Intelligent Diagnosis of Fish Behavior Using Deep Learning Method

Scientific methods are used to monitor fish growth and behavior reduce the loss caused by stress other circumstances. Conventional techniques time-consuming, labor-intensive, prone accidents. Deep learning (DL) technology is rapidly gaining popularity in various fields, including aquaculture. Moving towards smart farming necessitates precise accurate identification of biodiversity. Observing real time imperative make better feeding decisions. The proposed study consists an efficient end-to-end convolutional neural network (CNN) classifying into normal starvation categories. performance CNN evaluated varying number fully connected (FC) layers with or without applying max-pooling operation. accuracy detection algorithm increased 10% incorporating three FC max pooling results demonstrated that shallow architecture model, which employs a function more layers, exhibits promising achieves 98% accuracy. presented system novel step laying foundation for automated modern farming.