Akademik Veri Yönetim Sistemi
International Journal of Data Science and Analytics, cilt.20, sa.6, ss.5499-5516, 2025 (ESCI)
This study examines the use of multi-objective optimization and decision-making methods for optimizing parameter values in biclustering algorithms to analyse complex relationships in large datasets. The non-dominated sorting genetic algorithm-II (NSGA-II) optimization algorithm and technique for order preference by similarity to ideal solution (TOPSIS) method were applied to enhance the performance of these biclustering algorithms in fields such as bioinformatics and genetic analysis. Analyses of both synthetic and real datasets demonstrated that selecting and fine-tuning biclustering algorithms according to the structure of the data substantially improves the accuracy of the analysis. Applications on real data highlighted the capability of biclustering algorithms to model intricate relationships between cellular processes in biological data analysis. The results indicate that the NSGA-II algorithm integrated with the TOPSIS method is effective in identifying the optimal parameters. Additionally, future studies are encouraged to explore the applicability of these algorithms with various datasets and evaluation criteria to further enhance adaptability. This research underscores the potential of biclustering methods to provide robust and adaptable solutions, particularly in bioinformatics and across a range of other scientific domains.