Predictive mathematical models of biological processes like wound healing are essential for quantitative understanding, but their clinical utility is often limited by a critical roadblock: uncertainty in their biophysical parameters. These parameters are difficult to measure directly and must be inferred from sparse, noisy data. This paper presents a Bayesian Physics-Informed Neural Network (BPINN) framework to address this challenge by performing robust parameter inference and principled uncertainty quantification.
@article{debanath2025bayesian,title={Bayesian Physics-Informed Neural Networks for Parameter Inference and Uncertainty Quantification in Reaction-Diffusion Models of Wound Healing},author={Debanath, Koshik and Aich, Sagor and Srizon, Azmain Yakin},journal={Mathematical Biosciences},year={2025},month=jul,note={Under review},}
ECCE 2025
Advancing Low-Resource NLP: Contextual Question Answering for Bengali Language Using Llama
K. Debanath, S. Aich, and A. Y. Srizon
In 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), Jul 2025
Natural language processing (NLP) has witnessed significant advancements in recent years, particularly in improving question-answering (QA) systems for well-resourced languages such as English. However, the development of such systems for low-resource languages, including Bengali, remains insufficiently explored.
@inproceedings{debanath2025advancing,title={Advancing Low-Resource NLP: Contextual Question Answering for Bengali Language Using Llama},author={Debanath, K. and Aich, S. and Srizon, A. Y.},booktitle={2025 International Conference on Electrical, Computer and Communication Engineering (ECCE)},pages={1--6},year={2025},organization={IEEE},doi={10.1109/ECCE64574.2025.11013841},slide={/assets/img/545.pptx},}
ECCE 2025
Distinguishing Between Formal and Colloquial: A Multilingual BERT Approach to Bengali Language Classification
S. Aich, K. Debanath, and A. Y. Srizon
In 2025 International Conference on Electrical, Computer and Communication Engineering (ECCE), Jul 2025
The Bengali language, rich in history and cultural significance, poses unique challenges in Natural Language Processing (NLP) due to its dual-register structure: Sadhu (formal) and Cholit (colloquial).
@inproceedings{aich2025distinguishing,title={Distinguishing Between Formal and Colloquial: A Multilingual BERT Approach to Bengali Language Classification},author={Aich, S. and Debanath, K. and Srizon, A. Y.},booktitle={2025 International Conference on Electrical, Computer and Communication Engineering (ECCE)},pages={1--6},year={2025},organization={IEEE},doi={10.1109/ECCE64574.2025.11013999},slide={/assets/img/729_Sagor Aich.pptx},}
NCIM 2025
Analyzing Bot Activity and Political Discourse in the 2024 U.S. Presidential Election: A Machine Learning Approach to Misinformation and Manipulation
K. Debanath, S. Aich, and A. Y. Srizon
In 2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM-2025), Jul 2025
Social media has become a battleground for political discourse, with automated accounts (bots) playing a growing role in shaping public opinion and engagement. In the context of the 2024 U.S. Presidential Election, understanding bot activity is crucial for identifying potential misinformation and manipulation tactics.
@inproceedings{debanath2025analyzing,title={Analyzing Bot Activity and Political Discourse in the 2024 U.S. Presidential Election: A Machine Learning Approach to Misinformation and Manipulation},author={Debanath, K. and Aich, S. and Srizon, A. Y.},booktitle={2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM-2025)},pages={1--6},year={2025},organization={IEEE},doi={10.1109/NCIM65934.2025.11160229},slide={/assets/img/727_ Koshik Debanath.pptx},}
NCIM 2025
Distinguishing Human-Written and AI-Generated Text: A Comprehensive Study Using Explainable Artificial Intelligence in Text Classification
S. Aich, K. Debanath, and A. Y. Srizon
In 2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM-2025), Jul 2025
Enhancing interpretability without compromising accuracy is a critical challenge in text classification. This research explores the integration of Explainable Artificial Intelligence (XAI) techniques with advanced machine learning models, utilizing the Local Interpretable Model-Agnostic Explanations (LIME) framework to provide transparency.
@inproceedings{aich2025distinguishing_human_ai,title={Distinguishing Human-Written and AI-Generated Text: A Comprehensive Study Using Explainable Artificial Intelligence in Text Classification},author={Aich, S. and Debanath, K. and Srizon, A. Y.},booktitle={2nd International Conference on Next-Generation Computing, IoT and Machine Learning (NCIM-2025)},pages={1--6},year={2025},organization={IEEE},doi={10.1109/NCIM65934.2025.11160309},}
BIM 2025
Physics-Informed Neural Networks for Real-Time Anomaly Detection in Power System Dynamics
K. Debanath, S. Aich, and A. Y. Srizon
In 3rd International Conference on Big Data, IoT and Machine Learning (BIM 2025), Jul 2025
A physics-informed neural network approach for real-time anomaly detection in power system dynamics with improved accuracy and reliability for critical infrastructure monitoring.
@inproceedings{debanath2025physics,title={Physics-Informed Neural Networks for Real-Time Anomaly Detection in Power System Dynamics},author={Debanath, K. and Aich, S. and Srizon, A. Y.},booktitle={3rd International Conference on Big Data, IoT and Machine Learning (BIM 2025)},year={2025},note={Accepted, To appear},}
2023
ICCIT 2023
An Attention-Based Deep Learning Approach to Knee Injury Classification from MRI Images
K. Debanath, A. F. M. M. Rahman, and M. A. Hossain
In 2023 26th International Conference on Computer and Information Technology (ICCIT), Jul 2023
Knee injuries, prevalent in athletic and aging populations, pose significant challenges to healthcare professionals due to their complex nature and the critical function of the knee joint. Early and accurate diagnosis is paramount to ensure effective treatment and minimize long-term complications.
@inproceedings{debanath2023attention,title={An Attention-Based Deep Learning Approach to Knee Injury Classification from MRI Images},author={Debanath, K. and Rahman, A. F. M. M. and Hossain, M. A.},booktitle={2023 26th International Conference on Computer and Information Technology (ICCIT)},pages={1--6},year={2023},organization={IEEE},doi={10.1109/ICCIT60459.2023.10441340},slide={/assets/img/543_KoshikDebanath.pptx},}
