hyderabad
IIIT Hyderabad students develop dynamic ML model-switching approach for traffic monitoring
A team of second-year computer science students from IIIT Hyderabad developed a novel approach for dynamically switching machine learning models on smartphones for real-time traffic monitoring. Their project, 'EdgeML Balancer', aims to optimize model switching decisions based on factors like user requests, response time, accuracy, and energy consumption. The team prototyped their model on Qualcomm's development kit and tested it with real-time traffic data. Their work has now progressed to testing on the Samsung S24 Ultra and will be presented at both the SARECS workshop in Denmark and IIITH's R&D Showcase in March. The project, initially conceived as an exploratory exercise, highlights the potential of hands-on learning for undergraduate students to make impactful contributions to the field.11:49 AM Feb 27, 2025 IST