Research & Innovation
Welcome to my comprehensive research portfolio. Here, you'll find an in-depth look at my ongoing investigations into Reinforcement Learning, Graph Neural Networks, and Intelligent Systems. My goal is to build scalable, robust, and adaptive AI for complex real-world environments.
Current Research
Adaptive Evacuation:
A GNN-Enhanced Deep Reinforcement Learning Framework for Intelligent Indoor Emergency Response
Research Problem
Research Motivation
Methodology
Current Progress
- Literature Review Completed
- Environment Design Completed
- GCN Integration In Progress
- Experimental Evaluation Ongoing
- Manuscript Preparation Ongoing
"Developing graph-enhanced reinforcement learning methods capable of improving intelligent decision-making for dynamic indoor emergency response."
Research Journey
"My research journey has evolved from building strong computer science foundations to pursuing intelligent systems capable of learning, reasoning, and adapting within dynamic real-world environments."
Computer Science Foundations
Started my journey in Computer Science by building a strong foundation in programming, data structures, algorithms, operating systems, databases, and computer networks while exploring software development.
Applied AI & Development
Completed AI and Software Development internships, gaining experience with LangChain, large language models, full-stack development, and intelligent application design.
INEC Laboratory Intern
Joined the Intelligent Networks & Edge-Cloud Computing (INEC) Laboratory at Yuan Ze University, Taiwan, as an NSTC International Internship Pilot Program (IIPP) Research Intern. Transitioned from software development toward research in Artificial Intelligence.
Advanced AI Specialization
Studied Reinforcement Learning, Deep Reinforcement Learning, Graph Neural Networks, PyTorch, and intelligent decision-making systems.
Adaptive Emergency Response
Developing a Graph Convolutional Network enhanced Deep Q-Network framework for adaptive indoor emergency response. Research manuscript currently in preparation.
Graduate Research Aspirations
Pursuing a fully funded research-oriented Master's degree to continue research in Reinforcement Learning, Graph Learning, and Intelligent Systems, with the long-term goal of contributing to trustworthy AI research.
Research Methodology
Problem Formulation
Rigorous mathematical modeling of real-world dynamic environments into formal reinforcement learning setups.
Algorithmic Design
Developing novel hybrid architectures integrating representation learning (GNNs) with sequential decision making (RL).
Empirical Evaluation
Extensive simulation in Gymnasium, benchmarking against baselines, and ablation studies for theoretical validation.
Selected Research & AI Projects
My projects focus on applying artificial intelligence and machine learning techniques to solve practical problems while strengthening my research experience through implementation, experimentation, and system development.
Adaptive Evacuation: A GNN-Enhanced Deep Reinforcement Learning Framework
Developing a hybrid Graph Neural Network and Deep Reinforcement Learning framework for adaptive indoor emergency response. This approach bridges theoretical RL with real-time execution in IoT-enabled environments.
MindMate: AI-Assisted Mental Wellness Platform
AI-assisted mental wellness platform integrating conversational AI, journaling, mood tracking, and personalized recommendations. Built to explore human-centered LLM interactions.
Candidate Profile Transformer
Intelligent document analysis system for extracting structured information and generating explainable candidate profiles using language models.
"These projects represent my progression from applied AI development toward research-driven intelligent systems."
Research & Technical Expertise
My research combines computer science fundamentals with modern artificial intelligence techniques to design, implement, and evaluate intelligent systems.
Programming Languages
Programming languages used for research, experimentation, and software development.
Artificial Intelligence & Machine Learning
Machine learning techniques and intelligent decision-making methodologies explored through research and implementation.
Research & Scientific Computing
Frameworks and libraries used for developing and evaluating AI models.
Software Engineering
Building scalable software systems and intelligent applications.
Development Tools
Tools supporting collaborative development and experimentation.
Research Practices
Core research activities performed during academic projects.
"My expertise continues to evolve through research, experimentation, and interdisciplinary collaboration in artificial intelligence and intelligent systems."
Education & Academic Profile
My academic journey has provided a strong foundation in computer science while supporting my transition toward research in artificial intelligence and intelligent systems.
Sri Eshwar College of Engineering
Relevant Coursework
Academic Highlights
- Research Intern at Yuan Ze University, Taiwan
- Active research in Reinforcement Learning and Graph Neural Networks
- Current manuscript in preparation for IEEE International Conference on Intelligent Environments
- Strong foundation in Computer Science fundamentals
"My academic foundation continues to support my research through continuous learning, experimentation, and interdisciplinary collaboration."
Research Roadmap
Undergraduate Research
Finalizing GNN-DRL framework for indoor evacuation. Submitting manuscript to IEEE Intelligent Environments.
Master's Preparation
Expanding research into multi-agent reinforcement learning (MARL) and edge computing.
PhD Vision
Focusing on Trustworthy AI, safe exploration in RL, and scalable foundation models for sequential decision-making.
Future Directions
As AI systems become increasingly integrated into physical and social environments, the need for models that can act reliably under uncertainty grows. My future research will pivot toward:
- Multi-Agent Reinforcement Learning in decentralized edge networks.
- Safe and Interpretable RL for mission-critical applications.
- Integration of Foundation Models with Graph Structured Knowledge.