Evolving optimal fuzzy-connective-based hierarchical aggregation networks using genetic algorithms

Chao Ton Su, Fang Fang Wang, Taho Yang

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)


Multilayer fuzzy connective-based hierarchical aggregation networks provide a flexible and intuitive approach to decision analysis. This approach simulates the decision making processes performed by humans, and the results can be interpreted as a set of rules with which to fashion an abstract model of the problem. Identifying the relative importance of the criteria helps to identify redundancies that do not contribute to the decision-making process. However, a gradient-based learning approach tends to generate local solutions, and requires the aggregation function to be continuous and differentiable. This study proposes a GA-based learning approach to identify the connective parameters, exploiting the global exploration ability of GAs to improve the quality of solutions. This approach does not require gradient information, making it applicable to both differentiable and nondifferentiable aggregation functions. The benefits of this method were demonstrated using eight datasets with different characteristics. Statistical analysis of the experimental results confirms that the proposed approach outperforms the gradient-based learning approach, generating more accurate estimates for both generalized mean and gamma operators. The proposed approach is well suited to a broad range of fuzzy aggregation connectives, which further expands its applicability.

Original languageEnglish
Pages (from-to)617-631
Number of pages15
JournalInternational Journal of Innovative Computing, Information and Control
Issue number1 B
Publication statusPublished - 2012 Jan

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Computational Theory and Mathematics


Dive into the research topics of 'Evolving optimal fuzzy-connective-based hierarchical aggregation networks using genetic algorithms'. Together they form a unique fingerprint.

Cite this