Publications
Journal manuscripts, technical reports and research outputs.
Journal Manuscripts
Generalizable Ensemble Deep Learning for Dermoscopic Skin-Lesion Classification: Internal Evaluation on HAM10000 and External Evaluation on ISIC 2019
Status: Revised manuscript under review (major revision submitted, 2026)
Author: Md Naim Hassan Saykat
This study investigates the generalizability of deep learning models for multiclass dermoscopic skin-lesion classification using harmonized internal evaluation on HAM10000 and external evaluation on ISIC 2019.
Seven architectures are evaluated: a conventional CNN, ResNet-50, DenseNet-121, EfficientNet-B3, ConvNeXt-Tiny, MobileNetV3-Large, and ViT-B/16. Their class-probability outputs are additionally combined using an equal-weight soft-voting ensemble.
The evaluation includes classification and discrimination metrics, calibration analysis, bootstrap confidence intervals, paired statistical comparisons, and Grad-CAM-based qualitative interpretability analysis. The study emphasizes external generalization and the limitations of relying exclusively on internal performance.
- Seven deep learning architectures and probability-level ensemble learning
- HAM10000 internal evaluation and ISIC 2019 external evaluation
- Model calibration and bootstrap uncertainty analysis
- Paired statistical model comparisons
- Grad-CAM-based interpretability analysis
- Reproducible medical-image classification workflow
Technical Reports and Policy Publications
Bangladesh AI Policy & Innovation Lab (BAPIL), an independent research initiative. All publications are in English and Bangla, archived on Zenodo with persistent DOIs and licensed CC BY 4.0.
Bangladesh AI Policy & Innovation Lab (BAPIL): Technical Blueprint
Version 1.0, October 2026 · Md Naim Hassan Saykat · Zenodo
Turns the BAPIL White Paper into a buildable plan for an AI policy-intelligence capability: institutional design, reference architecture, bilingual citation-grounded AI design, governance and assurance, a tested reference implementation, a 36-month delivery plan with an indicative budget, and a strategic roadmap to 2041.
Bangladesh AI Policy & Innovation Lab (BAPIL): Blueprint Summary
Version 1.0, October 2026 · Md Naim Hassan Saykat · Zenodo
An eleven-page summary of the Technical Blueprint: the institution and its governance, the architecture and AI design, six pilots, safeguards, the delivery plan, the roadmap to 2041 and the decisions requested from the authorities.
Bangladesh AI Policy & Innovation Lab (BAPIL) White Paper
Version 1.0, July 2026 · Md Naim Hassan Saykat · Zenodo
The conceptual framework: international lessons in AI governance and digital government, the proposed institution, its research areas and a long-term vision to 2041.
Bangladesh AI Policy & Innovation Lab (BAPIL): Executive Summary
Version 1.0, July 2026 · Md Naim Hassan Saykat · Zenodo
A concise overview of the White Paper's vision, institutional framework, policy recommendations and implementation roadmap.
Research Outputs
Code, evaluation workflows, curated result tables, figures, and supporting reproducibility materials for the skin-lesion classification study are publicly available through the associated GitHub repository and persistent Zenodo archive.
In Preparation
Edge-Ready Skin Lesion Classification with Efficient Deep Ensembles and Latency-Aware Design: A Web-Based Decision-Support Prototype
Status: Research in preparation
Planned submission: 2026-27 academic year
This planned study extends the skin-lesion classification research toward computationally efficient deployment. It will investigate the trade-offs among predictive performance, model size, inference latency, and computational requirements for resource-constrained environments.
The planned methodology includes efficient model and ensemble configurations, model compression, quantization, inference benchmarking, and Grad-CAM-based interpretability. Evaluation will focus on the performance-efficiency trade-off rather than predictive performance alone.
A lightweight web-based research prototype is also planned to demonstrate model inference and visual explanation workflows. The prototype is intended for research and demonstration purposes and is not a clinical diagnostic system.
Research Profile
For persistent researcher identification and an up-to-date record of scholarly outputs, see my ORCID profile.
Publication status and bibliographic information will be updated as manuscripts progress through peer review, revision, publication, and archival release.