Modified Artificial Bee Colony Optimization with SVM for Optimize the Selection and Classification of Heart Disease

Medical guidance systems make extensive use of machine learning methods. A medical diagnostic aids in obtaining several characteristics that correspond to the various illness variants. It is probable to have redundant, irrelevant, and relevant aspects that reflect a disease with the use of various diagnostic techniques. The illness may be incorrectly classified due to redundant characteristics. Consequently, the amount of the data & computational complexity is decreased by eliminating the superfluous characteristics. Finding a suitable feature subset for efficient classification is a challenging problem. This calls for a thorough search over the dataset's sample space. This paper's primary goal is to identify the best feature subset with higher classification accuracy for the diagnosis of cardiovascular diseases using a metaheuristic algorithm. The best traits for illness detection are found using the Artificial Bee Colony (ABC) method, which is based on swarm intelligence. Support Vector Machine (SVM) categorisation is employed to assess ABC's capability. Dataset of Indian Heart Disease is used to verify the suggested algorithm's performance. According to the experimental findings, ABC-SVM performs well when compared with feature selection via reverse ranking. In addition, the results show that with only eight characteristics, the proposed approach accomplished maximum classification precision.