Hi, I'm Mohammad Zunaed! I am working as a research assistant in the mHealth Lab at Bangladesh University of Engineering and Technology (BUET) under the supervision of Dr. Taufiq Hasan. My work focuses on developing deep-learning algorithms such as addressing domain generalization aspects of CNN models, integrating anatomical knowledge in a CNN backbone to improve explainability, aggregating different levels of annotation granularities in a singular framework, and assisting students associated with the lab in their thesis tasks.

Before starting my journey as a research assistant, I worked as a lecturer in the Electrical and Electronic Engineering (EEE) department at Daffodil International University. I completed my M.Sc. and B.Sc. in EEE from Bangladesh University of Engineering and Technology (BUET) in 2023 and 2019, respectively. My academic path has been enriched by a multitude of projects and international competitions spanning Deep Learning, Computer Vision, and NLP.

My research interests involve improving the generalizability and robustness of deep learning models, developing trustworthy and explainable AI frameworks, utilizing multi-modal frameworks, using semi/unsupervised learning, and so on.

Interests
  • Computer Vision
  • Deep Learning
  • Domain Generalization
  • Medical Imaging
  • Natural Language Processing
Education
  • MSc in EEE, 2023
    Bangladesh University of Engineering and Technology
  • BSc in EEE, 2019
    Bangladesh University of Engineering and Technology
News
04/2024
One paper on improving pediatric pneumonia diagnosis with adult chest X-ray images has been accepted by IEEE EMBC.
02/2024
One paper on domain generalization via style perturbation for thoracic disease classification has been accepted by IEEE J-BHI.
12/2023
One paper on thoracic disease classification using anatomical prior probability maps has been accepted by IEEE Access.
08/2023
I passed my M.Sc. oral defense.
08/2023
An abstract based on my M.Sc. thesis work has been accepted for oral presentation at the Conference on Machine Intelligence in Medical Imaging.
08/2022
One paper on anatomy-aware thoracic disease classification has been accepted by IEEE J-BHI.
Selected Publications
description "Learning to Generalize towards Unseen Domains via a Content-Aware Style Invariant Framework for Disease Detection from Chest X-rays." IEEE Journal of Biomedical and Health Informatics (IEEE J-BHI), 2024.
IEEE Xplore arXiv GitHub
description "Improving Pediatric Pneumonia Diagnosis with Adult Chest X-ray Images Utilizing Contrastive Learning and Embedding Similarity." IEEE Engineering in Medicine and Biology Society (IEEE EMBC), 2024. (Accepted)
arXiv
description "ThoraX-PriorNet: A Novel Attention-Based Architecture Using Anatomical Prior Probability Maps for Thoracic Disease Classification." IEEE Access, 2023.
IEEE Xplore arXiv GitHub
description "Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays." IEEE Journal of Biomedical and Health Informatics (IEEE J-BHI), 2022.
IEEE Xplore arXiv PubMed
description "Solar PV Power Forecasting Using Traditional Methods and Machine Learning Techniques." IEEE Kansas Power and Energy Conference (IEEE KPEC), 2021.
IEEE Xplore
description "Dual-CyCon Net: A Cycle Consistent Dual-Domain Convolutional Neural Network Framework for Detection of Partial Discharge." arXiv, 2021.
arXiv
description "Non-invasive Blood Glucose Estimation Using Multi-sensor Based Portable and Wearable System." IEEE Global Humanitarian Technology Conference (IEEE GHTC), 2019.
IEEE Xplore
Awards and Highlights
Experience
Selected ML Competition Participation History