Researcher [Jun 2025 – Current]
Bio-Neural Intelligence and Research Advancement Lab Khulna, Bangladesh
City: Khulna | Country: Bangladesh
Supervisor: Amit Dutta Roy (Google Scholar; LinkedIn; ResearchGate; Portfolio)
Designed NeuroSwin, a hybrid deep learning model (Swin Transformer-GRU), to classify Parkinson's Disease and identify its source regions in the brain from EEG signals.
Research Assistant Intern [Oct 2024 – Current]
Ulster University Londonderry, Northern Ireland, UK
City: Londonderry, Northern Ireland | Country: United Kingdom
Supervisor: Dr. Nazmul Siddique (Google Scholar; LinkedIn; ResearchGate; Portfolio)
Developed TransfusionNet, a hybrid architecture augmented with a specialized preprocessing pipeline and an early-layer feature fusion paradigm for cervical cancer detection. This work has been published in the Q1 journal Results in Engineering (Elsevier, Impact Factor: 7.9).
Created a benchmark to evaluate the performance of large language models (LLMs) in identifying disease classes, comparing results against our proposed architecture MobileCoAtNet for stomach infection classification.
Investigated the adaptability of foundational AI models for multi-cancer classification, implementing Model-Agnostic Meta-Learning (MAML) for domain adaptation to enhance generalizability.
Actively researching the feasibility of large language models (LLMs) for disease diagnosis, reasoning, and treatment follow-up in medical applications.
Undergraduate Research Assistant [Feb 2023 – Sep 2024]
Department of Biomedical Engineering, KUET Khulna, Bangladesh
City: Khulna | Country: Bangladesh
Supervisor: Dr. Mostafa Zaman Chowdhury (Google Scholar; LinkedIn; ResearchGate; Portfolio)
Designed a hybrid model for gallbladder cancer classification using parallel transfer learning, feature fusion, and LSTM, achieving 99.37% accuracy; part of this work was published at ICEEICT 2024
Gained experience in academic writing, literature review, and presenting research findings.
Student Operator [10 Jun 2022 – 21 Mar 2024]
Fabrication Lab KUET Khulna, Bangladesh
City: Khulna | Country: Bangladesh | Website: https://www2.kuet.ac.bd/fablab/
• Assisted in organizing workshops such as ‘Hands-on Training Using Fabrication Tools’ and ‘IQAC's Hands-on-Training Program’ at FabLab KUET, covering 3D printing, laser cutting, and CNC milling.
• Helped over 50 students fabricate project and thesis models, guiding them in transforming innovative ideas into real products.