Clustering Method Analysis for Gene Expression Data using Fire Fly Optimization and Simple K-means Algorithm with Machine Learning

Data mining is an endeavor to identify patterns, correlations, similarities, and links among massive datasets in order to uncover hidden, intriguing information. The goal of clustering is to arrange data sets that share similar attributes into groups, or clusters. The gene data are enormous, complex, and contain information on gene expression simultaneously, making it difficult to manage the unmanageable amount of data. The massive volume of data makes cluster analysis and interpretation difficult. Self-organizing maps are thought to be a helpful method for evaluating and visualizing high dimensional gene data for machine learning algorithms. An instrument for the best cluster mining in gene samples is the Firefly algorithm. This approach helps to improve visualization and suggests a fresh angle for identifying reliable clusters from the massive amounts of gene expression data. The results of this work yield the most accurate and optimal clusters from the large gene data sets.