Welcome to my GitHub profile! 👋
I'm a passionate developer, AI Engineer, and data science enthusiast dedicated to building innovative solutions that solve real-world problems. With expertise across machine learning, deep learning, and full-stack development, I transform ideas into impactful code.
- 🌍 I'm based in Istanbul, Turkey.
- 🧠 I'm passionate about learning to code and making projects!
- 🎨 I love creating useful and interactive applications.
- 📫 You can reach me at: louisobadiah@gmail.com
- Machine Learning & AI - Building predictive models and intelligent systems
- Deep Learning - CNN, RNN, and neural network architectures
- Data Analysis & Visualization - Turning data into actionable insights
- Full-Stack Development - Creating end-to-end solutions
- Python Development - Core proficiency across ML/AI stack Technologies: TensorFlow, Keras, Python, Jupyter
Languages: Python, JavaScript, SQL, R, HTML & CSS, and React.
ML/DL Frameworks: TensorFlow, Keras, scikit-learn, pandas, NumPy.
Data Tools: Jupyter Notebook, Matplotlib, Seaborn.
Other: Git, REST APIs, Git.
Two CNN image classification projects were recently completed and merged into this repository.
File: brain_tumor_cnn_classification.ipynb
PR: #1 — Add Brain Tumor MRI CNN Classification Jupyter Notebook — ✅ Merged
Domain: Medical (Brain Tumor MRI — distinct domain)
Approach: Custom CNN + MobileNetV2 transfer learning, data augmentation, performance evaluation (accuracy, precision, recall, F1, confusion matrix, learning curves).
File: cnn_image_classification.ipynb
PR: #2 — Add EuroSAT CNN image classification notebook — ✅ Merged
Domain: Satellite imagery (EuroSAT — 10 land-use classes, completely distinct domain)
Approach: Custom CNN + MobileNetV2 transfer learning, controlled experiments (augmentation effect, optimizer comparison, fine-tuning), full rubric coverage.
File: brain_tumor_feature_classification.py
Traditional feature extraction (HOG, LBP, Sobel edges) + ML classifiers (SVM, Random Forest, k-NN, Logistic Regression) on the Brain Tumor dataset.
Copy each # %% block into a VS Code Jupyter cell or Jupyter Notebook cell and run directly.
Dataset path already set to: C:\Users\louis\Desktop\ML Project\brain_tumor_dataset.
| Step | What to do |
|---|---|
| Open PRs | Go to https://github.com/lobadiah/lobadiah/pulls |
| Closed / Merged PRs | Click the Closed tab on the Pull Requests page |
| Merged notebooks | Once a PR is merged, its files appear directly in the repository's file list on the main branch |
| PR history | Each PR page (e.g. #1, #2) shows the full diff, review comments, and merge timestamp |
| Specific file | Click any .ipynb file in the repo to view it rendered in GitHub's notebook viewer |
Note: Both CNN projects (PR #1 and PR #2) are already merged. Their notebooks are live in the
mainbranch and visible in this repository right now.
Lead Author
Obadiah, L. A., Godwin, D., Edward, N. M., Abubakar, N. M., Daniel, J., & Titus, D. K. (2026). Bias and Fairness in AI Systems: Theoretical Analysis and Empirical Validation Through Reweighing Mitigation. In Proceedings of the 8th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA 2026). Ankara, Türkiye, May 21–23, 2026. IEEE. (Paper ID: 581) [Oral Presentation]
Co-Author
Daniel, J., Wilson, S., Edward, N. M., Ishaya, C., Musa, Z. S., Augustine, V., Bello, Y. G., Obadiah, L. A., & Titus, D. K. (2026). Explainable Prediction of Daily Stress and Sleep Quality from Passive Smartphone Behavioral Sensing: A SHAP-Based Analysis of the StudentLife Dataset. In Proceedings of the 8th International Congress on Human-Computer Interaction, Optimization and Robotic Applications (ICHORA 2026). Ankara, Türkiye, May 21–23, 2026. IEEE. (Paper ID: 569) [Oral Presentation]
I'm always interested in collaborating on innovative projects and discussing the latest in tech!
- 🔬 Working on advanced machine learning models
- 📚 Continuously learning and experimenting with new technologies
- 🤖 Exploring deep learning applications in healthcare
