Research
My current research can be broadly described as Engineering Applications of Artificial Intelligence. I am particularly interested in developing intelligent systems that combine Artificial Intelligence, Machine Learning, Deep Learning, Computer Vision, Generative AI, Large Language Models, data-driven methods, and modern software architectures to solve practical engineering and societal problems.
My recent work focuses on deployable AI systems rather than algorithms in isolation. This includes intelligent transportation, industrial visual inspection, AI-assisted healthcare, personalized intelligent applications, and computing infrastructures for Artificial Intelligence and Data Science. A recurring objective is to bridge machine-learning models with complete engineering systems that can operate in real-world environments.
Research activities are closely connected with my teaching, student supervision, software and systems engineering background, and experience in academic and industrial R&D.
Current Research Areas
Engineering Applications of Artificial Intelligence
The central theme of my current research is the design, implementation, and evaluation of AI-enabled engineering systems. I am interested in integrating machine-learning models with software platforms, sensing and data-processing pipelines, user interfaces, decision-support mechanisms, and real-world operational requirements. The emphasis is on practical, deployable, explainable, and maintainable intelligent systems rather than isolated predictive models.
Computer Vision and Intelligent Transportation Systems
Current work in computer vision includes real-time vehicle detection, traffic analytics, intelligent intersection management, road-rule violation detection, object tracking, and visual decision-support systems.
Recent studies investigate deep-learning-based traffic analysis using modern object-detection models and practical deployment pipelines. Applications include adaptive traffic intersection control and the automatic detection of vehicles violating hatched road areas.
Industrial AI and Intelligent Visual Inspection
I am interested in applying deep learning and computer vision to industrial inspection, defect detection, quality control, and intelligent manufacturing.
Recent work explores explainable and robustness-aware surface defect classification together with AI-assisted reporting. An important research direction is combining visual classification with decision-support mechanisms and natural-language explanations.
Generative AI, Large Language Models and AI Agents
My current interests include Generative Artificial Intelligence, Large Language Models, intelligent agents, AI-assisted software systems, and the integration of LLMs with domain-specific applications.
Research topics include personalized intelligent assistants, AI-assisted reporting, natural-language interfaces, knowledge-supported applications, and agent-based systems that combine language models with application logic and structured data.
Recent student research includes an LLM-agent-based personalized fitness coaching platform and an AI-assisted web-based flashcard generation system.
Artificial Intelligence in Healthcare
Healthcare is another important application domain of my recent research. Current interests include machine learning for clinical decision support, temporal patient monitoring, risk prediction, explainable AI, medical image analysis, and intelligent mobile health applications.
Recent work includes AI-assisted temporal oncology monitoring with multiple risk models, as well as deep-learning-based applications for medical diagnosis and health-related decision support.
Machine Learning, Deep Learning and Applied Data Science
Machine Learning and Deep Learning provide the methodological foundation for many of my current projects. My interests include supervised learning, neural networks, transfer learning, feature engineering, model evaluation, explainability, robustness, and practical model deployment.
These techniques are applied across transportation, healthcare, industrial inspection, intelligent mobile applications, and other engineering domains.
AI Computing Infrastructure, Cloud Computing and Big Data
My research interests also include the computing infrastructure required to develop and deploy modern Artificial Intelligence systems.
This includes AI workstations, GPU-based computing, Artificial Intelligence and Data Science laboratories, cloud computing, distributed data processing, big-data platforms, and software environments for machine-learning research and education.
Recent Research and Project Examples
- Adaptive Intersection Control and Traffic Analytics: Development of a deployable dual-mode computer-vision framework combining vehicle detection, traffic analysis, and adaptive intersection control.
- Computer Vision-Based Traffic Violation Detection: Detection of vehicles violating hatched road areas in Istanbul traffic using object detection, geometric reasoning, and video analytics.
- RobustDefect-LLM: Explainable and robustness-aware industrial surface defect detection integrating computer vision, decision support, and AI-assisted natural-language reporting.
- OncoGuard-AI: An AI-assisted temporal oncology monitoring and multi-risk clinical decision-support system combining patient data, temporal monitoring, machine-learning risk models, and explainability.
- FitTracker: Personalized fitness coaching through the integration of Large Language Models, intelligent agents, user data, and application-level decision logic.
- AI and Data Science Research Laboratory Infrastructure: Design and development of hardware and software infrastructure for Artificial Intelligence, Data Science, Cloud Computing, and Big Data education and research.
Earlier and Continuing Research Areas
My current work builds on several earlier research areas in computer engineering. These topics remain part of my broader academic background and continue to influence my work in intelligent systems.
Software Engineering and Software Architectures
Research and teaching have included software architecture, object-oriented design, design patterns, requirements engineering, software processes, software quality, enterprise application development, service-oriented architectures, and software project management.
This background is increasingly relevant to AI systems, where reliable software architecture, requirements, testing, maintainability, and lifecycle engineering are essential for moving AI prototypes into production.
Distributed Systems, Cloud Computing and Big Data
Earlier work includes distributed computing, distributed applications, cloud computing, data-intensive systems, and big-data technologies. These areas now provide an important systems foundation for scalable Artificial Intelligence and data-driven engineering applications.
Computer Networks, Mobile and Wireless Computing
My research has covered computer networking, mobile and wireless networks, network programming, wireless protocol development, network performance analysis, network management, and security. Related work included IEEE 802.11-based systems, delay-sensitive wireless communication, telerobotics, and networked intelligent applications.
Pervasive and Context-Aware Computing
Earlier research investigated context-aware services, mobile context handoff, pervasive computing, service-oriented middleware, wireless positioning, and intelligent mobile applications. Many of these ideas have natural connections with today's AI-powered context-aware assistants and intelligent edge applications.
Intelligent Healthcare and Decision Support
Earlier work investigated neural-network-based disease diagnosis and pervasive healthcare applications. This research direction now continues through modern Machine Learning, Deep Learning, explainable AI, and clinical decision-support systems.
Digital Signal Processing and Parallel Computer Architectures
My earlier research included Digital Signal Processing, real-time filtering, multiprocessor scheduling, parallel and pipelined computer architectures, DSP software environments, and specialized processor systems. This work established a long-term interest in efficient computing architectures for computationally demanding engineering applications.
Microprocessors, Embedded Systems and Computer Hardware
Research and teaching have included microprocessors, microcontrollers, embedded systems, computer interfacing, computer architecture, and hardware/software integration. These topics remain relevant to edge AI, robotics, intelligent sensing, and embedded Artificial Intelligence applications.
Research and Teaching
My research and teaching activities are closely connected. Recent courses include Artificial Intelligence, Machine Learning, Deep Learning, Generative Artificial Intelligence, Data Structures and Algorithms for AI-oriented applications, Software Engineering, Software Requirements Engineering, and Graduation Project.
Project-based education provides an important environment for exploring new AI applications, evaluating emerging technologies, and transforming student projects into research prototypes and publications.
Publications
For journal articles, conference papers, books, book chapters, preprints, and other publications, please visit my Publications page.