
Pabon Shaha
Lecturer
Pabon Shaha is a Lecturer in the Department of Computer Science and Engineering (CSE) at Bangladesh University (BU). He holds an M.Sc. and a B.Sc. in Computer Science and Engineering from Mawlana Bhashani Science and Technology University (MBSTU), Tangail, Bangladesh. He has several years of academic experience in teaching and academic coordination within the Department of CSE at Bangladesh University.
Academic Experience
Pabon Shaha has been serving in the Department of Computer Science and Engineering at Bangladesh University since July 2023 as a Lecturer. Prior to his current appointment, he served as a Lecturer (Part-Time) in the same department from September 2022 to July 2023. He also served as an Academic Coordinator in the Department of CSE from March 2024 to January 2025, contributing to the coordination and smooth implementation of academic activities.
Professional Practice
His professional practice focuses on university-level teaching, academic coordination, and supporting departmental academic activities. Through his teaching and coordination responsibilities at Bangladesh University, he has contributed to classroom instruction, student support, academic planning, and the effective coordination of departmental activities.
Area of Interest
1. Data Science
2. Natural Language Processing (NLP)
3. Machine learning (ML)
4. Artificial Intelligence (AI)
5. Deep learning (DL)
6. Digital Image processing and computer vision
Journal Publications:
1. A Sophisticated Feature Vectorization-Based Stacked Machine Learning Approach for
Fake News Detection in Bangla and English. Journal: Social Network Analysis and Mining.
Publisher: Springer.
2. Title: Analysis of the Performance of Feature Optimization Techniques for the Diagnosis of
Machine Learning-based chronic kidney disease. Journal: Machine Learning with
Applications. Publisher: Elsevier. Doi: http://dx.doi.org/10.1016/j.mlwa.2022.100330
3. “A Prevalent Model-based on Machine Learning for Identifying DRDoS Attacks
through Features Optimization Technique”, Journal: Statistics, Optimization & Information
Computing. Publisher: Elsevier. Doi: 10.19139/soic-2310-5070-2042.3.
4. Stacked Ensemble Method: An Advanced Machine Learning Approach for Anomaly-
based Intrusion Detection System. Journal: Statistics, Optimization & Information
Computing. Publisher: Elsevier. DOI: 10.19139/soic-2310-5070-2352
Conference Publications:
1. A Hybrid Machine Learning Approach Utilizing CNN Feature Extraction with
Traditional Classifier to Identify Strawberry Leaf Diseases. Conference: 2025 International
Conference on Electrical, Computer and Communication Engineering (ECCE). Publisher: IEEE
Xplore. DOI: 10.1109/ECCE64574.2025.11014040
2. Bio-inspired Heuristic Optimization-Based Cascaded Hybrid Network for Brain Cancer
Screening. Conference: 2025 International Conference on Electrical, Computer and
Communication Engineering (ECCE). Publisher: IEEE Xplore. DOI:
10.1109/ECCE64574.2025.11013886
3. An Explainable AI Driven Machine Learning Approach for Maternal Health Risk
Analysis. Conference: ICCIT 2024.
4. Social Media Sentiments Analysis on the July Revolution in Bangladesh: A Hybrid
Transformer Based Machine Learning Approach. (Accepted: ECAI 2025 – 28th European
Conference on Artificial Intelligence).
5. Optimized Hybrid Cascaded Approach for Accurate Oral Cancer Detection in
Histopathology Images Using Deep CNNs".(Accepted: 2nd International Conference on Next-
Generation Computing, IoT and Machine Learning (NCIM 2025).
6. Explainable AI-Driven Intelligent Approach for Mango Leaf Disease Recognition.
(Accepted in QPAIN Conference-2025)
7. An XAI-Enhanced ML Approach for Cardiovascular Disease Detection and Risk
Assessment. (Accepted in QPAIN Conference-2025).
8. Jellyfish Species Identification: A CNN Based Artificial Neural Network Approach.
(Accepted in QPAIN Conference-2025))
9. StackTrace-AI: Source Detection of ChatGPT vs Gemini Texts using Ensemble Learning.
(Accepted in COMPAS Conference-2025)).
10. An Interpretable Malware Detection Framework Based on Gradient Boosting and
Explainable AI. (Accepted in ICCETE 2026).
Publication in progress:
Journal-
1. ConvNet9: A Cutting-Edge Customized Convolutional Neural Network Model to
Identify Potato Leaf Disease with Web Application. Journal: Computers and Electronics in
Agriculture. (Submitted).
2. A Secure Telemedicine Scheme Based on Distributed Database, Machine Learning and
IoT for Diagnosis of Diabetes Disease. (Submitted)
3. Optimized Hybrid Approach for Early Detection of Alzheimer’s Disease Using
Machine Learning and Deep Learning Technique. (Ready to submit)
4. BERT and Machine Learning-Based AI Text Detection Model with Explainable Feature
Analysis. (Submitted)
5. An Advanced Deep Learning Framework for Ischemic and Hemorrhagic Brain Stroke
Diagnosis Using Computed Tomography (CT) Images. (Ready to submit)
Conference-
1. Title: Optimized Hybrid Cascaded Approach for Accurate OSCC Detection in
Histopathology Images Using Deep CNNs. (Ready to submit)
2. Title: Attention-Guided Deep CNN for Robust Image-Based Weather Phenomena
Classification. (Submitted)
3. Title: Hybrid CNN Architecture for Bengali Pitha Recognition: A Deep Learning Approach
(Submitted).
