Teaching Assistant | Daffodil International University | Bangladesh
Sarbajit Paul Bappy is an emerging researcher in computer science with a growing focus on applied machine learning, medical image analysis, and agricultural informatics. He is currently serving as a Teaching Assistant in the Department of Computer Science and Engineering at Daffodil International University, Bangladesh, where he has been contributing to academic instruction and research support since 2025. Alongside his professional role, he is pursuing his undergraduate degree in Computer Science and Engineering at the same institution, demonstrating a strong integration of academic excellence and early-career research productivity. His scholarly work includes peer-reviewed publications and openly accessible datasets that address critical challenges in healthcare diagnostics and smart agriculture. Notably, he co-authored SkinVisualNet: A Hybrid Deep Learning Approach Leveraging Explainable Models for Identifying Lyme Disease from Skin Rash Images (MAKE, 2025), which combines deep learning with explainable AI techniques to enhance early disease detection. He also contributed significantly to the dataset Jackfruit AgroVision, a comprehensive benchmark for disease detection in jackfruit and its leaves, supporting advancements in precision agriculture and food-security research. His collaborations span multidisciplinary teams involving experts such as Amir Sohel, Rittik Chandra Das Turjy, Md Assaduzzaman, Ahmed Al Marouf, Jon George Rokne, and Reda Alhajj, illustrating his ability to contribute within diverse international research groups. Through his ongoing work in AI-driven health diagnostics, dataset development, and sustainable agricultural technology, Bappy aims to advance research that supports societal well-being, improves disease detection accuracy, and contributes to innovation within global machine learning communities.
Profiles: Google Scholar | ORCID | LinkedIn
Featured Publications
1. Sohel, A., Turjy, R. C. D., Bappy, S. P., Assaduzzaman, M., Marouf, A. A., Rokne, J. G., & Alhajj, R. (2025). SkinVisualNet: A Hybrid Deep Learning Approach Leveraging Explainable Models for Identifying Lyme Disease from Skin Rash Images. Machine Learning and Knowledge Extraction, 7(4), 157. https://doi.org/10.3390/make7040157 MDPI+1
2. Sohel, A., Bijoy, M. H. I., Turjy, R. C. D., & Bappy, S. P. (2025). Jackfruit AgroVision: A Extensive Dataset for Jackfruit Disease and Leaf Disease Detection using Machine Learning. Mendeley Data. https://doi.org/10.17632/pt647jfn52.1
