publication

2025

1. GitHub

   

   Adaptive Fuzzy Ensemble Learning with Multi-Distance Metrics for Cervical Cancer Classification (Prepared for Submission)

   2025

   Bib

   @unpublished{ashraful2025kidney,
     title = {Adaptive Fuzzy Ensemble Learning with Multi-Distance Metrics for Cervical Cancer Classification
      (Prepared for Submission) },
     year = {2025},
     howpublished = {https://github.com/povashraful/Cervical_Cancer_Classificiation},
   }

2. GitHub

   

   Enhanced Deep Learning Approach for Kidney Disease Detection and Diagnosis

   S.M.N. Nobel, M.A. Hossain, M.M. Hossain, and 3 more authors

   2025

   Bib

   @unpublished{nobel2025kidney21,
     title = {Enhanced Deep Learning Approach for Kidney Disease Detection and Diagnosis},
     author = {Nobel, S.M.N. and Hossain, M.A. and Hossain, M.M. and Sultana, S. and Alahmadi, T.J. and Moni, M.A.},
     year = {2025},
     howpublished = {Available at: https://github.com/povashraful/Kidney-Disease-Deep-Learning},
   }

2024

1. 

   SegX-Net: A novel image segmentation approach for contrail detection using deep learning

   S. M. Nuruzzaman Nobel, Md. Ashraful Hossain, Md. Mohsin Kabir, and 3 more authors

   PLOS ONE, Mar 2024

   Abs Video

   Contrails are line-shaped clouds formed in the exhaust of aircraft engines that significantly contribute to global warming. This paper confidently proposes integrating advanced image segmentation techniques to identify and monitor aircraft contrails to address the challenges associated with climate change. We propose the SegX-Net architecture, a highly efficient and lightweight model that combines the DeepLabV3+, upgraded, and ResNet-101 architectures to achieve superior segmentation accuracy. We evaluated the performance of our model on a comprehensive dataset from Google research and rigorously measured its efficacy with metrics such as IoU, F1 score, Sensitivity and Dice Coefficient. Our results demonstrate that our enhancements have significantly improved the efficacy of the SegX-Net model, with an outstanding IoU score of 98.86% and an impressive F1 score of 99.47%. These results unequivocally demonstrate the potential of image segmentation methods to effectively address and mitigate the impact of air conflict on global warming. Using our proposed SegX-Net architecture, stakeholders in the aviation industry can confidently monitor and mitigate the impact of aircraft shrinkage on the environment, significantly contributing to the global fight against climate change.

2. 

   An Integrative Machine Learning Strategy for the Prognosis of Heart Disease

   Md. Ashraful Hossain, S. M. Nuruzzaman Nobel, Md. Mohsin Kabir, and 2 more authors

   In Advances in Information Communication Technology and Computing, Mar 2024

   Abs Video

   The incidence of heart disease is concerning, and timely detection is essential for improving the health of patients. Machine learning has shown potential in assisting in the prognosis of heart conditions. This research evaluated the effectiveness of various machine learning algorithms, including Random Forest, XGBoost, LGBM, and CatBoost, in accurately predicting instances of heart disease. Furthermore, we suggested a hybrid model that integrates all four models, yielding a 97.50% accuracy rate, 0.98% precision value, 0.97% recall value, and 0.98% F1-score. This hybrid model surpasses both individual models and current methodologies. The study utilized the “Heart Failure Prediction Dataset” acquired from Kaggle, which consisted of 11 prevalent variables such as age, blood pressure, and cholesterol levels. These findings indicate that the hybrid model has promise as a powerful tool for predicting heart disease.