Scientific Profile
I am a research associate and PhD student at Qatar Computing Research Institute and College of Science and Engineering in Hamad Bin Khalifa University, where I work with my advisors, Ferda Ofli and David Yin Yang, on domain generalisation for real world applications.
I completed my MSc at Qatar University. My MSc thesis focused on anti-drone technologies for detecting and identifying drones using their acoustic signatures through deep learning.
Active projects
RWGAI (Real World Generalisation in Artificial Intelligence)
Research
I am interested in improving the robustness and generalisation of machine learning models for real-world applications. My research focuses on developing solutions, datasets, and benchmarks for challenges like domain generalisation, to enhance the reliability and applicability of models across diverse conditions and environments.
Publications
2025
Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery
Sara Al-Emadi, Yin Yang, Ferda Ofli
CVPR 2025
Project page/Paper/arXiv
Introducing the RWDS benchmark to evaluate object detection robustness in satellite imagery under real-world distribution shifts.
2021
MSc Thesis – 2021
2020
Towards enhancement of network communication architectures and routing protocols for FANETs: A survey
Sara Al-Emadi, Aisha Al-Mohannadi
IEEE CommNet 2020
Paper
This paper surveys the latest network communication architectures and routing protocols for Flying Ad hoc Networks (FANETs) and proposes a clustering-based architecture and new routing mechanism to address existing limitations.
Drone detection approach based on radio-frequency using convolutional neural network
Sara Al-Emadi, Felwa Al-Senaid
IEEE ICIoT 2020
Paper/Github
This paper presents a deep learning-based drone detection solution using Radio Frequency (RF) signals, outperforming existing methods.
Modern QoS Solutions in WSAN: An Overview of Energy Aware Routing Protocols and Applications
Ahmad Zaza, Sara Al-Emadi, Suleiman Kharroub
IEEE ICIoT 2020
Paper
This paper reviews state-of-the-art QoS-enhancing approaches, protocols, and applications in WSAN, highlighting their shortcomings and suggesting improvements.
Using deep learning techniques for network intrusion detection
Sara Al-Emadi, Aisha Al-Mohannadi, Felwa Al-Senaid
IEEE ICIoT 2020
Paper
The paper proposes a deep learning-based network intrusion detection system using CNN and RNN, comparing their performance to identify the best model for detecting attacks.
2019
Audio Based Drone Detection and Identification using Deep Learning
Sara Al-Emadi, Abdulla Al-Ali, Amr Mohammed, Abdulaziz Al-Ali
IEEE IWCMC 2019
Project page/Paper/Github
This study proposes a deep learning solution to detect and identify drones using acoustic signatures and introduces the first drone audio dataset.
Sara Al-Emadi 