Academic Research
Research Interests
My research bridges computer science, machine learning, and computer vision to build AI systems that solve complex real-world problems.
Focus Area
Computer Vision
My computer vision research focuses on building systems that can interpret and understand visual data at a deep level. I work on medical imaging, particularly 3D MRI analysis for neurological disease detection, as well as real-world applications like autonomous number plate recognition and surveillance. I apply modern architectures including YOLO-family detectors, 3D CNNs, and attention-based models to these problems.
Focus Area
Machine Learning
I design and analyze machine learning pipelines with a focus on real-world effectiveness. This includes feature engineering, model selection, and the development of novel ensemble methods. My KDRF Classifier integrates KNN and Decision Trees into the Random Forest meta-learning framework to outperform baselines on multi-class tasks. I prioritize interpretability and efficiency alongside raw accuracy.
Focus Area
Deep Learning
At the core of my research is deep learning architecture design and optimization. I work with Convolutional Block Attention Modules (CBAM), 3D ResNets for volumetric data, and IoT-integrated deep learning pipelines. My work on SafeTrax demonstrates how edge-deployed deep learning can deliver real-time collision prediction on embedded hardware like Raspberry Pi via AWS Greengrass.
Focus Area
Interdisciplinary AI
I believe the most impactful AI research crosses disciplinary boundaries. My interdisciplinary projects apply computational intelligence to healthcare (Alzheimer's early detection), transportation safety (IoT + deep learning collision prediction), and data security (chaotic map encryption for privacy-preserving detection). I collaborate across departments to ensure solutions are technically rigorous and practically deployable.
Related Publications
Interested in Collaboration?
I am open to research collaborations and PhD opportunities worldwide.