Papers
7
Total Citations
84
H-Index
4
About
Tughrul Arslan is a researcher whose work spans indoor positioning systems and edge artificial intelligence, with particular emphasis on low-power hardware accelerators for resource-constrained environments. His early contributions focused on indoor localization, most notably a 2017 paper introducing a Monte Carlo localization algorithm for Bluetooth Low Energy devices, which has accumulated 42 citations and demonstrated the practical viability of probabilistic approaches for real-world navigation challenges. His research trajectory then shifted toward the rapidly evolving field of edge AI, where he has made significant strides in designing efficient convolutional neural network accelerators suited for deployment in drones, wearables, robotics, and remote sensing satellites. His widely cited 2021 analysis of low-power, ultra-small edge AI accelerators for image recognition — garnering 30 citations across versions — has become a valuable reference for researchers navigating performance and power trade-offs in embedded systems. More recent work, including the DycSe dynamic reconfiguration convolution engine and fault-tolerant streaming architectures, reflects his growing interest in building reliable, resource-aware AI hardware. Collectively, Arslan's research addresses the critical challenge of bringing intelligent computation closer to the point of data collection without sacrificing efficiency or dependability.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7