Modelling an Effectual Glowworm Swarm Optimization Strategy for Feature Selection in Heart Disease Prediction
R.Gomathi1, R.Ramprashath2, P.Murugeswari3, A.Jeyachitra4

1R.Gomathi, Assistant Professor, Department of Master of Computer Applications of Karpagam College of Engineering, Coimbatore.
2R. Ramprashath, Assistant Professor, Karpagam College of Engineering, Coimbatore.
3P.Murugeswari, M.Sc., Assistant Professor, G.T.N Arts College, Dindigul.
4A.Jeyachitra, M.C.A.,M.Phil ., Assistant professor, G.T.N Arts College, Dindigul.

Manuscript received on April 02, 2020. | Revised Manuscript received on April 18, 2020. | Manuscript published on May 30, 2020. | PP: 500-505 | Volume-9 Issue-1, May 2020. | Retrieval Number: A1392059120/2020©BEIESP | DOI: 10.35940/ijrte.A1392.059120
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Heart disease is measured as a common disease all over the world. The ultimate target is to provide heart disease diagnosis with improved feature selection with Glow worm swarm optimization algorithm. The anticipated model comprises of optimization approach for feature selection and classifier for predicting heart disease. This system framework comprises of three stages: 1) data processing, 2) feature selection using IGWSO approach and classification with conventional machine learning classifiers. Here, C4.5 classifier is considered for performing the function. The benchmark dataset that has been attained from UCI database was cast off for performing computation. Maximal classification accuracy has been achieved based on cross validation strategy. Outcomes depicts that performance of anticipated model is superior in contrary to other models. Simulation has been done with MATLAB environment. Metrics like accuracy, sensitivity, specificity, F-measure and recall has been evaluated. 
Keywords: Heart disease, Glowworm swarm optimization, C4.5 classifier, Feature selection, Cross validation
Scope of the Article: Classification