Intelligent Identification System for Farming Water Quality Based on Deep Learning
Download as PDF
Lirong He, Jing Su, Baogui Tang, Hancheng Huang, Liang Zeng, Chuangwei Wen
Traditional aquaculture tends to judge water quality based on the experience of the farmer, failing to make effective use of farming data and lacking an intuitive and easy way to observe farming data. To settle the problem, we have developed a farming water quality intelligence identification system using deep learning and popular front and back-end technologies. The system provides digital management for farming data, makes analysis and prediction of water quality data and water color images using deep learning techniques, and visualizes the output of predictions, which helps to aid aquaculture, such as reducing farming risk, increasing the scale of farming and improving farming efficiency.
Deep learning, Aquaculture water quality, Intelligent identification