Fuzzy clustering and dynamic tables for knowledge discovery and decision-making: Analysis of the reproductive performance of the marine copepod Cyclopina sp.

Abstract The objective of this study was to evaluate the main reproductive aspects of the marine cyclopoid copepod Cyclopina sp. under laboratory conditions and to design, to implement, and to validate a framework for the development of decision system support based on a fuzzy set theory using clusters and dynamic tables. To validate the proposed framework, a fuzzy inference system was developed with the aim to estimate reproductive performance (Juvenile infertility period - JIP, Generational time – GT, Average fertility – AF, Reproductive frequency – RF, Reproductive events number – REN and Longevity - Long) of the marine copepod cyclopina sp. submitted to different thermal water and pH values conditions and compared with other computational intelligence techniques (Artificial Neural Networks models and Adaptive Neuro-Fuzzy Inference System - ANFIS). The results show that the determination coefficients (R2) for the six output variables for the Fuzzy Inference System – FIS were 0.991, 0.996, 1.0, 1.0, 0.999 and 1, respectively. The mean values of the standard deviations were 0.054 days, 0.047 days, 0.037 eggs, 0.061 h, 0.027 reproductive events, and 0.027 days respectively, representing mean percentage errors of 0.782, 0.583, 0.240, 0.181, 1.039, and 0.091%, showing a better accuracy, allowing the prediction of the reproductive performance to be more realistic. The Fuzzy Model produced more accurate predictions than other techniques (ANN and ANFIS). The proposed framework may provide an effective means to draw a pattern to the development of fuzzy systems.