Enhancing Arrhythmia Disease Classification Using MLP with Whale Optimization Approach

Cardiac arrhythmias are a serious health danger. Thus, timely diagnosis and treatment depend on precise and effective categorization techniques. The paper addresses the implementation of Multilayer Perceptron (MLP) in conjunction with Whale Optimization-based feature selection, Particle Swarm Optimization (PSO), and Antlion Optimizer (ALO) for the categorization of Atrial Fibrillation (AFib) illnesses. Key performance indicators, including Accuracy, precision, and recall, will be examined to determine whether MLP using Whale Optimization for feature selection works better than conventional techniques. The results indicate that the suggested strategy dramatically improves the classification performance compared to established methods based on thorough experimentation and comparative analysis. The combination of MLP and Whale Optimization-based feature selection exhibits excellent recall, Accuracy, and precision and is a viable option for reliable AFib illness categorization. From the results obtained, the proposed MLP+WO gave an Accuracy of 90.74 % and precision and recall of 0.90 and 0.88, respectively. The language used is Python.