An Accurate Weight Classification System for Live Fishes

This study seeks to establish a live fish weight classification system utilizing artificial intelligence (AI) and the Internet of Things (IoT) to enhance the efficiency of conventional fishing practices, alleviate labor demands, and decrease fish mortality rates. The implementation of sliding scale weighing technology facilitates the consistent capture of live fish and allows for weight categorization in accordance with consumer requirements and breeding efficiency. As fish attain a specific size, their rate of weight gain diminishes, which adversely affects economic returns. Furthermore, smaller fish within the same aquatic environment may not receive adequate nourishment to sustain growth, leading to financial losses for aquaculture producers. Fish that achieve the designated weight can be dispatched to avert waste associated with prolonged breeding, while those that fall short of the standard will continue to be cultivated. This system employs sliding scale weight grading technology to mitigate excessive size disparities within a single batch of fish, thereby bolstering the competitive edge of aquaculture operators. The system integrates various live fish weight classification devices via the Internet of Things, facilitating data collection for storage in a database, and enabling the analysis and consolidation of output information from the equipment. This production data is compiled and made available to the proprietors, which can enhance overall shipping efficiency and minimize inaccuracies in manual data collection.