Md Shahidul Islam Shabuz

Publications

Peer-reviewed work

Each entry links to the DOI and the full text. Citation counts and any newer items appear on Google Scholar and ORCID.

Journal articles

[1]
Published · open access

An Attention-Enhanced CNN with Explainable AI for Driver Behavior Detection in Intelligent Transportation Systems

Abdullah Al Mamun, Md Shahidul Islam Shabuz, Md Nahidur Rahaman, Khawja Imran Masud, Md. Biddut Hossain

Algorithms (MDPI), vol. 19, no. 8, art. 615 · 23 July 2026

Adds a multi-head attention module to a convolutional network for recognizing driver distraction, and uses Grad-CAM to show which parts of the image the decision rests on. Reported at 99.48% mean accuracy over stratified five-fold cross-validation, running at 122 frames per second.

Full text DOI 10.3390/a19080615 PDF
Abstract

Driver behavior detection is essential for improving road safety in Intelligent Transportation Systems (ITSs). This paper proposes an attention-enhanced CNN integrated with Explainable Artificial Intelligence (XAI) to achieve reliable and interpretable driver behavior classification. Furthermore, the model also uses a multi-head attention mechanism to ensure that it captures local spatial features as well as long-range dependencies in the activities of the driver. The State Farm Distracted Driver dataset is experimented with using stratified 5-fold cross-validation. The proposed MHA-CNN model has a mean accuracy of 99.48% on all folds and an overall high levels of precision, recall, and F1-score in all ten distraction classes. Grad-CAM is used to produce attribution maps to improve interpretability by showing semantically important parts of the image, including hands, face, and mobile devices, and can give a visual explanation of why models make decisions. In addition, an ablation investigation is performed with k-fold validation to assess the value of the multi-head attention mechanism. Its model can run at 122 frames per second with 42.92 million parameters, showing that the suggested method is a reasonable tradeoff between accuracy, efficiency, and transparency and can be applied in real-time driver monitoring applications.

Keywords: driver behavior detection · deep learning · attention mechanism · explainable AI · intelligent transportation systems · computer vision · safety-critical systems

BibTeX 
@article{mamun2026attention,
  author  = {Al Mamun, Abdullah and Shabuz, Md Shahidul Islam and
             Rahaman, Md Nahidur and Masud, Khawja Imran and Hossain, Md. Biddut},
  title   = {An Attention-Enhanced {CNN} with Explainable {AI} for Driver Behavior
             Detection in Intelligent Transportation Systems},
  journal = {Algorithms},
  volume  = {19},
  number  = {8},
  pages   = {615},
  year    = {2026},
  issn    = {1999-4893},
  doi     = {10.3390/a19080615},
  url     = {https://www.mdpi.com/1999-4893/19/8/615}
}