We propose a resilient edge data integrity verification approach that combines robust Merkle trees with steganographic transmission to strengthen proof reliability and secure verification communication in edge computing environments.

@article{islam2026resilient,
  author  = {Islam, Md Rashedul and Xiang, Yong and Uddin, Md Palash and Zhang, Yushu and Peng, Dezhong and Kua, Jonathan and Ghasemi, Abdorasoul},
  title   = {A Resilient Edge Data Integrity Verification Approach via Robust Merkle Trees and Steganographic Transmission},
  journal = {IEEE Transactions on Cloud Computing},
  pages   = {1--14},
  month   = may,
  year    = {2026},
  doi     = {10.1109/TCC.2026.3697006}
}
    

We propose a federated learning-based edge data corruption detection framework with adaptive regularization to improve detection performance under heterogeneous edge intelligence environments.

@article{islam2025tcc,
title   = {Federated learning with adaptive regularization for efficient edge data corruption detection in edge intelligence},
author  = {Islam, Md Rashedul and Uddin, Palash and Xiang, Yong and Yeh, K.-H. and Liu, L. and Kua, Jonathan},
journal = {IEEE Transactions on Cloud Computing},
year    = {2025}
}
    

We introduce a multi-vendor and multi-server edge data integrity verification method that reduces redundant verification overhead while supporting practical mobile edge computing scenarios.

@ARTICLE{10836859,
  author={Islam, Md Rashedul and Xiang, Yong and Uddin, Md Palash and Zhao, Yao and Kua, Jonathan and Gao, Longxiang},
  journal={IEEE Transactions on Mobile Computing}, 
  title={Multiple Edge Data Integrity Verification With Multi-Vendors and Multi-Servers in Mobile Edge Computing}, 
  year={2025},
  volume={24},
  number={6},
  pages={4668-4683},
  doi={10.1109/TMC.2025.3528016}
}
    

We develop a compact multi-branch deep learning model for hyperspectral image classification, improving classification performance while maintaining computational efficiency.

@Article{rs16122069,
AUTHOR = {Islam, Md. Rashedul and Islam, Md. Touhid and Uddin, Md Palash and Ulhaq, Anwaar},
TITLE = {Improving Hyperspectral Image Classification with Compact Multi-Branch Deep Learning},
JOURNAL = {Remote Sensing},
VOLUME = {16},
YEAR = {2024},
NUMBER = {12},
ARTICLE-NUMBER = {2069},
DOI = {10.3390/rs16122069}
}
    

We propose a hybrid spectral–spatial feature reduction approach integrated with deep learning to improve hyperspectral image classification accuracy.

@article{Islam2023JSSSpectralSpatialHybridDL,
author = {Md Rashedul Islam and M. T. Islam and Md Palash Uddin},
title = {Improving hyperspectral image classification through spectral--spatial feature reduction with a hybrid approach and deep learning},
journal = {Journal of Spatial Science},
year = {2023},
note = {Q2}
}
    

We present an information-theoretic dimension reduction method to select informative hyperspectral features and improve classification performance.

@article{Islam2023RemoteSensingITDR,
author = {Md Rashedul Islam and A. Siddiqa and M. I. Afjal and Md Palash Uddin and A. Ulhaq},
title = {Hyperspectral image classification via information theoretic dimension reduction},
journal = {Remote Sensing},
year = {2023},
note = {Q1}
}
    

We investigate feature reduction strategies for hyperspectral image classification to reduce dimensionality while preserving discriminative information.

@article{Islam2020JSSFeatureReductionHSI,
author = {Md Rashedul Islam and B. Ahmed and A. Hossain},
title = {Feature reduction of hyperspectral image for classification},
journal = {Journal of Spatial Science},
year = {2020},
note = {Q2}
}