MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541134163 A) filed by Nitte, Mangaluru, Karnataka, on Dec. 31, 2025, for 'an intelligent privacy-preserving multi-modal affect detection system and method thereof.'
Inventor(s) include Dr. Navaneeth Bhaskar; and Razeen Sheikh Ansar.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "Disclosed herein is an intelligent privacy-preserving multi-modal affect detection system (100) comprising an audio capture unit (102) configured to record voice signals, a video capture unit (104) configured to capture facial expressions and micro-expressions, a user interface (106) integrated into a user device (108) for receiving data inputs, a communication network (110) for data transmission, and a processing unit (112) configured to perform on-device multi-modal affect analysis using deep learning and differential privacy techniques, further comprising an input module (114), preprocessing module (116), audio analysis module (118), video analysis module (120), graph construction module (122) implementing message-passing neural networks, personalization module (124), explanation module (126), safety policy module (128), consent module (130), calibration module (134), and output module (132). The system (100) includes a database (136) for storing trained models, baselines, consent records, and affect detection results."
Disclaimer: Curated by HT Syndication.
