🔬 ML Researcher | IoT & Data Science Enthusiast | 2x Published Author | IT Specialist/Lab Engineer @ SCET 📍 Wah Cantonment, Pakistan 📧 muhammadhassaannaeem426@gmail.com 🔗 LinkedIn

Machine learning researcher with a focus on supervised learning and organisational analytics. Published in Elsevier (Ain Shams Engineering Journal) and ASCE. Currently working as IT Specialist and Lab Engineer at Swedish College of Engineering and Technology.

Open to research collaborations, applied ML and IoT projects.

📄 Evaluating the correlation between project selection criteria and organizational performance within the construction industry Ain Shams Engineering Journal, Elsevier · 2024 DOI: 10.1016/j.asej.2024.102794

📄 Impact of Project Selection Criteria on Organizational Performance: A Machine Learning Approach ASCE Inspire Conference Proceedings · 2023 DOI: 10.1061/9780784485163.016

• AI & Machine Learning: Python (Scikit-learn, TensorFlow, PyTorch), SVM, KNN, Predictive Analytics.
• IoT & Research: IoUT Protocols, Thorp's Acoustic Model, Edge AI, MQTT, Sensor Telemetry.
• Software Engineering: SQL (MySQL/SQLite), Tkinter GUI, GitHub Actions (CI/CD), Pytest.
• Hardware: Dell Precision & HP Z-series Workstations, Nvidia Quadro/AMD Radeon Pro optimization.

AquaSense is a complete, reproducible simulation framework designed to evaluate Energy-Efficient Clustering-Based Routing Protocols for the Internet of Underwater Things (IoUT).

Built as the core of my research thesis, it uses Machine Learning to predict node failures and optimizes energy consumption in deep-sea environments.

• Physics-Based Energy Modeling: Implements Thorp’s Acoustic Absorption Formula to calculate real-world signal degradation and per-round energy costs.
• Predictive Maintenance: Integrated ML models (SVM/KNN) that predict battery depletion and sensor malfunction with high accuracy.
• Scientific Reproducibility: Includes a protocol_comparison.csv generator to independently verify every metric, figure, and table presented in my research.
• Robust Engineering: 39+ automated tests and a GitHub CI/CD pipeline ensuring stability across Python 3.9–3.12.

• Language: Python 3.9+
• Mathematics & Data: Pandas, NumPy, Scikit-learn
• DevOps: GitHub Actions (CI/CD), Pytest
• Visualization: Matplotlib (Publication-quality PNG charts)

The IoT Sensor Analyzer is a robust Python utility designed to ingest, clean, and visualize data from distributed sensor networks. This tool serves as the analytical bridge between raw hardware output and high-level research insights.

• Dynamic Visualization: Generates real-time time-series plots for temperature, humidity, and energy metrics.
• Anomaly Detection: Basic statistical filtering to identify "noisy" or failing sensors.
• Data Export: Streamlines the transition from live sensor data to CSV/JSON formats for Machine Learning training.
• Scalable Processing: Optimized for handling large datasets from multi-node environments.

• Engine: Python 3.x
• Analysis: Pandas, NumPy
• Graphics: Matplotlib, Seaborn

Dizionario v2.0 is a specialized tool built to bridge the gap between traditional dictionaries and personal language learning. It allows users to build a custom database of vocabulary, specifically tailored for achieving native-level proficiency in Italian.

• Persistent Storage: Integrated with SQL to store and categorize words, definitions, and example sentences.
• Dynamic Search: High-performance search functionality to retrieve words in real-time.
• CRUD Operations: Full capability to Create, Read, Update, and Delete entries as your language level progresses.
• User-Friendly GUI: Built with Tkinter for a lightweight, desktop-native experience.

• Frontend: Python (Tkinter)
• Backend: SQL (MySQL/SQLite)
• Concepts: Database Management, CRUD Lifecycle, Event-Driven Programming

• 💼 Lab Engineer @ Swedish College of Engineering & Technology
• 🔍 Seeking MS/PhD / Research Assistant opportunities
• 📚 Exploring deep learning in organisational analytics