MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202641074775 A) filed by Vellore Institute Of Technology on June 17, 2026, for “a Multi-Tier Wearable Safety System For Context-Aware Detection Of Falls And Sleep-Phase Conscious Immobility”.
Inventors include Dr. Badrinath N; Gundumalle Ashlin Joel; and Dhruv Chaudhary.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: The present invention relates to a multi-tier wearable safety system for context-aware detection of falls and sleep-phase conscious immobility. The system comprises a wearable device having a motion sensing module, a physiological sensing module, a voluntary interaction module, a processing unit, a memory unit, and a communication module, wherein the processing unit executes a TinyML inference engine configured to generate and process feature vectors derived from motion information, physiological arousal indicators, and voluntary response indicators. The TinyML inference engine classifies a user state into at least one of a normal activity state, a fall event state, a benign sleep stillness state, a conscious immobility state, and an unconscious distress state. A context and state evaluation module evaluates the classified state using sleep-window information, non-impact immobility information, and voluntary response verification information to distinguish benign sleep stillness from safety-critical conditions. An escalation management module determines a risk level associated with the classified state and selectively initiates monitoring, caregiver notification, or autonomous emergency alert generation. Event summaries and classification metadata are communicated to fog or edge processing nodes and a cloud analytics platform for trend analysis, secure storage, post-event review, and model refinement while maintaining real-time safety decision execution locally within the wearable device. The invention enables low-latency, privacy-preserving, and autonomous safety monitoring across active and sleep-related conditions. Fig 1 to 9.
Disclaimer: Curated by HT Syndication.
