publications

2026

1. JMIR AI

   Clinical Validity in Synthetic EHR Generation: Best-of-N Sampling in Tabular GANs

   Md Akmol Masud and Mahmud Hasan

   JMIR AI, 2026

   Accepted; in production

   Abs DOI Bib HTML

   We introduce a three-regime taxonomy for evaluating clinical validity in synthetic EHR generation, governed by the generator’s valid-support mass (p_valid). Best-of-N sampling—generating multiple candidates and retaining the clinically closest one—shifts generators toward safer regimes. Benchmarked across WGAN-GP and CTGAN on multiple clinical datasets with a rigorous multi-metric privacy audit including distance-to-closest-record and proximity concentration analysis.

   @article{masud2026jmirai,
     author = {Masud, Md Akmol and Hasan, Mahmud},
     title = {Clinical Validity in Synthetic {EHR} Generation: Best-of-N Sampling in Tabular {GAN}s},
     journal = {JMIR AI},
     year = {2026},
     doi = {10.2196/90590},
     url = {https://doi.org/10.2196/90590},
     note = {Accepted; in production},
   }

2. TMLR

   

   Quantum Rationale-Aware Graph Contrastive Learning for Jet Discrimination

   Md Abrar Jahin, Md Akmol Masud, M. F. Mridha, and 1 more author

   Transactions on Machine Learning Research, 2026

   Abs arXiv Bib HTML

   We propose a quantum rationale-aware graph contrastive learning framework for jet discrimination in high-energy physics, combining graph neural networks with quantum computing to improve classification performance.

   @article{masud2026quantumcontrastive,
     author = {Jahin, Md Abrar and Masud, Md Akmol and Mridha, M. F. and Dey, Nilanjan},
     title = {Quantum Rationale-Aware Graph Contrastive Learning for Jet Discrimination},
     journal = {Transactions on Machine Learning Research},
     year = {2026},
     url = {https://arxiv.org/abs/2411.01642},
   }

3. PLOS ONE

   

   MosQNet-SA: Explainable Convolutional-Attention Network for Mosquito Classification with Application as a RESTful API for Dengue and Malaria Risk Mapping

   Md Akmol Masud, Sanjida Akter, Nadia Sultana, and 4 more authors

   PLOS ONE, 2026

   Abs DOI Bib HTML

   MosQNet-SA is an explainable convolutional-attention network for classifying mosquito species (Anopheles, Aedes, Culex) with integrated RESTful API for real-time dengue and malaria risk mapping.

   @article{masud2026mosquito,
     author = {Masud, Md Akmol and Akter, Sanjida and Sultana, Nadia and Islam, Mohammad Shahidul and Abu Yousuf, Mohammed and Noori, Farzan M. and Uddin, Md Zia},
     title = {MosQNet-SA: Explainable Convolutional-Attention Network for Mosquito Classification with Application as a RESTful API for Dengue and Malaria Risk Mapping},
     journal = {PLOS ONE},
     year = {2026},
     volume = {21},
     number = {4},
     pages = {1--30},
     doi = {10.1371/journal.pone.0344970},
     url = {https://doi.org/10.1371/journal.pone.0344970},
   }

4. BSPC

   

   DREAM: A Novel Explainable Neural Network for Detecting Sleep Apnea Using Single-Lead ECG Signals

   Sanjida Akter, Md Akmol Masud, Mst. Sanzida Islam Promi, and 6 more authors

   Biomedical Signal Processing and Control, 2026

   Abs DOI Bib HTML

   DREAM is an explainable neural network for detecting sleep apnea from single-lead ECG signals, featuring novel explainability mechanisms for clinical interpretability.

