Papers
7
Total Citations
753
H-Index
4
About
Ahmed Imteaj is a researcher whose work sits at the intersection of federated learning, Internet of Things (IoT), and distributed machine learning, with a growing focus on privacy-preserving AI for resource-constrained environments. He is perhaps best known for his landmark 2021 survey, "A Survey on Federated Learning for Resource-Constrained IoT Devices," which has amassed an impressive 719 citations and stands as a foundational reference for researchers navigating the challenges of deploying decentralized machine learning on edge devices with limited computational capacity. Beyond this seminal contribution, Imteaj has consistently advanced the application of federated learning to real-world autonomous systems. His FedAR framework introduced an activity- and resource-aware federated learning model tailored for distributed mobile robots, addressing practical constraints that standard FL approaches often overlook. He has also explored human activity recognition in resource-limited settings and applied computer vision alongside IoT technologies to develop autonomous search-and-rescue robots. His earlier work demonstrated hands-on engineering ingenuity through voice-controlled and path-following robotic systems. Together, these contributions paint the picture of a researcher deeply committed to making intelligent, privacy-conscious machine learning accessible across the full spectrum of connected devices and autonomous platforms.
Research Focus
Key Achievements
Top Papers
- 1A Survey on Federated Learning for Resource-Constrained IoT Devices719 citations · 2021
- 2
- 3
- 4
- 5Distributed machine learning for collaborative mobile robots2 citations · 2020
- 6
- 7