Skip to content
View karsterr's full-sized avatar
157 followers · 234 following

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: YOLOAchievement: QuickdrawAchievement: Pull Shark

Highlights

  • Pro

Block or report karsterr

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
karsterr/README.md

👋 Hi, I'm Efe Can Kara

Typing SVG

"The best way to predict the future is to invent it."

— Alan Kay


🚀 About Me

I'm a Computer Engineering student passionate about building efficient, scalable, and data-driven systems. My work sits at the intersection of Advanced Data Analytics and High-Performance System Architecture.

I approach engineering problems from two perspectives:

🔬 As an Analyst — Extracting meaningful insights from complex datasets using MATLAB and Python (ML, NLP)

⚙️ As a System Architect — Optimizing infrastructure with Linux, Docker, and C++ to ensure maximum performance


🛠️ Tech Stack & Expertise

Data Science & Analytics

📊 MATLAB          ████████████████░  95%
🐍 Python          ███████████████░░  90%
📈 Pandas/NumPy    ██████████████░░░  85%
🤖 ML/NLP          ████████████░░░░░  75%
📉 Statistical     ███████████████░░  88%

Systems & DevOps

🐧 Linux           ████████████████░  95%
🐳 Docker          ██████████████░░░  85%
⚡ C/C++           ███████████████░░  90%
🔧 Bash Scripting  ████████████████░  92%
🖥️  Raspberry Pi    ███████████░░░░░  70%

🎯 Featured Projects

🧠 AI & Machine Learning
  • FisheryAI — Edge-AI LSTM system for fisheries time-series analysis with Turkish NLP report generation
  • MATLAB Emotion Analysis — Comparative study: hand-coded vs. app-generated emotion classification models
  • VectorWise — High-performance ANN search engine using FAISS/Annoy for vector similarity
🔬 Data Analysis & Geospatial
  • GPR Analysis Tool — Ground Penetrating Radar data processing & porosity model validation toolkit
🔐 Security & Infrastructure
  • LLM Security Proxy — RAG system firewall for prompt injection & PII leak detection (Not Planned Yet)
  • Technical Lessons — Curated resources on algorithms, AI, cybersecurity & system architecture (Not Planned Yet)

🌱 Currently Learning

  • Advanced Docker orchestration & Kubernetes
  • Real-time data streaming architectures
  • Embedded Linux optimization techniques

💬 Let's Connect

I'm always open to collaborating on projects where I can apply my analytical skills to solve real-world problems.

Email LinkedIn GitHub


Profile Views

Open Source Enthusiast • Linux Poweruser • Data-Driven Problem Solver

Building scalable systems, one algorithm at a time 💻

Pinned Loading

  1. MATLAB-Code-vs-App-Emotion_Analysis MATLAB-Code-vs-App-Emotion_Analysis Public

    A comprehensive comparison between manually coded MATLAB models and models generated using MATLAB's Classification Learner app for emotion analysis.

    MATLAB

  2. VectorWise VectorWise Public

    Implements an Approximate Nearest Neighbor (ANN) search engine using Faiss/Annoy for fast vector retrieval, demonstrating optimization and high-dimensional data handling.

    Python

  3. envytui envytui Public

    TUI session manager for NVIDIA Optimus laptops on Linux

    Shell

  4. FisheryAI FisheryAI Public

    Edge-AI powered Data-to-Text system that analyzes global fishery trends (Capture, Aquaculture, Stocks) and generates automated status reports offline using LSTM & TensorFlow Lite.

    Python