Classification of ECG signals using hybrid particle swarm optimization in extreme learning machine

An Electrocardiogram or ECG is an electrical footage of the heart and is used in the investigation of heart disease. This ECG can be classified as normal and abnormal signals. The classification of the ECG signals is currently executed with the extreme learning machine. The generalization performance of the ELM classifier is not adequate for the correct classification of ECG signals. To defeat this difficulty the hybrid Particle Swarm Optimization (PSO) with ELM classifier is used which efforts by searching for the best value of the parameters that tune its discriminant purpose, and upstream by looking for the best subset of features that feed the classifier. The experiments were conducted on the ECG data from the Physionet arrhythmia dataset to classify abnormal waveforms and normal beats. In this research a thorough experimental study was done to prove the advantage of the simplification facility of hybrid PSO-ELM is presented and compared with PSO-ELM approach in the automatic classification of ECG beats. In particular, the sensitivity of the hybrid PSO-ELM classifier is tested and that is compared with standard PSO-ELM with respect to the curse of dimensionality and the number of available training beats. The obtained results clearly confirm the superiority of hybrid approach as compared to traditional classifiers.