Azzam Alhussain

Papers

Total Citations

H-Index

About

Azzam Alhussain is a researcher at the forefront of efficient edge computing, specializing in hardware-software co-design for real-time artificial intelligence. His primary research areas include embedded machine learning, field-programmable gate array (FPGA) acceleration, and human action recognition (HAR) systems. Alhussain’s major contribution is the development of FPGA-QHAR, a breakthrough throughput-optimized accelerator that enables quantized two-stream human action recognition directly on edge devices. This work directly addresses the critical challenge of deploying computationally intensive HAR algorithms—essential for real-time surveillance and robotics—onto resource-constrained chips without sacrificing performance. By proposing an integrated, end-to-end scalable hardware/software accelerator co-design, he has demonstrated a practical pathway for bringing high-accuracy AI inference to the edge. While his most-cited paper (2023) currently holds 1 citation, its foundational approach to optimizing throughput for quantized neural networks positions it as a significant step toward energy-efficient, real-time visual intelligence. Alhussain’s work is particularly notable for bridging the gap between theoretical deep learning models and practical, deployable edge solutions, making him a promising voice in the push for smarter, faster, and more autonomous embedded systems.