MUMBAI, India, Aug. 10 -- Intellectual Property India has published a patent application (202641085118 A) filed by Dr. V. Geethalakshmi; Ms. Aruna Verma; D Sudheer Reddy; Dr. G. Nageswara Rao; Suja Alphonse A; Girija Vasumathi G G; Prashant K; Dr. P. Sumalatha; Dr Thallapally Sreelatha; R. Anand; E. Ahiladevi; and Thonepudi Hemalatha on July 11, 2026, for Machine Learning-Based Intelligent Device For Real-Time Air Pollution Monitoring Using Electric Vehicles.
Inventors include Dr. V. Geethalakshmi; Ms. Aruna Verma; D Sudheer Reddy; Dr. G. Nageswara Rao; Suja Alphonse A; Girija Vasumathi G G; Prashant K; Dr. P. Sumalatha; Dr Thallapally Sreelatha; R. Anand; E. Ahiladevi; and Thonepudi Hemalatha.
The application for the patent was published on July 31, 2026, under issue no. 31/2026.
Abstract: Machine Learning-Based Intelligent Device for Real-Time Air Pollution Monitoring Using Electric Vehicles is the proposed invention. The proposed invention discloses a machine learning-based intelligent device for real-time air pollution monitoring using electric vehicles. The proposed system employs electric vehicles as mobile sensing platforms equipped with environmental sensors for measuring particulate matter, gaseous pollutants, meteorological parameters, and geographical location. Sensor data are pre-processed through an embedded edge-computing module and analyzed using the Mamba State Space Model (Mamba SSM), a recent sequence learning architecture optimized for efficient long-term temporal modeling. The model accurately predicts pollutant concentrations, detects abnormal pollution events, identifies pollution hotspots, and forecasts short-term air quality variations while requiring minimal computational resources. The predicted pollution information is integrated with GPS coordinates to generate dynamic pollution maps and transmitted to a cloud platform for visualization, environmental analytics, and smart city management. The invention offers high prediction accuracy, low latency, energy-efficient computation, and scalable deployment on mobile edge devices, making it highly suitable for sustainable urban environmental monitoring and intelligent transportation applications.
Disclaimer: Curated by HT Syndication.
