Optimizing Fish Feeding with FFAUNet Segmentation and Adaptive Fuzzy Inference System

Abstract

Efficient and optimized fish-feeding practices are crucial for enhancing productivity and sustainability in aquaculture. While many studies have focused on classifying fish-feeding intensity, there is a lack of research on optimizing feeding, necessitating a precise and automated model. This study fills this gap with a hybrid solution for precision aquaculture feeding management involving segmentation and optimization phases. In the segmentation phase, we used the novel feature fusion attention U-Net (FFAUNet) to accurately segment fish-feeding intensity areas. The FFAUNet achieved impressive metrics: a mean intersection over union (mIoU) of 89.39%, a mean precision of 95.07%, a mean recall of 95.08%, a mean pixel accuracy of 95.12%, and an overall accuracy of 95.61%. In the optimization phase, we employed an adaptive neuro-fuzzy inference system (ANFIS) with a particle swarm optimizer (PSO) to optimize feeding. Extracting feeding intensity percentages from the segmented output, the ANFIS with PSO achieved an accuracy of 98.57%, a sensitivity of 99.41%, and a specificity of 99.53%. This model offers fish farmers a robust, automated tool for precise feeding management, reducing feed wastage and improving overall productivity and sustainability in aquaculture.