Smart Aquaponics and Hydroponics Monitoring Using IoT

This project aims to develop an automated system for detecting diseases in hydroponic plants and aquatic fish by leveraging deep learning techniques, specifically Convolutional Neural Networks (CNN). Initially, datasets of hydroponic plant and fish diseases will be sourced from Kaggle to create a robust training set. For each input image, a preprocessing phase will resize the images to ensure uniformity, preparing them for accurate analysis. In the plant disease detection module, the CNN model will classify diseases affecting plants grown in water, identifying various types of leaf or root infections. Similarly, in the fish disease detection module, the CNN model will classify common diseases that affect aquatic life. The classified disease information for both plant and fish images will then be transmitted as text data to a hardware kit, enabling real-time response and potentially triggering necessary interventions or alerts in aquaculture and hydroponic systems. This system not only streamlines the process of disease identification in these specialized environments but also holds significant promise for improving disease management and reducing losses in controlled agricultural and aquatic ecosystems.

Keywords: Dataset, Pre-Processing, Convolutional Neural Networks, Deep learning, Classification, Accuracy.