Detection of cardiac problems by the extraction of multimodal functions and machine learning techniques

Abstract

The machine learning based model is designed for robustness on the basis of both ECG based HRV analysis and non-ECG based analysis. The goal is to evaluate the efficacy of different machine learning classification models. A statistical analysis is provided with repositories such as MIT / BIH Normal Sinus Rhythm (NSR) and MIT / BIH Atrial Fibrillation (AF) and Peripheral Pule Analyzer. The model was checked on all possible subject conditions, the form of ECG database and the non-ECG signal. The Best Feature was chosen from the various HRV Settings that will be used for classification. In our intra group selection analysis, traditional and well-known machine learning classification techniques, such as Random Forest, Support Vector Machine, K-Nearest Neighbours, Adaptive Boosting, Support Vector Machine. Robustness is driven primarily by precision, flexibility and specificity. The 5 percent higher accuracy band and lower band model are tested. The Random forest has produced better performance and has been tested for its robustness. Testing is carried out for more than 20 indices and more than 40,000 combinations generated and added to the model for study. The efficacy of these classifier-based Intra-Group selection models is tested by performing variety of dataset experiments obtained from standard sets as well as acquired data. Overall experimental findings and discussions will enable all researchers to assess the effect of the features on the model.