Centre for Applied Artificial Intelligence

Mission

Artificial intelligence (AI) has applications in many different fields. AI has become applicable in practical life mainly because of the advancements in machine/deep learning algorithms, the development of high-speed computer processors, the spread of cloud systems, and the availability of large amounts of data. Integration of AI to many different disciplines is inevitable. As the Center for Applied Artificial Intelligence at ODTÜ KALTEV, our mission is to conduct research and develop projects in different disciplines, produce AI applications for our university, and provide consultancy services to relevant companies.

Objectives

The main objectives of the Center for Applied Artificial Intelligence are to develop projects in different disciplines using AI technologies, provide consultancy services to relevant companies from data gathering to the development of AI technologies using the appropriate machine/deep learning models, and produce AI applications for our university to assist administration, education and research.

Role in KALTEV

As a part of ODTÜ KALTEV, the Center for Applied Artificial Intelligence is contributing to the growth and development by developing several intelligent projects using AI technologies in different disciplines. We believe that it will be a main hub to create collaborations between experts in AI, university students, and companies by promoting AI projects and providing consultancy in diverse fields from medicine to smart agriculture.

Directors

Director
Assoc. Prof. Dr. Cem Direkoğlu
Email: cemdir@metu.edu.tr

Vice-Director
Dr. Şükrü Eraslan
Email: seraslan@metu.edu.tr

Vice-Director
Assoc. Prof. Dr. Dizem Arifler
Email: darifler@metu.edu.tr

Vice-Director
Assist. Prof. Dr. Meryem Erbilek
Email: merbilek@metu.edu.tr

Members

To be announced later…

Focus Areas:

The Center currently aims at developing projects and providing consultancy services in different areas, including but not limited to:

  • Health monitoring systems: Accurate and early disease diagnosis with machine/deep learning models using images, sounds and other measurements.
  • Intelligent security systems: Smart traffic flow with camera security systems and different sensors, safer city projects, sound and air pollution prediction and awareness.
  • AI applications in education and administration: Smart interactive question-answer systems to support administrative management, preparation of interactive lecture notes and visuals to support instructors.
  • Smart agriculture: Crop disease diagnosis using images, crop yield prediction, and sensitive irrigation systems according to changing climate conditions.
  • Intelligent human-computer interaction: Design of interactive systems using multi-modal sensors, e.g. camera, audio, text.

    Other projects that integrate AI.

Ongoing Projects:

  • Crowd density estimation, people and vehicle counting, event detection using computer vision and machine/deep learning.
  • Generative AI models for smart question answering.
  • Disease classification models in healthcare using machine/deep learning.

Selected Publications:

  • Khalid Zaman, Melike Sah, Cem Direkoglu and Masashi Unoki. A Survey of Audio Classification Using Deep Learning. IEEE Access, vol. 11, pp. 106620-106649, (2023).
  • Yazan Zaid, Melike Sah, Cem Direkoglu, Pre-processed and combined EEG data for epileptic seizure classification using deep learning, Biomedical Signal Processing and Control, Volume 84, 104738, (2023).
  • Melike Sah, Cem Direkoğlu. Review and evaluation of player detection methods in field sports. Multimedia Tools and Applications 82, 13141–13165, (2023).
  • Victoria Yaneva, Le An Ha, Sukru Eraslan, Yeliz Yesilada, and Ruslan Mitkov. Reading differences in eye-tracking data as a marker of high-functioning autism in adults and comparison to results from web-related tasks. In Neural Engineering Techniques for Autism Spectrum Disorder, Volume 2, Academic Press, Elsevier, (2023).
  • A. Hendr, U. Ozgunalp, and M. Erbilek, “Diagnosis of Autism Spectrum Disorder Using Convolutional Neural Networks”, Electronics, vol.12, no. 3: 612, (2023).
  • Erfan Khalaji, Sukru Eraslan, Yeliz Yesilada and Victoria Yaneva. Effects of data preprocessing on detecting autism in adults using web-based eye-tracking data, Behaviour & Information Technology, 42:14, 2476-2484, (2023).
  • Nuray Vakitbilir, Adnan Hilal, and Cem Direkoğlu. Hybrid deep learning models for multivariate forecasting of global horizontal irradiation. Neural Comput & Applic 34, 8005–8026, (2022).
  • Melike Sah, Cem Direkoglu. A survey of deep learning methods for multiple sclerosis identification using brain MRI images. Neural Comput & Applic 34, 7349–7373, (2022).
  • D. Arifler and M. Guillaud. Assessment of internal refractive index profile of stochastically inhomogeneous nuclear models via analysis of two-dimensional optical scattering patterns. J. Biomed. Opt. 26, 055001, (2021).
  • Cem Direkoglu. Abnormal Crowd Behavior Detection Using Motion Information Images and Convolutional Neural Network. IEEE Access, 8, 80408-80416, (2020).
  • Victoria Yaneva, Le An Ha, Sukru Eraslan, Yeliz Yesilada, and Ruslan Mitkov. Detecting High-functioning Autism in Adults Using Eye Tracking and Machine Learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28, 6, 1254-1261, (2020).
  • H. Y. Yatbaz and M. Erbilek, “Deep Learning Based Stress Prediction From Offline Signatures”, 8th International Workshop on Biometrics and Forensics (IWBF), 29-30 April, 2020, Porto, Portugal. 
  • Hakan Yekta Yatbaz, Sukru Eraslan, Yeliz Yesilada and Enver Ever. Activity Recognition Using Binary Sensors for Elderly People Living Alone: Scanpath Trend Analysis Approach. IEEE Sensors Journal, 19, 17, 7575-7582, (2019).
  • Y.B. Ayzeren, M. Erbilek and E. Çelebi, “Emotional State Prediction From Online Handwriting and Signature Biometrics”, IEEE Access, vol.7, pp. 164759-164774, (2019).
  • D. Arifler, T. Zhu, S. Madaan, and I. Tachtsidis. Optimal wavelength combinations for near-infrared spectroscopic monitoring of changes in brain tissue hemoglobin and cytochrome c oxidase concentrations. Biomed. Opt. Express 6, 933-947, (2015).