Fast Parallel SVM based Arrhythmia Detection on Multiple GPU Clusters

Regression analysis and classification can be done using a supervised learning technique called Support Vector Machine (SVM) which is one of many such methods. The method creates hyperplanes which are used to analyze data patterns and separate data into multiple classes. The computation complexity of the algorithm is very high for training and testing of large multidimensional datasets. In this work, we propose a scalable and cost-effective method to run SVM that reduces memory usage and computing power. The process uses distributed cloud GPU’s cluster nodes to run the algorithm in parallel on data which is divided into "n" parts. The results obtained from each of the cluster nodes are merged on a master node and the SVM algorithm is applied once more for classification. The study tackles the ECG classification using parallel SVM to investigate heartbeats and brain traces linked with different types of Arrhythmia and Seizure. Experiments performed on real ECG datasets (MIT BIH Diagnostic database and EEG Seizure database) resulted in a classification accuracy of 97.45%. The technique is proven both efficient by reducing training time and with high classification accuracy. The results achieved show that the proposed technique outperforms similar methods proposed in previous literature.