https://github.com/arash-keshavarz/portfolio

https://github.com/arash-keshavarz/portfolio

Science Score: 26.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.6%) to scientific vocabulary
Last synced: 9 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: Arash-Keshavarz
  • Language: HTML
  • Default Branch: main
  • Size: 10.5 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 11 months ago · Last pushed 11 months ago
Metadata Files
Readme

README.md

👋 Hi, I'm Arash Keshavarz

🎯 Aspiring Machine Learning Engineer passionate about building intelligent systems that solve real-world problems using data. I have hands-on experience in computer vision, signal processing, time-series analysis, and scientific ML research.

📍 Based in Rostock, Germany | 📧 arash.keshavarz.dev@gmail.com
🌐 LinkedInGitHubUdacity Certificate


💼 About Me

  • 🎓 M.Sc. in Electrical Engineering and Computer Science @ University of Rostock
  • 🧠 2+ years of Python experience in ML, Deep Learning, and EIT-based medical data analysis
  • 🔬 Currently researching bruise evolution via hyperspectral imaging at Fraunhofer IGD
  • 🛠️ Experienced with Python, PyTorch, TensorFlow, OpenCV, Docker, and AWS

🔬 Featured Projects

🔹 Thigh Muscle Force Estimation using EIT

Master's thesis project combining electrical impedance tomography with ML models to estimate muscle force.

  • 🧪 Acquired and processed synchronized EIT and torque data from 15 participants (~80,000 samples)
  • 📊 Achieved 91% classification accuracy using Random Forest and SVM models
  • 🔧 Tools: Python, Scikit-learn, PCA, Custom GUI (Tkinter)

🔹 Y-Net for EIT Image Reconstruction

Developed a convolutional Y-Net model to enhance image quality in EIT-based bone imaging.

  • 📈 Outperformed classical methods with 89% SSIM
  • 🔬 Focused on detecting conductivity shifts around hip implants
  • 🔧 Tools: MATLAB, Python, PyTorch, EIDORS

🔹 Bruise Age Estimation with Hyperspectral Imaging

Fraunhofer IGD research project on medical image analysis.

  • 🌈 Analyzed 204-band hyperspectral images to track bruise evolution
  • 🧠 Applied PCA/t-SNE and spectral classifiers (SAM, SVM)
  • 📉 Reduced feature space by 90% while achieving 90% prediction accuracy

🛠️ Skills Snapshot

| Category | Tools & Technologies | |------------------|----------------------| | Languages | Python, Java, MATLAB, c++ | | Frameworks | PyTorch, TensorFlow, Scikit-learn | | CV/ML Tools | OpenCV, Torchvision, Albumentations | | Deployment | Docker, Gradio, Streamlit | | Data Tools | MongoDB, NumPy, Pandas | | Cloud | AWS, Google Colab | | Others | Git, GitLab, Linux, Jupyter |


📫 Get in Touch


This portfolio is built using GitHub Pages — check out the source code or connect to collaborate on cool projects!

Owner

  • Name: Arash
  • Login: Arash-Keshavarz
  • Kind: user

GitHub Events

Total
  • Watch event: 1
  • Push event: 7
  • Create event: 1
Last Year
  • Watch event: 1
  • Push event: 7
  • Create event: 1