Abstract

Changes in the normal rhythm of a human heart may result in different cardiac arrhythmias, which may be immediately fatal or cause irreparable damage to the heart sustained over long periods of time. The ability to automatically identify arrhythmias from ECG recordings is important for clinical diagnosis and treatment. Artificial immune systems (AISs) is a new but effective branch of artificial intelligence. Among the systems proposed in this field so far, artificial immune recognition system (AIRS), which was proposed by A. Watkins, has showed an effective and intriguing performance on the problems it was applied. Previously, AIRS was applied a range of problems including machine-learning benchmark problems and medical classification problems like breast cancer, diabets, liver disorders classification problems. The conducted medical classification task was performed for ECG arrhythmia data taken from UCI repository of machine-learning. Firsly, ECG dataset is normalized in the range of [0,1] and is weighted with fuzzy weighted pre-processing. Then, weighted input values obtained from fuzzy weighted pre-processing is classified by using AIRS classifier system. In this study, fuzzy weighted pre-processing, which can be improved by ours, is a new method and firstly, it is applied to ECG dataset. Classifier system consists of three stages: 50–50% of traing-test dataset, 70–30% of traing-test dataset and 80–20% of traing-test dataset, subsequently, the obtained classification accuries: 78.79, 75.00 and 80.77%.

Keywords: ECG arrhythmia; Artificial immune system; AIRS; Fuzzy weighted pre-processing

Article Outline

1. Introduction

2. Background

2.1. ECG arrhythmia classification problem

2.2. Previous research

2.3. Natural and artificial immune systems

3. Method

3.1. AIRS classification algorithm

3.1.1. Initialization

3.1.2. Memory cell identification and ARB generation

3.1.3. Competition for resources and development of a candidate memory cell

3.1.4. Memory cell introduction

3.2. Fuzzy weighted pre-processing

3.3. Used parameters

3.4. Measures for performance evaluation

3.4.1. Classification accuracy

3.4.2. k-fold cross-validation

4. Results and discussion

5. Conclusion

References