Open AccessHeart Disease Prediction and Classification Using Machine Learning Algorithms Optimized by Particle Swarm Optimization and Ant Colony Optimization
Author(s) -
Lalit and Mantosh Kumar Aditya
Publication year - 2020
Publication title -
international journal of modern trends in science and technology
Language(s) - English
Resource type - Journals
ISSN - 2455-3778
DOI - 10.46501/ijmtst061282
Subject(s) - ant colony optimization algorithms , particle swarm optimization , artificial intelligence , support vector machine , computer science , machine learning , random forest , feature selection , naive bayes classifier , artificial neural network , robustness (evolution) , algorithm , pattern recognition (psychology) , data mining , biochemistry , chemistry , gene
The prediction of heart disease is one of the areas where machine learning can be implemented. Optimizationalgorithms have the advantage of dealing with complex non-linear problems with a good flexibility andadaptability. In this paper, we exploited the Fast Correlation-Based Feature Selection (FCBF) method to filterredundant features in order to improve the quality of heart disease classification. Then, we perform aclassification based on different classification algorithms such as K-Nearest Neighbour, Support VectorMachine, Naïve Bayes, Random Forest and a Multilayer Perception | Artificial Neural Network optimized byParticle Swarm Optimization (PSO) combined with Ant Colony Optimization (ACO) approaches. The proposedmixed approach is applied to heart disease dataset; the results demonstrate the efficacy and robustness ofthe proposed hybrid method in processing various types of data for heart disease classification. Therefore,this study examines the different machine learning algorithms and compares the results using differentperformance measures, i.e. accuracy, precision, recall, f1-score, etc. A maximum classification accuracy of99.65% using the optimized model proposed by FCBF, PSO and ACO. The results show that the performanceof the proposed system is superior to that of the classification technique presented above.