My research centers on Machine Learning, Deep Learning, Computer Vision, Explainable AI (XAI), and High-Frequency Time-Series Forecasting. Below are peer-reviewed articles, manuscripts under review, academic thesis work, and ongoing research initiatives.
Published in Array, Elsevier, 2026
A multi-tier explainable hybrid ensemble combining gradient-boosted trees (XGBoost, LightGBM, CatBoost) with regularized meta-regressors, achieving test RMSE of 0.0006 with policy-grade SHAP/LIME interpretability on high-frequency macro-financial data. Read more
Recommended citation: S. M. Mohiuddin Khan Shiam, Meherunnesa Neela, Amrijit Biswas, and Mahdy Rahman Chowdhury. (2026). "HybridStack: Explainable hybrid ensemble for accurate inflation forecasting with high-frequency macro-financial data." Array, Elsevier, Vol. 31, Art. 101003, ISSN: 2590-0056. DOI: 10.1016/j.array.2026.101003.
Download Paper
Published in Scientific Reports (Nature Portfolio) [Under Review], 2026
An edge-ready 3D-CNN architecture containing only 486K parameters (1.86 MB model size) delivering 88.7% accuracy, 0.947 AUC, and 7.19 ms latency across 5 canonical anomaly datasets with spatiotemporal Grad-CAM visual attribution. Read more
Recommended citation: S. M. Mohiuddin Khan Shiam, et al. (2026). "Nano3D: An Explainable Ultra-Lightweight Deep Learning Model for Surveillance Video Anomaly Detection." Under review in Scientific Reports, Nature Portfolio.
Download Paper
Published in Department of Computer Science & Engineering, BRAC University, 2026
Undergraduate Academic Thesis at BRAC University benchmarking spatiotemporal architectures across 5 public surveillance benchmarks and proposing Nano3D with Grad-CAM visual interpretability. Read more
Recommended citation: S. M. Mohiuddin Khan Shiam. (2026). "Deep Learning Frameworks for Suspicious Activity Detection." Academic Thesis, Department of Computer Science & Engineering, BRAC University. Supervised by Prof. Dr. Amitabha Chakrabarty & Prof. Dr. Md. Golam Rabiul Alam.
Download Paper
