Jayeeta Mondal

Papers

Total Citations

H-Index

About

Jayeeta Mondal is a leading researcher at the forefront of edge computing and deep learning inference, with a focus on enabling intelligent, real-time decision-making in resource-constrained environments. Her work tackles the critical challenge of deploying sophisticated AI models on embedded devices, where computational power and energy are limited. In her highly cited 2019 paper, "Offloaded Execution of Deep Learning Inference at Edge: Challenges and Insights" (29 citations), she systematically analyzed the bottlenecks and trade-offs in distributing DL inference tasks between edge devices and cloud servers, providing foundational guidance for efficient model offloading. Mondal further demonstrated the practical impact of her research in "Accelerated Fire Detection and Localization at Edge" (2022, 10 citations), where she developed a robust, low-latency system for autonomous disaster response. This work highlights her ability to translate theoretical insights into life-saving applications, leveraging edge AI to enable robots to detect and localize fires rapidly without relying on constant cloud connectivity. Her contributions are pivotal for advancing autonomous systems, smart surveillance, and emergency robotics, making her a key figure in the evolution of practical, on-device intelligence.