Gazi University AI Center is a research and application institution that develops advanced artificial intelligence, machine learning and deep learning technologies. We strive to create innovative solutions to the most complex industry and research problems. Our goal is to lead the industry in artificial intelligence, machine learning and big data analytics.
Artificial intelligence theory encompasses the foundational concepts and methodologies for simulating human intelligence in machines, including machine learning, neural networks, natural language processing, and computer vision. We research and develop applications in a wide array of fields such as healthcare, where it aids in diagnostics and treatment planning; finance, for algorithmic trading and risk assessment; and autonomous systems.
Machine learning theory encompasses the mathematical foundations and principles that guide the development of algorithms capable of learning from data, including concepts like generalization, overfitting, and the bias-variance tradeoff. We study on machine learning span diverse fields such as natural language processing, computer vision, healthcare, finance, and autonomous systems, where it is used to make predictions, classify data, optimize processes, and generate insights from large datasets, leading to innovative solutions and enhanced decision-making.
Deep learning is a subset of machine learning that utilizes neural networks with many layers to model complex patterns in large datasets. The theory behind deep learning involves concepts from linear algebra, calculus, and statistics, which help optimize network training and improve generalization. We study on applications span various domains, including computer vision (e.g., image classification and object detection), natural language processing (e.g., language translation and sentiment analysis), healthcare (e.g., disease diagnosis through imaging), and autonomous systems (e.g., self-driving cars).
Intelligent systems theory encompasses the study of algorithms, models, and methodologies that enable machines to perform tasks requiring cognitive functions, such as learning, reasoning, and problem-solving. We study on applications of intelligent systems span various fields, including artificial intelligence, robotics, machine learning, natural language processing, and decision support systems. These systems can analyze vast amounts of data, automate processes, enhance human decision-making, and improve efficiencies across sectors like healthcare, finance, transportation, and manufacturing.
Big data analytics refers to the process of examining large and complex data sets to uncover hidden patterns, correlations, and insights that can drive decision-making in various fields. The theory behind big data analytics involves understanding statistical methods, machine learning algorithms, and data mining techniques to process and analyze vast amounts of data efficiently. We study on applications span numerous industries, including healthcare for predictive analytics in patient outcomes, retail for customer behavior analysis, finance for fraud detection, and urban planning for smart city initiatives.
Data science combines statistical analysis, machine learning, data mining, and big data technologies to extract insights and knowledge from structured and unstructured data. Theoretical foundations of data science include probability theory, statistics, linear algebra, and algorithms, which underpin techniques like regression analysis, clustering, and neural networks. We study on applications span various domains, such as finance for fraud detection, healthcare for predictive analytics, marketing for customer segmentation, and transportation for route optimization.
The projects in which academics from our center participate as principal investigator/researcher/advisor are listed below.
The project aims to develop, implement, and evaluate the effectiveness of a "professional training program" enriched with new and innovative interactive digital content for family physicians. This program focuses on improving health literacy in the community, a crucial aspect of healthcare, by equipping them with the knowledge, attitudes, and skills to develop and utilize personalized approach and communication strategies after graduation, enabling them to assess the health literacy level of individuals/patients who seek their care. The project's unique value lies in the fact that such a training program does not currently exist in Turkey, and that it will be developed using innovative, interactive, digital, and evidence-based technology. This project, which will contribute to the career development of both the project team and the target group (family physicians), will also contribute to the improvement of healthcare in Turkey through its widespread adoption and sustainability.
This project aims to facilitate the exchange of information between Gazi AI Center and Vellore Institute of Technology (VIT) in India through course content, projects, trainings, events, and other activities on technology topics, and to enable researchers to share their thoughts and studies on these technologies. In the first phase, staff mobility is planned between Gazi AI Center, GUZEM, and VIT, with 10 staff members each giving lectures and 3 staff members each receiving training.
