MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122967 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'spatiotemporal graph convolutional network system for traffic accident prediction.'
Inventor(s) include Dr. Priyanka N; Mr. Shetty Dhanish Prakash; Mr. Munawwar Abdul Muneer; and Ms. Anjali Mishra.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a computer-implemented method for traffic accident prediction. The method includes acquiring road network topology data representing a road network and temporal data, constructing a graph structure wherein road segments of the road network are represented as nodes and edges represent spatial connectivity between adjacent road segments, processing the graph structure and the temporal data through a spatiotemporal graph convolutional network model having graph convolutional layers configured to capture spatial dependencies between connected road segments, and generating predictions of traffic accident occurrence for the road segments based on the processed spatial and temporal data. The system architecture (FIG. 1) demonstrates a modular pipeline that integrates multiple data sources, processing components, and visualization elements to provide real-time traffic accident risk assessment and prediction capabilities."
Disclaimer: Curated by HT Syndication.
