I am Raihan Tanvir, currently serving as a Senior Lecturer in the Department of Computer Science and Engineering at Ahsanullah University of Science and Technology (AUST) in Dhaka, Bangladesh. I earned my Bachelor of Science in Computer Science and Engineering from AUST and completed my Master of Science in Computer Science and Engineering from BRAC University.
My research interests lie at the intersection of Computer Vision, Natural Language Processing (NLP), Large Language Models (LLMs), Vision-Language Models (VLMs), and Large Vision-Language Models (LVLMs). A significant portion of my research focuses on leveraging generative adversarial networks (GANs) and multimodal deep learning to address practical and societal challenges, especially within the local context of Bangladesh.
Prior to joining AUST, I served as a Lecturer at Stamford University Bangladesh, where I actively contributed to teaching and curriculum development. I am passionate about teaching, mentoring, and collaborative research, and I strive to promote a student-centered and innovation-driven academic environment.
In addition to my teaching responsibilities, I am involved in multiple ongoing research projects in collaboration with students and faculty peers. I remain committed to advancing the field of AI through rigorous research, interdisciplinary collaboration, and impactful technological development.
For more information, please see my 📃 Curriculum Vitae.
MSc in CSE
BRAC University, Dhaka, Bangladesh
BSc in CSE
Ahsanullah University of Science and Technology, Dhaka, Bangladesh
This study presents a deep neural network and transformer-based framework for classifying Bengali texts into saint and common forms, with SahajBERT achieving the best performance. The integration of LIME enhances interpretability, providing insights into stylistic cues aligned with linguistic expectations.
Deep learning models were developed to predict agricultural land suitability and soil quality for precision agriculture. TabTransformer achieved the highest accuracy (97.40%) on augmented data, demonstrating the potential of deep learning for structured agricultural data.
LIME was used to enhance the interpretability of model predictions, especially in cases of misclassification, contributing to the development of reliable and interpretable AI-driven solutions for medical imaging.
Handwritten character recognition is a significant research area, especially for languages like Bengali where quality OCR applications are scarce. Merging machine learning and deep learning techniques, including CNN, improves accuracy. The use of Grad-CAM as an XAI method enhances model interpretability.
This work uses Hidden Markov Models (HMM) to predict next-day stock prices based on historical data, focusing on fractional price changes and intraday highs and lows. The Maximum a Posteriori HMM method showed satisfactory results and can generalize to predict stock prices for any company with proper training.
