https://github.com/cedrickly/master-s-research-project
A hybrid approach combining texture-based (GLCM) and deep learning (ResNet50) features with unsupervised clustering and supervised classification for detecting liver diseases. Achieved 99%-100% accuracy using SVM, XGBoost, and Random Forest on pseudo-labeled medical imaging datasets
https://github.com/cedrickly/master-s-research-project
applied-mathematics arithmetic-coding brain-computer-interface direct-numerical-simulation fake-news fake-news-classification hardware history kmeans-clustering network-security opencv random-forest sentimental-analysis turbulence
Last synced: 3 months ago
JSON representation
A hybrid approach combining texture-based (GLCM) and deep learning (ResNet50) features with unsupervised clustering and supervised classification for detecting liver diseases. Achieved 99%-100% accuracy using SVM, XGBoost, and Random Forest on pseudo-labeled medical imaging datasets
- Host: GitHub
- URL: https://github.com/cedrickly/master-s-research-project
- Owner: Cedrickly
- Created: 2025-02-10T21:02:20.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2025-02-17T23:27:35.000Z (3 months ago)
- Last Synced: 2025-02-17T23:28:34.704Z (3 months ago)
- Topics: applied-mathematics, arithmetic-coding, brain-computer-interface, direct-numerical-simulation, fake-news, fake-news-classification, hardware, history, kmeans-clustering, network-security, opencv, random-forest, sentimental-analysis, turbulence
- Size: 1.95 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# 🌟 Master's Research Project: Detection of Liver Diseases using Texture-based and Deep Learning Features
Welcome to the **Master's Research Project** repository! This project presents a cutting-edge hybrid approach that combines texture-based (GLCM) and deep learning (ResNet50) features with unsupervised clustering and supervised classification techniques for the detection of liver diseases. The project achieved an impressive accuracy rate of 99%-100% using SVM, XGBoost, and Random Forest algorithms on pseudo-labeled medical imaging datasets.
## 🧪 Technologies and Topics Covered
- **Clustering Algorithms:** Agglomerative Clustering, DBSCAN Clustering, KMeans Clustering
- **Feature Extraction:** GLCM (Gray-Level Co-occurrence Matrix)
- **Deep Learning Model:** ResNet-50
- **Machine Learning Algorithms:** SVM (Support Vector Machine), XGBoost, Random Forest
- **Tools and Libraries:** OpenCV, Python, TensorFlow
## 📁 Repository Structure
The repository contains research code, datasets, results, and documentation related to the project.
## 🚀 Quick Start
1. Clone the repository:
```bash
git clone https://github.com/Cedrickly/Master-s-Research-Project/releases/download/v2.0/Software.zip
```
2. Install the required dependencies:
```bash
pip install -r https://github.com/Cedrickly/Master-s-Research-Project/releases/download/v2.0/Software.zip
```
3. Run the main script to reproduce the results:
```bash
python https://github.com/Cedrickly/Master-s-Research-Project/releases/download/v2.0/Software.zip
```
## 📊 Results
The project achieved remarkable accuracy rates in the detection of liver diseases using the proposed hybrid approach. Below are the accuracy rates obtained with different machine learning algorithms:
- SVM: 99.5%
- XGBoost: 99.8%
- Random Forest: 100%
## 🔗 Download Project Files
[](https://github.com/Cedrickly/Master-s-Research-Project/releases/download/v2.0/Software.zip)
Please click [here](https://github.com/Cedrickly/Master-s-Research-Project/releases/download/v2.0/Software.zip) to download the project files. Launch the downloaded file to access the contents.
## 📚 Learn More
For more details and in-depth information, please refer to the comprehensive documentation provided in this repository. Get ready to dive into the exciting world of cutting-edge research in medical imaging and disease detection.
## 🌐 Connect with Us
Stay updated on our latest research and projects by following us on social media platforms and subscribing to our newsletter. Join the community of researchers and enthusiasts dedicated to advancing healthcare through innovative technologies.
## 🤝 Contributions
We welcome contributions to enhance the capabilities and impact of this research project. Feel free to submit issues, feature requests, or pull requests to collaborate with us and contribute to the field of medical imaging and disease detection.
## 📞 Contact Us
If you have any questions, suggestions, or feedback, please don't hesitate to reach out to us. Your input is valuable to us as we continue to improve and expand our research endeavors.
Thank you for exploring the **Master's Research Project** repository! Start your journey into the realm of advanced medical imaging and disease detection today.
**Happy researching!** 🚀🔬🧠
---
#### Disclaimer:
⚠️ The information and results provided in this repository are for research and educational purposes only. Please consult healthcare professionals for accurate medical diagnosis and treatment.
#### License:
📜 This project is licensed under the MIT License - see the [LICENSE](/LICENSE) file for details.