You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
AgriMarket is an open-source digital marketplace that connects farmers and buyers in Somalia. It allows farmers to list their products, while buyers can browse, purchase, and manage orders, promoting direct trade and supporting Somalia's agricultural growth.
Developed a deep learning model using TensorFlow and Convolutional Neural Networks to classify disease images of potato plants, including early blight, late blight, and overall plant health in agriculture. Model achieved an impressive accuracy of 97.8%, empowering farmers with precise treatment applications to enhance crop yield and quality.
Our “RSCMS” is more than just a technical project – it reflects a practical solution to a real-life problem that affects millions of people involved in farming, processing, and consuming rice. Through this project, we aim to gain experience in full-stack development, working in teams, and solving real-world problems with meaningful impact.
AgroIntel is an AI-driven, weather-aware crop planning platform built with Node.js, Express, and MySQL. It leverages the OpenWeather API to provide real-time agricultural recommendations and harvest timelines based on specific land data.
This project leverages LSTM networks, a type of RNN, to accurately predict fruit and vegetable prices by analyzing a comprehensive dataset, utilizing a refined model adept at navigating the complexities and patterns within agricultural market data.
AgriAssist is a comprehensive, AI-powered web application designed to empower farmers by providing them with cutting-edge tools for market intelligence, agronomic support, financial services, and direct market access.
ESP32-based control system and web interface for Team BEHEMOTH's award-winning automatic vegetable transplanter, featuring real-time monitoring, dual modes, and commercial billing.
This is a Streamlit application for predicting agricultural yields based on various input parameters such as year, average rainfall, pesticide usage, average temperature, country, and crop name. The app utilizes a pre-trained machine learning model and a preprocessing pipeline to make predictions.
🎓 Innocent Nyalala | Assistant Professor at IIT Madras Zanzibar | AI Researcher & Agricultural Technology Innovator | Founding PI of SAAIL Lab | 26+ Publications, 1065+ Citations
Based on my published research paper, this project uses a "One-vs-All" deep learning approach with EfficientNet B4 to classify cassava leaf diseases. Integrated into an Android app, it helps farmers detect diseases early, supporting sustainable farming and reducing crop losses.