The graduation project topics offered by the faculty members of the Software Engineering Department are listed below:

 

    - Evaluation of Open-Ended Exam Questions with Artificial İntelligence: In this project, students answers to open-ended questions will be evaluated with artificial intelligence for each question. Written explanations and mathematical calculations in the exam answers will be checked and evaluated. Scoring will be determined by comparing correct and incorrect explanations in the questions

    - How could robots help during natural disasters? : In this project, students will engage with the various ways in which robots can assist to victims of natural disasters such as earthquakes, floods, or wildfires. Students will learn how these technologies can help the emergency services, locate survivors, provide aid to them, and help with communication in hostile areas.

 

 

 

    - Geometric Flows for Image Restoration and Denoising: The Mean Curvature Flow Approach: Mean curvature flow is a mathematical technique that is widely used to smooth and denoise images. Through this project, students will be learn mean curvature flow concept, implementations of its algorithms, and examine how it refines image quality in image processing applications.(See)

    - Application of Ricci Flows in Deep Learning: Recent studies have shown that Ricci flow, a geometric method, can be used to extract meaningful features from data sets, especially in deep learning applications. In this project, students will learn the theoretical foundations of Ricci flow, implement models, and investigate how this technique can improve feature extraction and data analysis in modern machine learning tasks.(See)

    - Application of Tensor Network Algorithms in the Field of Machine Learning: Tensor network algorithms, which were originally developed for modeling multidimensional quantum systems, have recently begun to be widely used in the field of machine learning as well. These methods allow high-dimensional data to be represented in a lower-dimensional space via local tensors. In this way, while the components of the data can be processed locally, the structural correlations between them can also be effectively revealed. Thanks to these properties, tensor networks are well-suited for various machine learning applications such as data compression, feature extraction, and denoising.(See)

    - Simulation of Quantum Walks via Quantum Computing Platforms: Quantum walks, which are quantum mechanical generalizations of classical random walks, play an important role both in the development of quantum algorithms and in the modeling of physical systems. Compared to classical walks, quantum walks have advantages such as faster spreading and superposition, making them particularly effective in search algorithms. In this project, the evolution of discrete-time quantum walks on different graph structures will be examined, and this process will be simulated using current quantum computing platforms.

     - Federated learning for health problems: One of the critical issues in the AI model is preserving privacy. This becomes serious when it comes to health data. Federated learning technique helps to train models from data located in different locations (it can be hospitals) without sharing private data. This kind of approach is vital in situations where there are strict rules in data sharing, for example, KVKK. Students can simulate federated learning using  TensorFlow Federated, PySyft, NVIDIA FLARE (NVFlare) and other tools

    - Optimization techniques in machine learning: Machine learning algorithms involve a number of hyperparameters, whose values have an impact on the performance of algorithms. Therefore, selecting or setting those values manually would be difficult to achieve the desired accurate results unless optimization algorithms are used together. Optimization techniques, such as heuristic/metaheuristic ones, are used as the best solution for a given problem. Students can apply machine learning and optimization algorithms for different types of problems in software engineering such as software effort estimation, project planning, log analysis and anomaly detection.

    - Explainable AI - It is a relatively new approach in machine learning and AI in general. Traditional or 'black box' models have no capability of explaining why the model has reached a decision. Opposed to, black box AI models, Explainable AI is a technique in AI that helps to build trust, transparency and interpretability in the decision or predictions of AI models.

    -  Numerical Simulation and Visualization of Integral Operators: In this project, students will focus on developing numerical methods to simulate integral operators and visualize their effects. They will use computational tools to analyze how these operators work in practice and present their findings through graphical representations.