Classification of ECG Signals By the Neighborhood Feature Extraction Method

In this study, non-linear dimension reduction methods were applied to ECG signals and success of such dimension reduction techniques for the classification and segmentation of ECG signals were discussed. Also, segmentation of data through neighbourhood feature extraction (NFE) method were enabled by transiting from high dimensioned space to low dimension space by considering the longitudinal combination of ECG signals. Results classification results of NFE algorithm performed through longitudinal combination and as a newly developed method were compared with classification results of ECG signals obtained through dimension reduction by taking one pixel. Results of NFE dimension reduction technique performed by considering the neighbour pixels, advantage of effect on segmentation of ECG signals were presented at empirical results section and the success of suggested method was indicated. Results obtained by performed study are promising for the studies to be conducted in further period.

Keywords:

classification, ECG, kNN, Neighbourhood Feature Extraction RBF,

PDF

___

[1] Kiranyaz S., Ince T. etc, “Personalized long-term ECG classification: A systematic approach”, Expert Systems with Applications, vol.38, issue 4, pp.3220-3226, 2011. [2] Erdoğmuş P., Peşçaker A., “Dalgacık Dönüşümü ile EKG Sinyallerinin Özellik Çıkarımı ve Yapay Sinir Ağları ile Sınıflandırılması”, 5.Uluslararası İleri Teknolojiler Sempozyumu (IATS’09), 2009. [3] Martis R., Acharya R. And Min L., “ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform”, Elseiver Biomedical Sifnal Processing and Control, vol.8, issue 5, pp.437-448, 2013. [4] Ceylan R.,Ozbay Y., “Comparison of FCM, PCA and WT techniques for classification ECG arrhytmias using neural network, Expert Systems with Applications, vol.33, issue 2, pp.286-295, 2007. [5] Bakir C., “Nonlinear Feature Extraction for Hyperspectral Images”, International Conference on Advanced Technology & Sciences (ICAT’14), pp.945-949, 2014. [6] Silipo R., Bortolan G. And Marchesi C., “Design of hybrid architectures based on neural RBF pre-processing for ECG analysis”, International Journal of Approximate Reasoning, pp.177-196, 1999. [7] Castillo O., Melin P. ETC, “Hybrid intelligent system for cardiac arrhythmia classification with Fuzzy K-Nearest Neighbors and neural networks combined with a fuzzy system”, Expert Systems with Applications, vol.39, issue 3, pp.2947-2955, 2012. [8] Maglaveras N., Stamkopolous T. etc, “ECG pattern recognition and classification using nonlinear transformations and neural networks:A review”, Medical Informatics, vol.52, issue 1-3, pp.191-208, 1998. [9] Wen Y., He L. And Shi P., “Face recognition using difference vector plus KPCA”, Digital Signal Processing, vol.22, issue 1, pp.140-146, 2012. [10] Widjaja D., Varon C.etc, “Application of Kernel Principal Component Analysis for Single-Lead-ECG-Derived Respiration”, IEEE Transactions on Biomedical Engineering, vol.59, no.4, pp.1169-1176, 2012. [11] Shalbaf A., Alizadefsani Z. And Behram H. “Echocardiography without electrocardiagram using nonlinear dimensionality reduction methods”, J.Med Ultrasonics, vol.42, pp.137-149, 2015. [12] Perry T., Zha H. etc, “Supervised Laplacian Eigenmaps with Applications in Clinical Diagnostics for Pediatric Cardiology”, Computer Science & Learning, 2012. [13] Vozda M., Cerny M., “Methods for derivation of orthogonal leads from 12-lead electrocardiogram:A review”, Biomedical