Automatic Data Clustering Framework Using Nature-Inspired Binary Optimization Algorithms

Cluster analysis using metaheuristic algorithms has earned increasing popularity over recent years due to the great success of these in finding high-quality clusters complex real-world problems. This paper proposes a novel framework for automatic data clustering with capability generating approximately same maximum distortion nature-inspired binary optimization algorithms. The inherent problem such is having huge search space. Therefore, we have also proposed encoding scheme particle representation alleviate this problem. solution requires no prior knowledge number and proceed process based on re-clustering, merging, modifying small compensate gap between groups different sizes. framework's performance been evaluated wide range synthetic, real-life, higher dimensional datasets first by considering four optimizer module. Then, it compared multiple classical new solutions two other techniques continuous space terms separation compactness utilizing internal validity measures. experimental results show highly efficient creating well-separated compact most datasets. Moreover, application correlated dataset reported as case study. presence correlation from similarity points category, repeated measurements remote sensing, crowdsourced multi-view video uploading, augmented reality. Simplicity, customizability, flexibility adding extra conditions dynamic are advantages framework.