I'm a Postdoctoral Researcher in AI Agents at Ariel University, Israel, with a core mission: transforming research into real-world impact. I believe that research only has true value when it moves beyond academic papers to create tangible solutions that benefit society. My current work focuses on developing advanced AI agents capable of adaptive reasoning, autonomous decision-making, and human–AI collaboration, integrating machine learning, natural language processing, and multi-agent systems for dynamic and complex environments.

• 🤖 AI Agent Development: Designing AI agents with enhanced interpretability and trustworthiness for adaptive reasoning and autonomous decision-making
• 🤝 Human-AI Collaboration: Developing frameworks for human–AI interaction and cooperative problem-solving in complex environments
• 🔄 Multi-Agent Systems: Investigating multi-agent coordination and emergent behaviors in real-world scenarios
• 🏥 Applied AI Research: Applying AI agent architectures to domains such as education, healthcare, and computational social science
• 🦙 LLM & RAG Systems: Exploring Large Language Model applications with LangChain, LangSmith, LangGraph, and LlamaIndex for intelligent document processing

• 🇮🇱 Postdoctoral Researcher @ Ariel University (2025-Present)
• 🇮🇩 Assistant Professor @ Nusa Putra University (2024-August 2025)
• 🇨🇳 Lecturer @ Zhejiang A&F University (2023-2024)
• 🇹🇷 Postdoc Researcher @ Sabanci University (2021-2022)
• 🇰🇷 PhD @ Sungkyunkwan University (2016-2021)

I firmly believe that the true measure of research success is not in publications alone, but in how effectively we translate theoretical discoveries into practical solutions. My approach to research follows a clear principle:

🔬 Research → 🛠️ Development → 🚀 Implementation → 🌍 Impact

• 🎯 Purpose-Driven: Every project targets a real-world problem
• 🔄 Iterative Approach: Continuous feedback from practical implementation
• 🤝 Collaboration: Working with industry to ensure applicability
• 📈 Measurable Impact: Success measured by real-world adoption and effectiveness

• Smart Cities: AI-powered waste management systems
• Network Optimization: SDN solutions for IoT infrastructure
• User Experience: QoE models for mobile gaming platforms
• Education: Practical big data courses for industry readiness

mindmap
  root((Core Technologies))
    AI/ML Architectures
      Hybrid Attention-Gated U-Net
      Deep Reinforcement Learning
      Hidden Markov Models
      Fuzzy Logic Systems
    SDN Technologies
      Q-Learning Flow Placement
      Proactive Eviction Algorithms
      Predictive Mobility Models
      Cost-Aware Optimization
    Advanced Analytics
      Quality of Experience Prediction
      Machine Learning Model Evaluation
      Statistical Performance Analysis
      Big Data Processing Pipelines
    Research Infrastructure
      Network Simulation (ns-3, Mininet)
      Distributed Computing
      IoT Network Architectures

• Machine Learning Integration: Applying advanced ML techniques to network optimization problems
• Hybrid Model Development: Combining attention mechanisms with reinforcement learning for dynamic classification
• Predictive Analytics: Developing Q-learning approaches for mobility-aware network management
• Performance Optimization: Creating proactive algorithms for SDN flow table management

• Network Simulation: ns-3, Mininet for large-scale network modeling
• Machine Learning Pipeline: TensorFlow, PyTorch for deep learning implementations
• Data Analytics: R, MATLAB, Apache Spark for big data processing
• Performance Evaluation: Statistical analysis, hypothesis testing, model validation

1. Predictive mobility and cost-aware flow placement in SDN-based IoT networks: a Q-learning approach (2024)
   Journal of Cloud Computing - SCIE Q2 | Machine Learning + SDN Integration

2. Deep Learning-Based QoE Prediction for Streaming Services in Mobile Networks (2022)
   WiMob Conference - CORE Tier C, QUALIS Tier B1 | Neural Network Performance Prediction

3. Proactive eviction of flow entry for SDN based on hidden Markov model (2020)
   Frontiers of Computer Science - SCIE Q1 | Probabilistic Network Optimization

• 2 SCIE Journal Publications (Q1-Q2 Impact Factor)
• 4 International Conference Papers
• Advanced ML Techniques: Hidden Markov Models, Deep Reinforcement Learning, Q-Learning, Fuzzy Logic
• Technical Domains: SDN, IoT, Computer Vision, Quality of Experience, Network Security