Communication Hacks
Published:
Mastering practical interpersonal communication, public presentation, technical storytelling, and stakeholder persuasion. Read more
Posts by Collection
certifications
Time Management Fundamentals
Published:
Professional certification from the Project Management Institute on productivity systems, task prioritization, workflow structuring, and deadline management. Read more
Agile Foundations
Published:
Comprehensive training in Agile principles, Scrum workflows, sprint planning, adaptive product management, and continuous delivery. Read more
Enhance Your Leadership Skills
Published:
Professional certification covering team dynamics, empathetic leadership, strategic alignment, and organizational communication. Read more
open_source
Apache Airflow Permalink
Apache · Workflow Management
DAG scheduling improvements and operator implementations. Read more
AutoGen Permalink
Microsoft · Multi-Agent AI
Contributed small optimizations and improvements to multi-agent conversation tooling and its supporting components. Read more
Boltz Permalink
jwohlwend · Biomolecular Interaction Models
Computational structural biology contributions for biomolecular interaction modeling. Read more
Keras Permalink
Keras · Deep Learning Framework
Model architecture improvements and training pipeline enhancements. Read more
kOps Permalink
Kubernetes · Kubernetes Operations
Cluster provisioning automation and cloud integration enhancements. Read more
Kubernetes Permalink
Kubernetes · Container Orchestration
Controller improvements and resource management optimizations. Read more
Manim Permalink
ManimCommunity · Mathematical Animation
Mathematical visualization improvements, animation engine features, and rendering pipeline refinements. Read more
OpenVINO Permalink
OpenVINO Toolkit · AI Inference Toolkit
Neural network inference acceleration and improvements for hardware compatibility. Read more
PowerToys Permalink
Microsoft · Productivity Tools
Contributed UI/UX-oriented improvements and small refinements to help keep day-to-day productivity tools polished and consistent. Read more
scikit-learn Permalink
scikit-learn · Machine Learning Library
Algorithm optimization, documentation improvements, and contributions to estimator implementations. Read more
Windows Terminal Permalink
Microsoft · Command Line
Contributed improvements around performance and shell integration, with attention to maintainability and user-facing behavior. Read more
The Algorithms (Python) Permalink
The Algorithms · Educational Algorithms
Clean algorithm implementations and documentation optimizations for open computer science education. Read more
Ultralytics Permalink
Ultralytics · YOLO Computer Vision
YOLO model performance tuning and deployment optimizations. Read more
vcpkg Permalink
Microsoft · Package Manager
Contributed improvements related to package management workflows and dependency resolution to reduce friction for downstream users. Read more
VS Code Permalink
Microsoft · Code Editor
I contributed small improvements focused on developer experience, including IntelliSense-related refinement and extension API details. Read more
WinGet Permalink
Microsoft · App Installer
Contributed command-line experience improvements and small enhancements around package discovery and usability. Read more
WSL Permalink
Microsoft · Linux Subsystem
Contributed fixes and refinements that support smoother cross-platform development and improve filesystem-related workflows. Read more
portfolio
Autonomous Line Following Hardware Robot
Published:
Autonomous vehicle engineered from fundamental discrete logic gates, IR optical sensors, comparator ICs, and H-bridge motor drivers without microcontrollers. Read more
Comparing Deep Learning and Statistical Models for Stock Price Prediction
Published:
Empirical time-series forecasting evaluating Long Short-Term Memory (LSTM) recurrent neural networks against classical ARIMA statistical models on historical equity data. Read more
SkillShikhi: Collaborative Skill-Sharing & Learning Web Platform
Published:
Full-stack educational and skill-sharing web platform built with Next.js, React, Node.js, and MongoDB featuring JWT authentication, role dashboards, and RESTful APIs. Read more
HybridStack: Interpretable Macro-Financial Forecasting Framework
Published:
Multi-tier hybrid ensemble combining gradient-boosted decision trees with regularized meta-regressors, achieving 0.0006 test RMSE with policy-grade SHAP/LIME interpretability on high-frequency indicators. Read more
Nano3D: Explainable Ultra-Lightweight Deep Learning Model for Video Anomaly Detection
Published:
Resource-efficient 3D-CNN architecture containing only 486K parameters (1.86 MB model size) achieving 88.7% accuracy and 7.19 ms latency on edge devices with spatiotemporal Grad-CAM attribution. Read more
publications
HybridStack: Explainable hybrid ensemble for accurate inflation forecasting with high-frequency macro-financial data
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
Deep Learning Frameworks for Suspicious Activity Detection
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
Nano3D: An Explainable Ultra-Lightweight Deep Learning Model for Surveillance Video Anomaly Detection
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
Hybrid Quantum-Classical Algorithms & Parameterized Quantum Circuits for High-Dimensional Optimization
Published in Ongoing Research Project, 2026
Ongoing research formulating hybrid quantum-classical frameworks, Parameterized Quantum Circuits (PQCs), and Variational Quantum Classifiers (VQCs) using Qiskit and PennyLane for high-dimensional constrained optimization. Read more
Recommended citation: S. M. Mohiuddin Khan Shiam. (2026). "Hybrid Quantum-Classical Algorithms & Parameterized Quantum Circuits for High-Dimensional Optimization." Working Paper / Ongoing Research.
3D Vision Transformers & Deep CNNs for Acute Stroke Lesion Segmentation and Early Oncological Detection
Published in Ongoing Research Project, 2026
Investigating 3D Vision Transformers (ViT) and CNNs for early cancer screening across mammography and histopathology, alongside acute ischemic stroke lesion segmentation from brain CT/MRI scans with Grad-CAM and SHAP interpretability. Read more
Recommended citation: S. M. Mohiuddin Khan Shiam. (2026). "3D Vision Transformers & Deep CNNs for Acute Stroke Lesion Segmentation and Early Oncological Detection." Working Paper / Ongoing Research.