MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541133079 A) filed by Koneru Lakshmaiah Education Foundation, Vaddeswaram, Andhra Pradesh, on Dec. 29, 2025, for 'a hybrid intelligent system and method for depression detection using multimodal emotion recognition.'
Inventor(s) include Mrs. Janaswami. Hymavathi; and Dr. Chokka. Anuradha.
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: "The present invention provides a development of a hybrid intelligent system & approach for detection of depression that combines multimodal emotion recognition from verbal & facial video, text, & optional physiological modalities. The approach processes modality-specific embeddings prosody/MFCCs for audio, action units & gaze/head pose for video, contextual embeddings for text, & EEG/ECG/GSR signals if available via hierarchical hybrid fusion that combines early feature interaction & late decision-level fusion, thus being robust against the presence/absence of modalities. The results for severity estimation are aligned with standard clinical measures such as PHQ-9 cut-offs for distinguishing among mild to severe conditions. The approach is amenable for privacy-preserving preprocessing on devices & interfaces for telehealth & offline applications. Results, framed within recent works on multimodal frameworks for studying depression & fusion for emotion recognition, suggest that the choice of hybrid fusion enhances robustness & interpretability over individual baselines for implementation in clinical settings."
Disclaimer: Curated by HT Syndication.