   @article{akter2026dream,
     author = {Akter, Sanjida and Masud, Md Akmol and Promi, Mst. Sanzida Islam and Sultana, Nadia and Ahmed, Maruf and Rahman, Md. Mahmudur and Yousuf, Mohammad Abu and Aloteibi, Saad and Moni, Mohammad Ali},
     title = {DREAM: A Novel Explainable Neural Network for Detecting Sleep Apnea Using Single-Lead ECG Signals},
     journal = {Biomedical Signal Processing and Control},
     volume = {114},
     pages = {109291},
     year = {2026},
     doi = {10.1016/j.bspc.2025.109291},
     url = {https://www.sciencedirect.com/science/article/pii/S1746809425018026},
   }

5. ICECTE

   

   FedDQN-TSR: Federated Deep Q-Learning for Resource-Aware Traffic Sign Recognition in Internet of Vehicles

   Zannat Hossain Tamim, Md Akmol Masud, Md. Sazzadur Rahman, and 1 more author

   In 5th International Conference on Electrical, Computer & Telecommunication Engineering (ICECTE), 2026

   Abs DOI Bib HTML

   FedDQN-TSR applies federated deep Q-learning for resource-aware traffic sign recognition in Internet of Vehicles environments, balancing communication efficiency and model accuracy.

   @inproceedings{masud2026feddqn,
     author = {Tamim, Zannat Hossain and Masud, Md Akmol and Rahman, Md. Sazzadur and Islam, Mohammad Shahidul},
     title = {FedDQN-TSR: Federated Deep Q-Learning for Resource-Aware Traffic Sign Recognition in Internet of Vehicles},
     booktitle = {5th International Conference on Electrical, Computer \& Telecommunication Engineering (ICECTE)},
     year = {2026},
     pages = {1--6},
     publisher = {IEEE},
     doi = {10.1109/ICECTE69292.2026.11429337},
     url = {https://doi.org/10.1109/ICECTE69292.2026.11429337},
   }

6. arXiv

   

   HealthNLP_Retrievers at ArchEHR-QA 2026: Cascaded LLM Pipeline for Grounded Clinical Question Answering

   Md Biplob Hosen, Md Alomgeer Hussein, Md Akmol Masud, and 3 more authors

   2026

   Abs arXiv Bib HTML

   A cascaded LLM pipeline for grounded clinical question answering over electronic health records, submitted to the ArchEHR-QA 2026 shared task (CL4Health @ LREC 2026). The system retrieves evidence spans from EHR notes and grounds answers in retrieved clinical context.

   @misc{hosen2026healthnlp,
     author = {Hosen, Md Biplob and Hussein, Md Alomgeer and Masud, Md Akmol and Faruque, Omar and Reynolds, Tera L. and Chen, Lujie Karen},
     title = {{HealthNLP\_Retrievers at ArchEHR-QA 2026}: Cascaded LLM Pipeline for Grounded Clinical Question Answering},
     year = {2026},
     archiveprefix = {arXiv},
     primaryclass = {cs.CL},
     url = {https://arxiv.org/abs/2604.26880},
   }

7. QPAIN

   

   SQU: Sensitivity-Guided Quantum Machine Unlearning for Privacy-Preserving ML

   Md Akmol Masud, Zannat Hossain Tamim, Md Musa Kalimullah Ratul, and 1 more author

   In 2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN), 2026

   Abs DOI Bib HTML

   SQU is a sensitivity-guided quantum machine unlearning framework for privacy-preserving ML, enabling the right to be forgotten in quantum models via variational quantum circuits and differential privacy mechanisms.

   @inproceedings{masud2026squ,
     author = {Masud, Md Akmol and Tamim, Zannat Hossain and Ratul, Md Musa Kalimullah and Hosen, Md Biplob},
     title = {{SQU}: Sensitivity-Guided Quantum Machine Unlearning for Privacy-Preserving {ML}},
     booktitle = {2026 IEEE 2nd International Conference on Quantum Photonics, Artificial Intelligence \& Networking (QPAIN)},
     year = {2026},
     pages = {1--6},
     publisher = {IEEE},
     doi = {10.1109/QPAIN69676.2026.11546660},
     url = {https://doi.org/10.1109/QPAIN69676.2026.11546660},
   }

2025

1. arXiv

   

   Stabilizing Federated Learning under Extreme Heterogeneity with HeteRo-Select

   Md Akmol Masud, Md Abrar Jahin, and Mahmud Hasan

   2025

   Abs arXiv Bib HTML

   HeteRo-Select is a client selection framework for federated learning under extreme statistical and system heterogeneity, featuring variance-aware scheduling and heterogeneity-aware aggregation strategies.