This project will involve collaboration between Gazi AI Center and Yahia Fares University (YFU). In 2024 and 2025, six doctoral students from YFU visited Gazi AI Center as visiting researchers. This collaboration agreement covers the training of doctoral students in the field of computer engineering and the teaching mobility of academic staff. Five incoming students, two outgoing and four incoming teaching staff, and one incoming and one outgoing training mobility are planned from each level.
This project aims for bilateral or multilateral international project cooperation between Gazi AI Center and King Fahd University of Petroleum and Minerals, as well as doctoral student mobility and faculty mobility in computer engineering. This project plans for 5 outgoing and 5 incoming doctoral students and 3 outgoing and 3 incoming faculty mobility.
Stakeholders of critical industrial and civil infrastructure, e.g., airports, power plants and road networks, frequently suffer from the disruptions caused by an overwhelming diversity of man-made physical safety and security threats ranging from well-organised crime activities to low-level but costly actions like vandalism. SINTRA aims to improve the resilience and protection of these critical infrastructures by developing an open data-streaming AI platform that enables interoperability, information sharing, and privacy protection. Using multi-modal sensing and AI-powered data analysis, it will provide a comprehensive view of the infrastructure’s safety and security and detect complex anomalies.
Read More
The project aims to revolutionise digital twin technology through IoDT2, an open framework that addresses scalability and collaboration challenges. By leveraging serverless edge computing and digital twin-centric networking, IoDT2 enables seamless sharing of distributed models and real-time responsiveness. This approach enhances interoperability, optimises performance, and simplifies digital twin creation, benefiting various industries and promoting widespread adoption.
Read More
The I2DT project aims to create an interoperability framework, methodology and tool support for constructing digital twins that can reflect complex systems with large-scale heterogeneous data and interactions. The project will address core technologies and application domains of interoperable digital twins and apply them to relevant areas like industrial production, smart cities, infrastructure asset management, wildfire protection and renewable energy resources. The project will also advance model-based development, integrate machine learning components, define a unified reference architecture and provide tool support for both engineering and operating digital twins.
Read More
The retail sector plays a crucial role in a country's economy, but needs to undergo a transformation in order to be able to provide a seamless shopping experience, combining online and offline activities, that includes personal recommendations and the continuation of purchases initiated in one channel to the other. CAPE addresses these challenges by using various technologies such as AI, deep learning, blockchain, and IoT to develop personal experiences, improve the performance of robots/kiosks, and offer alternative opportunities and technologies not widely available in today’s market. The targeted impact includes improved customer and employee satisfaction, increased sales, and more efficient store operations.
Read More
The publications of the academics affiliated with our center are listed below.
Assessment of apical patency in permanent first molars using deep learning on CBCT-derived pseudopanoramic images: A retrospective study
Bostancı, S.D., Hatipoğlu Palaz, Z., Özdem Karaca, K., Akcayol, M.A., Bani M.
Bioengineering, DOI: 10.3390/bioengineering12111233, 2025.
AI-driven identity and access management: A hybrid deep learning approach for anomaly detection in enterprise environments
Demirsoy H.B., Akcayol M.A.
7th International Conference on Artificial Intelligence and Applied Mathematics in Engineering, Antalya, Türkiye, October 31 - November 2, 2025.
Selecting generated synthetic features using clustering algorithm for generalized zero-shot learning
Akdemir, E., Barisci, N., Akcayol, M.A., Doğan, N.,
Multimedia Systems, DOI: 10.1007/s00530-025-01979-z, 2025.
Video frame denoising via CNN and GAN methods
Yapıcı A., Akcayol M.A.
KSII Transactions on Internet and Information Systems, DOI: 10.3837/tiis.2025.03.001, 2025.
Hybrid deep learning model for predicting the contribution of SMEs to the economy: A case study for Türkiye
Utku A., Sevinç A., Akcayol M.A.
Journal of Soft Computing and Artificial Intelligence, 2025.
Multiple attention-based deep learning model for MRI captioning
Maraş B., Karatorak S., Özdem Karaca K., Gedik A.O., Akcayol M.A.
