A new parallel metaheuristic optimization algorithm and it's application in CDM

Abstract

An evidential comprehension and the substantial insights to analyze the clinical data has the maximum level of significance in the clinical decision-making (CDM) process. Many DM researchers have proven clustering methods are efficient, in looking up worthwhile critical information by describing important data classes. Finding optimized structuresof real-complex data is a challenging task. Parallel metaheuristic algorithms are getting more popularin solving high-dimensional and complex problems because of their upgraded performance. In this work a new parallel metaheuristic optimization algorithm is proposed by hybridizing WOA with Clonal selection algorithm (CSA). Comparable investigations are conducted on 23 standard mathematical benchmark function. Simulation results confirm, with statistical significance, that the proposed scenario is more efficient in finding optimized solutions for complex functions. In addition to this, we exploit the proposed technique to a clinical dataset of heart patient, which is taken from https://archive.ics.uci.edu to secure the optimized structures for predicting heart disease. Four evaluationmetrics Accuracy, Precision, Recall, and Fmeasureare used to compare with those from other methods published in heart disease prediction. The experimental results show that the proposed technique is very competitive for predicting heart disease.