I am a MSc student in Computer Engineering at Eskisehir Technical University. I graduated from Eskişehir Technical University with a degree in Computer Engineering. Additionally, I have completed a minor program in Artificial Intelligence and Machine Learning at Eskişehir Technical University. During my studies, I was a lab student at the AI in Healthcare Lab, where I focused on developing my skills in image processing and machine learning.
I am currently seeking a position in the field of artificial intelligence and machine learning.
Master of Science in Computer Engineering
Sep. 2024 – Current
Eskisehir, Türkiye
Minor in Artificial Intelligence and Machine Learning
Feb. 2021 – Jan. 2024
Eskisehir, Türkiye
Bachelor of Science in Computer Engineering
Sep. 2019 – Jun. 2024
Eskisehir, Türkiye
I have worked on data analysis, model development, and algorithm design using Python. I have carried out projects particularly in the fields of machine learning algorithms, deep learning algorithms and computer vision. My projects span across various domains such as healthcare, finance, and commerce. I have experience working with large datasets, performing data cleaning, transformation, and feature engineering. I have also applied augmentation techniques to balance imbalanced datasets. I am proficient in using popular libraries such as TensorFlow, Keras, and PyTorch for modeling. Additionally, I have experience in model evaluation, hyperparameter optimization, and utilizing explainable AI (XAI) methods to enhance the accuracy and reliability of projects. Furthermore, I have developed end-to-end projects by integrating models into user interfaces using the Gradio library.
Projects are being developed in the field of medical image processing. Work is continuing with the aim of observing an increase in model performance with limited and unlabeled data.
Theoretical and practical experience was gained in machine learning and image analysis.
Image processing techniques were utilized in the projects.
The VGG16 model within PyTorch was utilized in the Emotion Recognition project.
Object detection was conducted using YOLOv7 and YOLOv8 algorithms.
Segmentation performed using U-Net architecture with ResNet.
In the project, the UI/UX design part was done using Figma.
The web page, designed in Figma, was coded with adherence to SEO rules and utilizing Bootstrap 5.3.
Git was employed for source code review, code sharing, branching structure, and version control management.
Designed a self-training pipeline for segmenting COVID-19 lesions in chest CT images using the teacher-student model, a semi-supervised learning approach with limited labeled data.The teacher model generated pseudo-labels for unlabeled images. Applied Monte Carlo Dropout to estimate uncertainty and filter out low-confidence pseudo-labels, improving their reliability.
The system effectively segments lesions using a dataset consisting mostly of unlabeled chest CT images. It demonstrates that accuracy can be achieved with limited annotation through semi-supervised learning strategies.
🧪 Developed at AI in Healthcare Lab, Eskisehir Technical University, under the supervision of Dr. Sema Candemir.
🎓 This resarch was presented at SIU 2025 (IEEE Signal Processing and Communications Applications Conference).
The system has three main components: (i) The eye disease prediction model is trained with a dataset containing fundus images with six different diseases. (ii) The diabetic retinopathy severity prediction model is trained with fundus images obtained from patients with diabetic retinopathy labeled with the stage of the disease. (iii) The system locates the regions related to eye diseases using the Grad-CAM.
🏆 The project has been selected as the winner among 31 groups at the 17th Project Fair and Competition held at Eskisehir Technical University on May 28, 2024.
🎓 This research was presented at the Engineering Sciences and Research Student Congress, Ankara, Atilim University, 2024.