Edge Computing Based Smart Aquaponics Monitoring System Using Deep Learning in IoT Environment

This research presents an approach to automatic control of the aquaponics system using an autoML algorithm to improve plant and fish growth and help monitor the system using a cloud platform. Is the process of growing plants and fishes maintain an equilibrium in the system is of importance. Hence water-rich with the organic waste of fishes from the fish tank is fed to plants that utilize this water's organic nutrients for growth. The perforated water from the plants is sent back to fishes; thus, recycling the organic water and consume less water than traditional agricultural practice. A miniature model was developed in this research paper using different sensors like DHTII, BH1750, soil moisture, HC-SR04, and pH. The sensors reading collected at ten other times internal for a few days and fish count extracted using mask R-CNN instance segmentation algorithm are taken as a feature to train autoML machine learning. The experimental results have shown promising results as the event's automatic triggering has improved with machine learning prediction than the conventional method and helped enhance the plant and fish growth.