   @misc{masud2025heteroselect,
     author = {Masud, Md Akmol and Jahin, Md Abrar and Hasan, Mahmud},
     title = {Stabilizing Federated Learning under Extreme Heterogeneity with HeteRo-Select},
     year = {2025},
     url = {https://arxiv.org/abs/2508.06692},
   }

2. IEEE TAI

   

   Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics

   Md Abrar Jahin, Md Akmol Masud, Md Wahiduzzaman Suva, and 2 more authors

   IEEE Transactions on Artificial Intelligence, 2025

   Abs DOI Bib HTML

   A Lorentz-equivariant quantum graph neural network for jet classification in high-energy physics, exploiting physical symmetries via quantum circuits for improved discrimination.

   @article{jahin2025lorentz,
     author = {Jahin, Md Abrar and Masud, Md Akmol and Suva, Md Wahiduzzaman and Mridha, M. F. and Dey, Nilanjan},
     title = {Lorentz-Equivariant Quantum Graph Neural Network for High-Energy Physics},
     journal = {IEEE Transactions on Artificial Intelligence},
     year = {2025},
     pages = {1--11},
     doi = {10.1109/TAI.2025.3554461},
     url = {https://doi.org/10.1109/TAI.2025.3554461},
   }

3. CBM

   

   KACQ-DCNN: Uncertainty-Aware Interpretable Kolmogorov–Arnold Classical–Quantum Dual-Channel Neural Network for Heart Disease Detection

   Md Abrar Jahin, Md Akmol Masud, M. F. Mridha, and 2 more authors

   Computers in Biology and Medicine, 2025

   Abs DOI Bib HTML

   KACQ-DCNN combines classical and quantum computing in a dual-channel neural network with Kolmogorov-Arnold representations for interpretable, uncertainty-aware heart disease detection.

   @article{jahin2025kacq,
     author = {Jahin, Md Abrar and Masud, Md Akmol and Mridha, M. F. and Aung, Zeyar and Dey, Nilanjan},
     title = {KACQ-DCNN: Uncertainty-Aware Interpretable Kolmogorov--Arnold Classical--Quantum Dual-Channel Neural Network for Heart Disease Detection},
     journal = {Computers in Biology and Medicine},
     year = {2025},
     volume = {197},
     pages = {110976},
     doi = {10.1016/j.compbiomed.2025.110976},
     url = {https://doi.org/10.1016/j.compbiomed.2025.110976},
   }

4. ECCE

   

   Multi-Layered Password-Based Steganography: A Novel Approach for Tiered Information Hiding

   Md Akmol Masud, Sanjida Akter, Nadia Sultana, and 2 more authors

   In International Conference on Electrical, Computer and Communication Engineering (ECCE), 2025

   Abs DOI Bib HTML

   A multi-layered password-based steganography system for tiered information hiding with hierarchical access control and improved security against steganalysis.

   @inproceedings{masud2025ecce,
     author = {Masud, Md Akmol and Akter, Sanjida and Sultana, Nadia and Yousuf, Mohammad Abu and Uddin, Md Zia},
     title = {Multi-Layered Password-Based Steganography: A Novel Approach for Tiered Information Hiding},
     booktitle = {International Conference on Electrical, Computer and Communication Engineering (ECCE)},
     year = {2025},
     pages = {1--6},
     publisher = {IEEE},
     doi = {10.1109/ECCE64574.2025.11013270},
     url = {https://doi.org/10.1109/ECCE64574.2025.11013270},
   }