Classification of ECG Signals Using Particle Swarm Optimization and Extreme Learning Machine

The ECG is one of the mainly effective investigative tools to detect cardiac diseases. It is a technique to calculate and record dissimilar electrical potentials of the heart. The electrical potential generated by electrical action in cardiac tissue is calculated on the surface of the human body. Present flow, in the variety of ions, signals reduction of cardiac muscle fibers important to the heart's pumping action. This ECG can be classified as standard and abnormal signals. In this work, a systematic experimental study was conducted to demonstrate the advantage of the generalization capability of the Particle Swarm Optimization Extreme Learning Machine (PSO-ELM) compared with Extreme Learning Machine (ELM) approach in the automatic classification of ECG beats. The simplificationpresentation of the ELM classifier has not attained the nearest maximum accuracy of ECG signal classification. To attain the maximum accuracy the PSO-ELM classifier design by searching for the best value of the parameters that tune it’sdistinguish function, and upstream by looking for the best subset of features that feed the classifier. The experiments were conducted on the ECG data from the Massachusetts Institute of Technology?Beth Israel Hospital (MIT? BIH) arrhythmia database to categorize five kinds of abnormal waveforms and normal beats. In particular, the sensitivity of the PSO-ELM classifier is tested and that is compared with ELM. The attained results clearly confirm the superiority of the PSO-ELM approach when compared to ELM classifiers.