9 papers · See Google Scholar for up-to-date metrics
Md. Mahfuz Uddin , Md. Binyamin , , Md. Rezaul Karim
Benchmarking eight ML algorithms on 61,711 patient records, LightGBM comes out on top for cardiovascular disease prediction (AUC 0.800), with systolic blood pressure, age, and cholesterol as the strongest predictors.
, M. Monimul Huq , M. Sabiruzzaman , Md. Rezaul Karim
The revised arXiv preprint is now on v2 and reflects the current BMC Public Health submission. In a four-round BDHS benchmark, validation-regime choice changed screening workload estimates more than architecture choice, making temporal splits and capacity-based metrics essential before programmatic use.
, Humyra Ankona , Md Monimul Huq , Md. Rezaul Karim
High digital engagement makes students more vulnerable to infrastructure failures, not less. We call this the 'Dependency Divide', and targeted reliability improvements for heavy users yield 2× the return of blanket interventions.
, Md. Rezaul Karim
Width should grow 2.8× faster than depth in transformers, validated across 30 architectures up to 7B parameters. Past a critical depth, adding layers actively hurts, even though parameter count increases.
, Md Jahid Hasan Imran , Md. Naim Molla , Luknath Debnath , Tonmoy Shil , Ehsanul Bashar Pranto , Md Mostafizur Rahman Likhon , Md Shafin Sanyan Saad , Md. Rezaul Karim
The revised preprint maps all 17 SDGs across 114 countries and finds 84 supported directed linkages after false-discovery control. No single goal behaves as a stable universal accelerator, so portfolio policy should track time-lagged, evidence-backed linkages instead of rankings alone.
Md. Naim Molla , , Md. Binyamin , Md Jahid Hasan Imran , Tonmoy Shil , Nura Rayhan , Md Rezaul Karim
Classical models outperform fine-tuned XLM-RoBERTa on 5,652 English-Bangla government banking app reviews; aspect analysis surfaces transaction speed and UI as top pain points; 16.1pp Bangla–English accuracy gap.
, Soyda Humyra Yesmin , Saiful Islam , Md. Palash Bin Faruque , Md. A. Salam , Md. Mahfuz Uddin , Samiul Islam , Tofayel Ahmed , Md. Binyamin , Md. Rezaul Karim
239× fewer parameters than GraphCast at near-identical accuracy. Principled multi-objective NAS can find truly deployable models, and transfer learning adds ~5% accuracy gains when historical data is scarce.
Saiful Islam , Md. Palash Bin Faruque , Tanjina Khan , Most. Shabrina Afroz , Tofayel Ahmed , , Md. Kamruzzaman , Md. Mostafizur Rahman , Md. Abdul Khalek
Hybrid model (SVM+RF+XGBoost) predicts early childhood development in Bangladesh with 0.77 accuracy (cognitive) and 0.71 (social-emotional). SHAP reveals domain-specific drivers: books and education for cognition, caregiving and discipline for social-emotional outcomes, with urban-rural subgroup divergences informing targeted SDG 4.2 interventions.
Pre-trained on 357K children across 44 countries, this encoder solves the cold-start problem: with only 50 samples it beats gradient boosting by 8–12%. Zero-shot to unseen countries still reaches AUC 0.84.
