MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641018162 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Feb. 18, for 'edge-based anomaly detection system for chemical plant sensors using isolation forest machine learning.'
Inventor(s) include Dr. B. Kalaavathi; Dr. A. Arivoli; Vishnu Priya P; C. Nivyasree; and Thirisha M.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "An edge-based anomaly detection system (100) includes an edge computing device (102) having a processor (104) configured to execute anomaly detection locally, at least one sensor (116) configured to acquire sensor data from an industrial environment, a feature engineering module (210) configured to extract temporal features from the sensor data using sliding window processing, and an anomaly detection engine (216) having a quantized Isolation Forest model (218) configured to generate anomaly scores based on the temporal features. The quantized Isolation Forest model (218) is executed on the edge computing device (102). The at least one sensor may include a gas sensor (118), a temperature and humidity sensor (120), a force sensing resistor (122), and a light dependent resistor (124). The system (100) may further include a signal conditioning module (110), a data acquisition layer (202), an adaptive threshold module (220), and an alert management system (222)."
Disclaimer: Curated by HT Syndication.
