Application of fuzzy inference engine as an automatic switch between ensembles of clustering methods

An automatic switch between ensembles of clustering algorithms is proposed as a part of the Bibliographic Big Data Retrieval System by utilizing a fuzzy inference engine as a decision support tool to select the fastest performing clustering algorithm between fuzzy c-means clustering, Newman-Girvan clustering, and the combination of both. It aims to realize the best clustering performance with the reduction of computational complexity from 0(n³) to 0(n). The automatic switch is developed a fuzzy logic controller written in Java and the experimental results demonstrates that the combination of both clustering algorithms is selected as the best performing algorithm in 7 out of 9 cases with the highest percentage of 90.50%, completed in 161 seconds and the individual clustering algorithms were selected once each with the Newman-Girvan algorithm at 84.85% in 152 seconds and the self-adapted fuzzy c-means at 67.54% in 259 seconds. The automatic switch is to be incorporated into the Bibliographic Big Data Retrieval System that focuses on visualization of fuzzy relationship using hybrid approach combining fuzzy c-means and Newman-Girvan algorithm, planning to be released to the public through the Internet.