[01] Irshad Khalil, Department of Computer Science, University of Malakand, Lower Dir, Khyber Pakhtunkhwa, Pakistan. [02] Adnan Khalil, Department of Computer Science, University of Malakand, Lower Dir, Khyber Pakhtunkhwa, Pakistan. [03] Sami Ur Rehman, Department of Computer Science, University of Malakand, Lower Dir, Khyber Pakhtunkhwa, Pakistan. [04] Hammad Khalil, Department of Mathematics, University of Malakand, Khyber Pakhtunkhwa, Pakistan. [05] Rahmat Ali Khan, Dean Faculty of Science, Department of Mathematics, University of Malakand, Lower Dir, Khyber Pakhtunkhwa, Pakistan. [06] Fakhre Alam, Department of Computer Science, University of Malakand, Lower Dir, Khyber Pakhtunkhwa, Pakistan.

During the last few decades, a huge amount of work is devoted to the study of classification techniques of Electrocardiogram (ECG) signals. In this paper, we present a robust algorithm based on shifted Legendre polynomials. These polynomials are successfully implemented to extract features from ECG signals. The ECG signals are first decomposed into its sub band using Legendre polynomials in specific time interval. The objective of the study is to classify two different types of ECG signals. We test two different classifier, KNN and simple logistic. A comparative study is presented on the behaviour and results of these classifiers. Experimental results are obtained for both classifiers and compared with some other results available in the open literature. The experimental results lead us to conclusion that the proposed method provides more accurate results as compare to other classification methods.

ECG Signals, Simple Logistic Classifier, Legendre Polynomials, KNN Classifier

[01] K. Balasundaram, S. Masse, K. Nair, K. Umapathy, A classification scheme for ventricular arrhythmias using wavelets analysis, Medical & biological engineering & computing, 51 (1-2) (2013), 153--164. [02] S. N. Yu, Y. H. Chen, Electrocardiogram beat classification based on wavelet transformation and probabilistic neural network, Pattern Recognition Letters, 28 (10) (2007), 1142--1150. [03] M. Thomas, M. K. Das, S. Ari, Classification of cardiac arrhythmias based on dual tree complex wavelet transform, Communications and Signal Processing (ICCSP), 2014 International Conference on, IEEE, 2014, 729--733. [04] S. Kadambe, P. Srinivasan, Adaptive wavelets for signal classification and compression, International Journal of Electronics and Communications, 60 (1) (2006), 45--55. [05] R. J. Martis, U. R. Acharya, K. Mandana, A. K. Ray, C. Chakraborty, Application of principal compo-nent analysis to ECG signals for automated diagnosis of cardiac health, Expert Systems with Applications, 39 (14) (2012), 11792--11800. [06] H. G. Hosseini, K. Reynolds, D. Powers, A multi-stage neural network classier for ECG events, Engineering in Medicine and Biology Society, (2001) 1672--1675. [07] P. De Chazal, M. O. Dwyer, R. B. Reilly, Automatic classification of heartbeats using ECG morphology and heartbeat interval features, Biomedical Engineering, IEEE Transactions, 51 (7) (2004), 1196--1206. [08] A. Ebrahimzadeh, A. Khazaee, An efficient technique for classification of electrocardiogram signals, Advances in Electrical and computer engineering, 9 (3)(2009). [09] N. Emanet, ECG beat classification by using discrete wavelet transform and random forest algorithm. DOI: 10.1109/ICSCCW.2009.5379457, (2009). [10] M. A. Fayyaz, A. Afsar, Robust electrocardiogram beat classification using discrete wavelet transform, Bioinformatics and Biomedical Engineering, ICBBE, 16-18( 2008), 1867--1870. [11] B. N. Dhannoon, L. E. George, Color image compression using polynomial and quad tree coding techniques, International Journal of Scientific & Engineering Research, 4(11) (2013), 11--20. [12] H. Zhang, et al. Blurred image recognition by Legendre moment invariants, Image Processing, IEEE Transactions, 19(3) (2010), 596--611. [13] K. M. Hosny, Exact Legendre moment computation for gray level images, Pattern Recognition, 40 (12)(2007), 3597--3605. [14] K. M. Hosny, Rened translation and scale Legendre moment invariants, Pattern Recognition Letters, 31 (7) (2010), 533--538. [15] K. M. Hosny, Efficient computation of Legendre moment for gray level images, International Journal of Image and Graphics, 7 (4) (2007), 735--747. [16] K. M. Hosny, Robust template matching using orthogonal Legendre moment invariants, Journal of computer science, 6 (10) (2010), 10--83. [17] K. M. Hosny, G. Papakostas, D. E. Koulouriotis, Accurate reconstruction of noisy medical images using orthogonal moments, Digital Signal Processing (DSP), 2013, 18th International Conference, IEEE ( 2013) 1--6. [18] H. Khalil, R. A. Khan, A new method based on Legendre polynomials for solutions of the fractional two-dimensional heat conduction equation, Computer and Mathematics with application, 67 (10)(2014), 1938--1953. [19] H. Khalil, R. A. Khan, M. M. Rashidi, Brenstein polynomials and its application to fractional differential equations, Computational methods for differential equations, 2015. [20] H. Khalil, R. A. Khan, A new method based on legendre polynomials for solution of system of fractional order partial differential equations, International Journal of Computer Mathematics, 91 (12)(2014), 2554--2567. [21] H. Khalil, R. A. Khan, The use of Jacobi polynomials in the numerical solution of coupled system of fractional differential equations, International Journal of Computer Mathematics, 92 (7)(2014), 1452-1472. [22] A. Azemi, V. R. Sabzevari, M. Khademi, H. Gholizade, A. Kiani, Z. S. Dastgheib, Intelligent arrhythmia detection and classification using ICA, Engineering in Medicine and Biology Society, 2006, 28th Annual International Conference of the IEEE, 2006, 2163--2166. [23] R. O. Duda, P. E. Hart, D. G. Stork, Pattern classification, John Wiley & Sons, 2012.