In this study, two well-known dictionary-learning algorithms are used to extract features of ECG signals. The features of ECG signals are extracted by using Method of Optimal Direction (MOD) and K-Singular Value Decomposition (K-SVD). However, the extracted features are classified by Artificial Neural Network (ANN). Twelve different ECG signal classes which taken from MIT-BIH ECG Arrhythmia Database are used. When the obtained results are examined, it is seen that performance of classifier increases in usage of K-SVD for feature extraction. The highest classification accuracy is obtained as 98.74% with 5 nonzero elements in [20 1] feature vector, while K-SVD is used in feature extraction phase. The obtained results are assessed by comparing with the results obtained when discrete wavelet transform and principal component analysis are used

PDF

___

[1] F. Castells, P. Laguna, L. Sörnmo, A. Bollmann, J.M. Roig, “Principal Component Analysis in ECG Signal Processing”, EURASIP Journal on Advances in Signal Processing, vol.2007, Article ID:74580.

[2] A. Sharma, T. Sharma, “ECG Beat Recognition using Principal Components Analysis and Artificial Neural Network”, International Journal of Electronics Engineering, vol.3(1), pp.55-58, 2011.

[3] S.N. Yu, K.T. Chou, “Combining Independent Component Analysis and Backpropagation Neural Network for ECG Beat Classification”, Proceedings of the 28th IEEE EMBS Annual International Conference, New York City, USA, Aug-2008.

[4] T. Punithavalli, S. Sindhu, “PCA and SVD based feature reduction for cardiac arrhythmia classification”, International Journal of Engineering research and Technology, vol.3(9), September, 2014.

[5] M.F. Shinwari, N. Ahmed, H. Humayun, I. Haq, S. Haider, A. Anam, “Classification Algorithm for Feature Extraction using Linear Discriminant Analysis and Cross-correlation on ECG Signals”, International Journal of Advanced Science and Technology, vol.48, November, 2012.

[6] Q. Zhao, L. Zhang, “ECG Feature Extraction and Classification Using Wavelet Transform and Support Vector Machines”, International Conference on Neural Networks and Brain (ICNN&B’05), 13-15 Oct-2005.

[7] S.Z. Mahmoodabadi, A. Ahmedian, M.D.Abolhasani, “ECG Feature Extraction Using Daubechies Wavelets”, International Conference Visualization, Imaging and Image Processing, 7-9 September, 2005, Spain.

[8] T. Liu, Y. Si, D. Wen, M. Zang, L. Lang, “Dictionary Learning for VQ feature extrction in ECG beats classification”, Expert Systems with Applications, Vol.53, pp.129-137, July, 2016.

[9] A. Kar, L. Das, “A Technical Review on Statistical Feature Extraction of ECG Signal”, IJCA Special Issue on Computing, Communication and Sensor Network, CCSN2011.

[10] S.J. Lee, J. Luan, P.H. Chou, “A New Approach to Compressing ECG Signals with Trained Overcomplete Dictionary”, International Conference on Wireless Mobile Communication and Healthcare (Mobilhealth), 2014.

[11] M. Balouchestani, L. Sugavaneswaran, S. Krishan, “Advanced K-means Clustering Algorithm for Large ECG Data Sets Based on K-SVD Approach”, International Symposium on Communication Systems, Networks and Digital Sign, 2014.

[12] S.M. Mathews, “Leveraging Discriminative Dictionary Learnng Algorithms for Single Lead ECG Classification”, PhD Thesis, 2015.

[13] I. Kalaji, K. Balasundaram, K. Umapathy, “Discriminative Sparse Coding of ECG During Ventricular Arrhythmias Using LC-K-SVD Approach”, IEEE Eng Med Biol Soc, EMBC-2015.

[14] K. Engan, S. O. Aase, J. H. Husoy, “Method of Optimal Directions for Frame Design”, IEEE International Conference on Acoustic, Speech and Signal Processing, pp.2443-2446, 1999.

[15] K. Engan, S. O. Aase, J. H. Husey, “Designing Frames for Matching Pursuit Algorithms”, ICASSP’98, pp.1817-1820, May 1998, Seattle-USA.

[16] Emrah Yavuz, “Dictionary design for sparse representation of signal”, Master Thesis, İstanbul Technical University, Natural Science Institute, 2011.

[17] Özden Bayır, “Dictionary Learning Algorithm for Synthesis Sparsity and Image Processing Applications”, Master Thesis, İstanbul Technical University, Natural Science Institute, 2015.

[18] M. Elad, M. Aharon, “Image Denoising via Sparse and Redundant Representations Over Learned Dictionaries”, IEEE Transactions on Image Processing, vol.15, no.12, pp. 3736-3745, December 2016.

[19] C. Rusu, B. Dumitrescu, “Stagewise K-SVD to Design Efficient Dictionaries for Sparse Representations”, IEEE Signal Processing Letters, vol.19, no.10, pp. 631-634, October, 2013.

[20] Y. Tang, Y. Shen, A. Jiang, N. Xu, C. Zhu, “Image Denoising via Graph Regularized K-SVD”, IEEE International Symposium on Circuits and Systems(ISCAS), 2013.

[21] Physionet Database, Access time: April-2017.

[22] R. Ceylan, “A telecardiology system design using feature extraction techniques and artificial neural network”, PhD Thesis, Selcuk University, Natural Science Institute, 2009.

[23] G. M. Friesen, T. C. Jannett, M. A. Jadallah, S. L. Yates, S. R. Quint, H. T. Nagle, “A Comparison of the Noise Sensitivity of Nine QRS Detection Algorithms”, IEEE Transactions on Biomedical Engineering, vol.37, no.1, 1990.