Prof. M Ashraful Amin, PhD

My teaching philosophy is “Application Oriented Learning”. Focus of this philosophy is to restructure course material in such a way that it contains more real-life example-oriented explanation and demonstration such that students know where and how they can apply knowledge acquired during a course. This is done through introduction of practical problem-solving strategies and relevant literature surveying. After attending my courses students know how to seek for relevant material for learning. I teach my students how to learn.

My research philosophy is “Humanitarian Technology Innovation for 4th Industrial Revolution Challenges”. Focus of this philosophy is to motivate and equip, Bangladeshi youth to learn and apply research on machine learning and statistical data analytics, computer vision and cybernetics, and IoT and robotics, to develop humanitarian technology to address issues such as: climate, gender, disability, healthcare, education, and poverty alleviation.

Prof. M Ashraful Amin, PhD

Bio

Publications (188)

Deciphering Salinity-Induced Transcriptomic Variations inOsmoregulatory Tissues Gills and Kidney of Hilsa Shad (Tenualosa ilisha)

FedCTTA: A Collaborative Approach to Continual Test-Time Adaptation in Federated Learning

Performance Analysis of Machine Learning Models for Detecting Anomalous Traffic in Internet of Medical Things

Integrating Supervised and Self-Supervised Models for an Enhanced PCOS Detection: A Data-Driven Approach with Machine Learning Perspective

Improving User Engagement and Learning Outcomes in LLM-Based Python Tutor: A Study of PACE

Internet Disconnection as a Risk to Cross-Border Human Rights

Emotion Recognition in Bangla Text: An Ensemble Approach with Data Augmentation using BanglaBERT and MultiBERT

SOMAJGYAAN: A dataset for evaluating LLMs on Bangla culture, social knowledge, and low-resource language adaptation

Hatenet-bn at BLP-2025 Task 1: A hierarchical attention approach for bangla hate speech detection

Analyzing Machine Learning Models for Multiclass Classification of Human Stress Levels: Comparison Between Balanced and Imbalanced Data