Research
My research lies at the intersection of Computer Vision and Deep Learning, with a current focus on damage detection and quantification in images across construction structures, real-world objects, and medical contexts. As a founding member and active researcher at KCR-Lab, I supervise student research projects and lead initiatives addressing real-world problems in healthcare and visual AI.
Current Research Themes
Damage Detection & Quantification Computer Vision Vision Transformers AI for Healthcare Dataset Development Multimodal AI
Research Experience
Founding Member & Researcher — KCR-Lab
Oct 2024 – Present
- Supervise undergraduate research in machine learning, deep learning, and computational linguistics
- Organize workshops and hands-on training sessions to equip students with AI skills
- Lead NLP projects focusing on low-resource languages, especially Bengali
- Collaborate with faculty on interdisciplinary AI initiatives
Undergraduate Thesis Researcher — CUET
Feb 2022 – Apr 2023
A Deep Learning Based Pharmaceutical Product Evaluation from Bengali Reviews Considering Emoji
- Developed a benchmark dataset of 4,000+ Bengali pharmaceutical reviews
- Identified the rating-review mismatch problem in local e-commerce
- Proposed a novel emoji-aware approach to enhance review classification
- Supervised by Prof. Dr. Muhammad Ibrahim Khan
Publications C: Conferences | J: Journals
C.1
BScFilter: A Deep Learning Approach for Sports Comments Filtering in a Resource-Constrained Language
TCCE 2023, Springer [Paper]
C.2
Vision Transformers for Multi-Class Eye Disease Classification: Enhancing Early Detection in Resource-Constrained Healthcare
BIM 2025, Springer [Paper]
C.3
Addressing the Mental Health Crisis: Understanding Suicidal Risk Factors in University Students Through Interpretable Machine Learning
IDAA 2025, Springer [Paper]
C.4
SETBoost: An Interpretable Machine Learning Approach for Predicting Software Employee Turnover Tendency
ICCIT 2025, IEEE Xplore [Paper]
C.5
Evaluating Prompting and Fine-Tuning Approaches for Bengali Violence Detection in a Low-Resource Language
ICCIT 2025, IEEE Xplore [Paper]
Works in Progress
J.1 · Under Review
Addressing Rating-Review Discrepancy in a Novel Dataset: An Explainable Pharmaceutical Product Evaluation using Multi-Stream Attention Transformer
J.2 · Under Review
Triple-Pooling Feature Fusion for Transformer-Based Text Classification: A Low-Resource Language Approach with Explainable AI
J.3 · With Editor
BSC: Transformer-Based Bengali Audio Slang Detection in Low-Resource Settings
J.4 · With Editor
Machine Learning for Suicidal Risk Identification Among University Students: An Explainable and Subgroup-Aware Approach
Research Projects
Diabetes Factor Analysis with Outlier Detection [GitHub]
scikit-learn · pandas · numpy · matplotlib · seaborn
- Applied statistical methods to identify significant factors affecting diabetes diagnosis
- Implemented outlier detection techniques to improve feature selection quality
- Achieved 2-4% overall performance increment with outlier removal
Sentiment Analysis on Twitter Texts [GitHub]
scikit-learn · NLTK · Transformers · Tkinter · pandas · matplotlib
- Implemented multiple feature extraction techniques including TF-IDF and word embeddings
- Compared performance across classical ML and deep learning approaches
- Created an interactive interface for real-time sentiment prediction
CUET-BUS-TRACKER: Real-time Transportation Monitoring System [GitHub]
Java · Firebase · Google Maps API · Android Studio
- Designed and implemented location tracking system for university transport
- Integrated Google Maps API with Firebase for synchronous data updates
For further details, visit my Google Scholar profile.