An evolutionary chimp-based chimp-based metaheuristic of data clustering with intelligent learning system applications

The importance of data clustering is importance in assisting the decision-making process in any given complex system especially in an environment where data is large-scale and high-dimensional and heterogeneous. This paper introduces an evolutionary adaptation of the Chimp Optimization Algorithm (EVCHOA) to enhance the quality and strength of clustering when applied to the real world. The suggested solution implements an adaptive evolutionary update mechanism into the chimp-inspired search process to increase the exploration-exploitation ratio and avoid the early convergence. The effectiveness of EVCHOA in practice can be illustrated with references to intelligent learning systems, where the use of clustering allows analyzing the information about student performance and assisting in the making of individual decisions. Tests are done on real-life datasets implemented in a distributed computing framework and the outcomes are resolved against known methods of clustering, such as K-means, DBSCAN, hierarchical clustering, mean shift, and Gaussian mixture models. The evaluation of performance is based on conventional validity indices including DaviesBouldin Index, Silhouette Score, Adjusted Rand Index (ARI) and CalinskiHarabasz Index. The findings indicate that EVCHOA always achieves better clustering performance resulting in more coherent group structures and better interpretability by decision-makers. Within the framework of intelligent learning environments, the offered approach allows identifying student profiles more accurately, interfering with the target intervention, distributing resources in a more adaptive manner, and may support data-informed instructional planning. It is evident in these results that evolutionary metaheuristics is a useful tool in the operational research field and provides data-driven and scalable solutions to decision support in a variety of application fields.