Research Focus

Abduljabbar Ba Mahel’s research centers on the intersection of deep learning and biomedical engineering, with an emphasis on healthcare applications. His primary focus lies in developing robust AI models for ECG-based arrhythmia detection, chronic wound monitoring, and breast cancer diagnosis through medical image segmentation and signal analysis. He is deeply interested in leveraging transfer learning, domain adaptation, and attention-based architectures to improve diagnostic accuracy in real-world, imbalanced datasets. His work frequently combines CNNs, GRUs, and hybrid architectures for multi-scale feature extraction and classification. Additionally, he explores explainable AI (XAI) to enhance transparency in clinical decision-making. His contributions reflect a commitment to transforming traditional diagnostics into intelligent, automated systems that can be deployed in both high-tech hospitals and resource-limited settings. His collaborative projects span across China, Russia, and the Middle East, contributing to a globally relevant, scalable healthcare innovation portfolio.

🧠 Skills 

Abduljabbar Ba Mahel possesses a rich and diverse skill set essential for modern biomedical research and AI model development. He is proficient in Python, MATLAB, R, and C++, and frequently uses frameworks such as TensorFlow, Keras, and PyTorch to implement and optimize deep learning algorithms. For scientific workflows, he is adept in Docker, Git, Jupyter, and LaTeX, enabling reproducibility and collaboration. In the medical imaging domain, he works with tools like DICOM, ITK-SNAP, and 3D Slicer for preprocessing and visualization of radiological data. He also employs statistical tools like SPSS and advanced functions in MATLAB for signal processing and hypothesis testing. His domain-specific expertise spans ECG signal classification, image segmentation, transfer learning, and synthetic data generation. With both technical and analytical strengths, Abduljabbar bridges the gap between engineering innovation and clinical application, creating end-to-end solutions for smart diagnostics and digital health systems.

Conclusion