MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641078364 A) filed by Cmr Engineering College, Kandlakoyav, Medchal Road, Hyderabad, Medchal Malkajgiri, Telangana-, India. on June 25, 2026, for Machine Learning-Based Adaptive Traffic Congestion Prediction And Smart Route Optimization System.
Inventors include Dr. A Srinivasula Reddy, Professor And Principal, Electrical And Electronics Engineering, Cmr Engineering College, Kandlakoya; Mr. Radhe Shyam Panda, Assistant Professor, Computer Science And Engineering Aiml, Cmr Engineering College, Kandlakoya, Hydeabad-.; Ms. D. Navanitha, Assistant Professor, Computer Science And; Mr. V. Kiran Kumar, Associate Professor, Computer Science And; Mr. K. Shyam Babu, Assistant Professor, Computer Science And; Mrs N. Madhavi, Assistant Professor, Computer Science And Engineering Data Science Cmr Engineering College, Kandlakoya, Hydeabad-; and Mr. Janga Rajendar, Assistant Professor, Computer Science And Engineering Data Science, Cmr Engineering College, Kandlakoya, Hydeabad-.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: The present invention discloses a Machine Learning-Based Adaptive Traffic Congestion Prediction and Smart Route Optimization System for intelligent transportation management in smart city environments. The system is designed to address the growing challenges of traffic congestion, increased travel time, fuel consumption, and environmental pollution caused by rapid urbanization and increasing vehicle density. The proposed framework utilizes advanced machine learning algorithms to analyze both historical and real-time traffic data collected from multiple sources, including GPS-enabled devices, IoT sensors, traffic cameras, road infrastructure, and mobile applications. Traffic congestion levels are accurately predicted using machine learning models such as Random Forest, XGBoost, and Long Short-Term Memory (LSTM) networks, enabling early detection of congestion patterns and traffic anomalies. Based on the predicted traffic conditions, an adaptive route optimization engine dynamically generates efficient travel routes by considering parameters such as traffic density, road availability, travel time, and distance. The system continuously updates predictions and route recommendations through real-time data processing and cloud-edge computing integration. Furthermore, the invention supports seamless integration with intelligent transportation systems and smart city infrastructures for enhanced traffic monitoring and management. The proposed system significantly improves urban mobility, reduces travel delays and fuel consumption, minimizes environmental impact, and enhances road safety. Its scalable and adaptive architecture makes it suitable for deployment in large metropolitan areas, thereby contributing to sustainable and efficient transportation systems for modern smart cities.
Disclaimer: Curated by HT Syndication.
