KKT-ML-Models

🧠 KKT-ML-Models

This repository serves as a centralized suite of machine learning models developed and trained by Dr.K.K. Thyagharajan for research, experimentation, and deployment across multiple domains. The repository is organized by application domain, with each domain containing one or more trained models, preprocessing pipelines, and documentation.

The repository supports:

• Reproducible research
• Model reuse and deployment
• Separation of preprocessing and inference artifacts
• Compatibility with Hugging Face Spaces and APIs

🔍 Domains Covered

• Diabetes prediction (tabular clinical data)
• Additional healthcare and ML domains will be added incrementally

---

📂 Repository Structure

KKT-ML-Models/
│
├── README.md
│
└── diabetic_models/
    │
    ├── README.md
    │
    ├── logistic_reg_diabetic.pkl
    │   (Baseline batch Logistic Regression model)
    │
    └── SGD_scaler_diabetic_models/
        │
        ├── README.md
        │
        ├── SGD_model.pkl
        │   (Final SGD-based logistic regression classifier)
        │
        └── SGD_scaler.pkl
            (Fitted StandardScaler used during training)

---

📦 Model Collections

Each subdirectory corresponds to a domain-specific model collection.

Models are released with:
- Serialized artifacts
- Explicit preprocessing components
- Clear inference documentation
- Licensing and citation metadata

---

🧰 Technology Stack

• Python ≥ 3.8
• scikit-learn
• numpy
• pandas
• joblib

---

📜 License

This repository is released under the MIT License.
See the LICENSE file for full terms.

---

📖 Citation

If you use these models in academic work, please cite using the CITATION.cff file.

---

👨‍💻 Maintainer

Dr. Thyagharajan K K
Professor & Dean (Research)
RMD Engineering College
📧 [email protected]