Sabbir Hossen
About Me
đź‘‹ Hi! I am Sabbir Hossen
I am a recent Computer Science graduate from Bangladesh University with a strong foundation in Machine Learning, and I am currently working as a Research Assistant at at BU. My research interests mainly focus on Natural Language Processing, Large Language Models, and Computer Vision. Through several impactful research projects in these areas, I have developed both analytical and creative approaches to problem-solving.
My long-term goal is to build computational systems with a broader and more coherent understanding, where vision models, language models, and generative frameworks work in concert rather than in isolation. I aim to develop techniques that not only interpret images and text but also ground their reasoning in real-world structure across diverse application domains, enabling more reliable and context-aware AI systems. I am committed to conducting rigorous, forward-looking research that contributes meaningfully to this direction.
For more information about my research background, ongoing work, and academic experience related to these interests, please take a look at my resume and publications sections.
Latest News
Our Paper “Explainable Machine Learning Framework for Cardiovascular Disease Diagnosis and Prognosis" has been accepted at 9th International Conference on Smart Computing and Systems Engineering (SCSE).
Our Paper “TransCNN: A Hybrid CNN-Transformer Synergy for Reliable Deepfake Forensics" has been accepted at 28th International Conference on Computer and Information Technology (ICCIT).
Our Paper "A Sophisticated Feature Vectorization-Based Stacked Machine Learning Approach for Fake News Detection in Bangla and English" has been accepted at Social Network Analysis and Mining. [Q1].
New Preprint "An Efficient Deep Learning Framework for Brain Stroke Diagnosis Using Computed Tomography Images" is out. [CLick Here]
Our Paper "Jellyfish Species Identification: A CNN Based Artificial Neural Network Approach" has been accepted at 2nd International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN).
Our Paper "StackTrace-AI: Identifying Generative AI Text Origins using Ensemble Learning" has been accepted at 2nd International Conference on Computing, Applications and Systems (COMPAS).
Our Paper "Optimized Hybrid Cascaded Approach for Accurate Oral Cancer Detection in Histopathology Images Using Deep CNNs" has been accepted at IEEE 2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM).
Our Paper "Social Media Sentiments Analysis on the July Revolution in Bangladesh: A Hybrid Transformer Based Machine Learning Approach" has been accepted at IEEE 17th International Conference on Electronics, Computers and Artificial Intelligence (ECAI).
Our Paper "A Hybrid Machine Learning Approach Utilizing CNN Feature Extraction with Traditional Classifiers to Identify Strawberry Leaf Diseases" has been accepted at IEEE 4th International Conference on Electrical, Computer and Communication Engineering (ECCE).
Our Paper "An Explainable AI Driven Machine Learning Approach for Maternal Health Risk Analysis." has been accepted at IEEE 27th International Conference on Computer and Information Technology (ICCIT).
Successfully defended Bachelor's thesis, fulfilling all requirements for the B.Sc. degree in Computer Science.
Appointed as a Undergraduate Research Assistant at NextGen AI Lab, Bangladesh University.