Regression Heuristics by Optimal Tridimensional Features of Electrocardiogram for Arrhythmia Detection
S.Aarathi1, S. Vasundra2
1S. Aarathi, Reasearch Scholar, Department of Computer Science and Engineering, JNTUA, CEA Anantapuramu (Andra Pradesh), India.
2Dr. S. Vasundra, Professor, Department of Computer Science and Engineering, JNTUA, CEA Anantapuramu (Andra Pradesh), India.
Manuscript received on 25 November 2019 | Revised Manuscript received on 19 December 2019 | Manuscript Published on 30 December 2019 | PP: 147-158 | Volume-9 Issue-1S5 December 2019 | Retrieval Number: A10361291S52019/19©BEIESP | DOI: 10.35940/ijeat.A1036.1291S519
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Computer aided predictive analytics are vital in noncommunicable diseases. In particular, early diagnosis of arrhythmia (heart related disease) is crucial to prevent sudden deaths due to heart failure. The critical context to prevent deaths caused by arrhythmia is early prediction of the arrhythmia scope. The clinical experts widely consider the Electro Cardio Gram (ECG) report as primary parameter to scale the scope of arrhythmia. However, the diagnosis accuracy of clinical experts is highly correlate on their expertise. Unlike the other domains, the sensitivity that is the accuracy in disease-prone is very much crucial in clinical practices. Particularly, the accuracy and sensitivity are more vital in computer-aided heart disease prediction methods. Hence, the recent research contributions are quantifying the possibilities of optimizing machine-learning approaches to achieve significance in computer-aided methods to perform predictive analysis on arrhythmia detection. Regarding this context, this manuscript is defining a Regression Heuristics by Tridimensional Features of the electrocardiogram reports, which has intended to perform arrhythmia prediction. The experimental study evincing the significance of the proposed model that scaled against the contemporary methods.
Keywords: Predictive Analytics, Machine Learning, Electrocardiogram, Feature Optimization, Linear Regression, Classification.
Scope of the Article: Regression and Prediction