MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641113742 A) filed by Koneru Lakshmaiah Education Foundation Deemed To Be University on September 23, 2026, for Intelligent Hyperspectral Device And Deep Learning System For Non-Invasive Pesticide Residue Detection On Fruits And Vegetables.
Inventors include Dr. Jagan Mohan Reddy Danda; Payala Krishnanjaneyulu; Ivsl Haritha; Dr. N. D. S. S. Kiran Relangi; Mrs. D. Aswani; and G. Gowri Pushpa.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: An intelligent device (100) for non-invasive detection and quantification of pesticide residues on fruits and vegetables is disclosed. The device comprises a handheld housing (101), a hyperspectral sensing module (102) capturing reflectance spectra over 400 nm to 1700 nm, an embedded processing unit (103) having a neural processing unit, a memory (104) storing a pre-trained one-dimensional Convolutional Neural Network model, a user interface (105) and a wireless communication module (108). Captured spectra are pre-processed onboard and classified by the model into residue classes correlated with regulatory Maximum Residue Limits, and the result is displayed with a recommended action. The model comprises one-dimensional convolutional layers, batch normalization, pooling, dropout and a SoftMax output layer. A cloud based federated learning system (400) enables collective model improvement while preserving data privacy, thereby providing rapid, portable and non-destructive residue screening.
Disclaimer: Curated by HT Syndication.
