Intellectual Property India Publishes Patent Application for 'Federated Learning System For Groundnut Leaf Disease Detection' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122145 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'federated learning system for groundnut leaf disease detection.'

Inventor(s) include Dr. Niha K; Mr. Vaibhav Kawatra; Mr. Arth Pratap Singh; and Mr. Vaibhav Bansal.

The application for the patent was published on Jan. 2, under issue no. 01/2026.

According to the abstract released by the Intellectual Property India: "The present disclosure provides a federated learning system for groundnut leaf disease detection. The system includes a central server coordinating federated learning operations and aggregating model updates from distributed clients. Each client includes a local computing device with processor, memory, and storage, a local dataset of groundnut leaf images, and a local convolutional neural network model for image classification. The system includes a federated averaging module aggregating model parameters from clients to generate a global model, and a model distribution module distributing updated global models back to clients. The system performs iterative federated learning rounds where each client trains the local model on respective local datasets and transmits model parameters to the central server without sharing raw image data, maintaining data privacy. Local datasets include groundnut leaf images labeled with disease classifications: Early Leaf Spot, Late Leaf Spot, Rust, and Nutrition Deficiency."

Disclaimer: Curated by HT Syndication.