Classification of Normal and Pathological Heart Signal Variability Using Machine Learning Techniques
- Anees Q. Abbasi, University of Azad and Kashmir, Muzaffarabad, Pakistan
- Lal Hussain, University of Azad and Kashmir, Muzaffarabad, Pakistan, firstname.lastname@example.org
- Sajjad A. Nadeem, University of Azad and Kashmir, Muzaffarabad, Pakistan
- Wajid Aziz, University of Azad and Kashmir, Muzaffarabad, Pakistan
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.