MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641016175 A) filed by Dr. V. Vaishnavi; Dr. P. Suveetha Dhanaselvam; and Ms. R. Brindha, Kariapatti, Tamil Nadu, on Feb. 13, for 'wireless cyber-physical system and method for non-invasive, monitoring of neonatal physiological states using acoustic and multi-model data analytics.'
Inventor(s) include Dr. V. Vaishnavi; Dr. P. Suveetha Dhanaselvam; and Ms. R. Brindha.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "This invention presents a non-invasive, wireless health monitoring system for neonates in NICUs, integrating multi-modal sensing into a compact wearable pod to replace wired sensors. It continuously captures vital signs such as heart rate, respiratory rate, SpOO, temperature and acoustic biomarkers via specialized sensors. A key innovation is the embedded machine learning-driven fusion architecture that correlates disparate physiological and acoustic data streams to detect subtle pre-pathological states missed by conventional single-parameter monitors. The signal processing pipeline uses a three-layer hierarchy: (1) non-invasive sensors, (2) an intermediate layer for synchronization, noise filtering and signal normalization including time, frequency and time-frequency-domain processing of acoustic inputs and (3) an intelligent analysis layer running optimized ML models. These models, trained on NICU datasets using supervised and unsupervised methods, identify conditions like sepsis, respiratory distress and hypoxia through hyb~id deterministic and data-driven logic. Edge computing enables on-device inference during connectivity loss, powered by a low-power MCU with AI accelerators such as tensor processing units. The system fuses distress cry patterns with physiological trends to generate risk scores and event alerts. Communication uses secure, dual-mode wireless protocols for continuous streaming for routine data and event-triggered transmission for alerts for optimizing power. Computational load dynamically shifts among the wearable pod, bedside gateway and cloud based on criticality and connectivity."
Disclaimer: Curated by HT Syndication.
