Hamza Ahmed Abushahla

I'm a Master's student in Machine Learning at the American University of Sharjah, where I also earned my B.Sc. in Computer Engineering and a minor in Engineering Management.

I currently work as a research and teaching assistant in the department of Computer Science and Engineering. My research focuses mainly on model compression, optimizaztion and quantization for deploying neural networks on resource-constrained edge devices. Additionally, I explore energy-efficient computing and intelligent autonomous robotics.

Email  |  CV  |  LinkedIn  |  GitHub

Publications

These are papers that have already been published.

Accepted Papers

These are papers that have been accepted for publication, but are not yet up.

Real-Time Student Engagement Monitoring on Edge Devices: Deep Learning Meets Efficiency and Privacy

Hamza Abushahla, Rana Gharaibeh, Lodan Elmugamer, Ali Reza Sajun, Imran A. Zualkernan
IEEE Global Engineering Education Conference (EDUCON), 2025
[Code] [Paper]

This work explores the deployment of deep learning models on resource-constrained edge devices to monitor student engagement in real time, with an emphasis on efficiency and privacy.

Submitted Papers

These are papers that have been submitted for publication, but have not yet been released.

Cognitive Radio Spectrum Sensing on the Edge: A Quantization-Aware Deep Learning Approach

Hamza A. Abushahla, Dara Varam, Mohamed I. AlHajri
IEEE Communications Letters, 2025
[Code] [Paper]

We study the effect of quantization-aware-training (QAT) on two SOTA spectrum sensing models - DeepSense and ParallelCNN. Models are deployed on a Sony Spresense for hardware evaluation.

Different Strokes for Different Folks: Writer Identification for Historical Arabic Manuscripts

Hamza A. Abushahla*, Ariel Justine Navarro Panopio*, Layth Al-Khairulla*, Mohamed I. AlHajri
Expert Systems with Applications, 2025
[Code] [Paper]

We develop an end-to-end CNN-based system for line-level writer identification in historical Arabic manuscripts using the Muharaf Dataset.

Research Projects

These include coursework, side projects and unpublished research work.

From Script to Digital: A Deep Learning Approach to Arabic Handwriting Recognition

Hamza Abushahla, Ariel Justine Panopio, Layth Al-Khairulla , 2024
[Code] [Paper] [Slides]

This was my MLR503: Data Mining and Knowledge Discovery Course Research Project. We developed an end-to-end deep learning-based handwritten text recognition (HTR) system for Arabic script leveraging the KHATT Dataset. To further enhance recognition accuracy, we incorporated KenLM for post-processing.

Cognitive Radio Spectrum Sensing and Allocation: A Low-Complexity Deep Learning Approach

Hamza Abushahla, Ghanim Al-Ali, Sultan Abdalla, Muhammad Ismail Sadaqat, Mohamed AlHajri, Taha Landolsi , 2024
[Code] [Paper] [Poster] [Slides]

This was my B.Sc. in Computer Engineering Senior Design Project, focused on spectrum sensing and allocation using a low-complexity deep learning-based (CNN) spectrum sensing algorithm. The project involved developing and quantizing the CNN model, which was deployed on hardware for real-time operation. The solution was demonstrated both in simulation and on hardware, utilizing a Raspberry Pi as the central node, RTL-SDR for signal sensing, and LoRa transceivers for communication. This dual demonstration validated the practicality and efficiency of the approach in addressing dynamic spectrum management challenges.

Miscellanea

Design and source code from Leonid Keselman's Jekyll fork of Jon Barron's website