Line balancing is considered as an unsupervised partitioning method which is an intelligent selforganizing system that partitions the datasets in a comparable or a different way, where each data cluster consists of similar job points. As of late, the scheduling ensemble is regarded as a solution to extract the categorical data points into relevant clusters in a more effective way. However, it encounters a serious problem related to data imperfection during data partitioning into clusters. The present study considers this as the main problem and improves it using following consideration. In this paper presents the ensemble Line balancing over categorical datasets using Particle Swarm Optimization (PSO) based cluster ensemble approach. The similarity measurement is carried out using entropy weighted triple quality to finds the similarity difference between the clusters. The knowledge paradigms including cognitive science and systems are intended to improve the clustering quality over categorical datasets. The result shows that the proposed method is accurate than existing methods over categorical datasets in terms of clustering accuracy, normalized mutual information and adjusted rand. This shows the effectiveness of the PSO ensemble clustering algorithm than the existing link-based clustering ensemble algorithm.
Volume 12 | Issue 3