(Research Article) Classification of Normal and Pathological Heart Signal Variability Using Machine Learning Techniques L. Hussain 1* , W. Aziz 2 , S.A.Nadeem 3 , A. Q. Abbasi 4 1*2,3,4 Department of Computer Science & IT, University of Azad and Kashmir ,Muzaffarabad, PAKISTAN Abstract The guide Heart rate signals provide valuable information for assessing the state of autonomic nervous system that control functioning of heart. Heart rate variability analysis is an important non-invasive tool that has been widely used for assessing autonomic control of heart using linear and non-linear techniques since last three decades. Different methods used to detect these beats include ECG, blood pressure etc. but ECG has great importance because it gives a complete and clear waveform. Heart rate variability analysis is a tool that assesses the autonomic nervous system. It is based on the measurement of changing heart rate signals. In past two decades a large number of research efforts were made and a number of techniques were proposed for heart rate variability. In this study, the techniques used for HRV analysis includes linear (time and frequency domain) and non-linear techniques. We have used different classifiers and their methods to check heart rate variations in healthy cases and diseased cases. Methods showing highest accuracy include Naïve Bayes method of Bayes classifier; sequential minimal optimization (SMO) of functions classifier, lazy locally weighted learning (LWL) method, AdaBoost and logical model tree. Among all these methods LMT (logical model tree) is considered as best method with the accuracy level of 92.5%. In this study 10 folds cross-validation was used as test option. Cross-validation is a technique to assess the accuracy of results where the goal is predicted. In 10 folds cross-validation 10 times repetition occurs and the result is obtained by taking mean accuracy. Keywords: Heart Rate Variability, Classifier, Machine Learning, Sample Entropy, Complexity Analysis. 1. Introduction In this world diseases of heart are responsible for number of deaths. To examine the behavior of heart a lot of techniques and different instruments are made. One of these methods includes the analysis of HRV [1]. HRV analysis means to measure nonlinear, unsteady or changeable signals of heart, particularly variations of heartbeat in per unit time these are known as RR interval (it is the time interval between successive R points of electrocardiogram). It is the measurement of changing heart rate signals. A person presenting large values of HRV is considered as healthy person and that having low HRV values are considered as unhealthy. HRV have been investigated by many techniques but machine learning technique has make up a powerful position. Heart rate signal classification through support vector machine learning is presented in [2]. HRV is chiefly noted for the judgment of cardiac abnormalities. For the valuation of autonomic nervous system and cardiovascular autonomic regulation, the computerized analysis of HRV is a tool. Linear and non-linear parameters as artificial neural networks for arrhythmia classes are described in [3]. North American society of pacing electrophysiology (NASPE) and European society of cardiology (ESC) established rules using time and frequency domains in 1996. Later it was shown by further research that due to complex heart rate vacillation some information remain hidden. For this purpose a non-linear analysis was proposed [4]. Fractal analysis was used for hidden information of heart rate in 1999. Non-linear analysis of HRV may provide precious information for exposition of heart rate vacillation [5]. Effect INTERNATIONAL JOURNAL OF DARSHAN INSTITUTE ON ENGINEERING RESEARCH & EMERGING TECHNOLOGIES Vol. 3, No. 2, 2014 www.ijdieret.in IJDI-ERET * Corresponding Author: e-mail: lall_hussain2008@live.co ISSN 2320-7590  2014 Darshan Institute of Engg. & Tech., All rights reserved