Muş Alparslan University Journal of Science, DOI: 10.18586/msufbd.1532112, 2025.
Estimation of market clearing price in day ahead electricity market with RNN based deep learning method
Peker H.P., Batur Sir G.D., Akcayol M.A.
44th National Congress on Operations Research and Industrial Engineering, Ankara, Türkiye, 25-27 June 2025.
Optimizing access point allocation based on genetic algorithm with channel conflict detection
Kocaoğlu R., Calp M.H., Akcayol M.A.
El-Cezeri, DOI: 10.31202/ecjse.1529228, 2025.
Spread patterns of COVID-19 in European countries: Hybrid deep learning model for prediction and transmission analysis
Utku A., Akcayol M.A.
Neural Computing and Applications, DOI: 10.1007/s00521-024-09597-y, 2024.
An ensemble approach for classification of tympanic membrane conditions using soft voting classifier
Akyol K., Uçar E., Atila Ü., Uçar M.
Multimedia Tools and Applications, DOI: 10.1007/s11042-024-18631-z, 2024.
APT-scope: A novel framework to predict advanced persistent threat groups from enriched heterogeneous information network of cyber threat intelligence
Gulbay B., Demirci M.
Engineering Science and Technology, an International Journal, 57, 101791, 2024.
Real time malicious drone detection using deep learning on FANETs
Yapıcıoğlu C., Demirci M., Akcayol M.A.
IEEE International Black Sea Conference on Communications and Networking, Tbilisi, Georgia, June 24–27, 2024.
Optimization of planetary gearbox using nature inspired meta-heuristic optimizers
Top N., Dörterler M., Şahin İ.
Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science, Vol. 238, No. 8, pp. 3338-3347, 2024.
Multimodal fusion for enhanced semantic segmentation in brain tumor imaging: Integrating deep learning and guided filtering via advanced 3d semantic segmentation architectures
Saleh A., Atila Ü., Menemencioğlu O.
International Journal of Imaging Systems and Technology, DOI: 10.1002/ima.23152, 2024.
A novel hybridization approach to improve the critical distance clustering algorithm: Balancing speed and quality
Hamed Kuwil F., Atila Ü.,
Expert Systems with Applications, vol.247, DOI: 10.1016/j.eswa.2024.123298, 2024.
A nested optimization approach for robot gripper multi-objective optimization problem
Dörterler M., Atila Ü., Top N., Şahin İ.
Expert Systems with Applications, vol.239, 1-15, DOI: 10.1016/j.eswa.2023.122163, 2024.
Smart meter-based energy consumption forecasting for smart cities using adaptive federated learning
Abdulla N., Demirci M., Ozdemir S.
Sustainable Energy, Grids and Networks, 38, 101342, 2024.
Neural network based a comparative analysis for customer churn prediction
Utku A., Akcayol M.A.
Muş Alparslan University Journal of Science, DOI: 10.18586/msufbd.1466246, 2024.
Hybrid ConvLSTM model for evaluating the performance of SMEs in the software sector
Utku A., Sevinç A., Akcayol M.A.
Naturengs, Vol.5(1), 2024.
Log anomaly detection in application servers using deep learning
Alagöz E., Şahin Y.M., Özdem K., Gedik A.O., Akcayol M.A.
Innovative Methods in Computer Science and Computational Applications in the Era of Industry 5.0, Vol.1(1), pp.258-268, 2024. (Selected from ICAIAME 2023)
Hybrid deep learning model for earthquake time prediction
Utku A., Akcayol M.A.
Gazi University Journal of Science, DOI: 10.35378/gujs.1364529, 2024.
EMACrawler: Web search engine database freshness optimization
Alanoğlu Z., Akcayol M.A.
Journal of Polytechnic, DOI: 10.2339/politeknik.1347054, 2024.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Gazi Üniversitesi Rektörlüğü |
|
aicenter@gazi.edu.tr Administration:+90 312 202 20 49-50 |
|
|
|||
