This thesis investigates the potential of EEG-based features to distinguish between Attention Deficit Hyperactivity Disorder (ADHD) and Major Depressive Disorder (MDD), two conditions that often share overlapping symptoms and neurophysiological characteristics. Focusing on power spectral density (PSD) across frequency bands and mean curve length (MCL) as a complexity measure, the study applies multilayer perceptron (MLP) classifiers to a clinically diverse sample under both eyes open and eyes closed resting state conditions.

Date: 16.07.2025 / 14:00 Place: A-212

In energy and latency-constrained embedded systems, binary neural networks offer dramatic reductions in compute and memory by binarizing weights and activations. This thesis focuses binarizing a lightweight neural network model for classification. Using MNIST, CIFAR-10, and ImageNet, it compares full-precision models with binarized models according to accuracy, resource use, and performance trade-offs. Moreover, this thesis surveys AI hardware frameworks for FPGA-based reconfigurable systems in terms of compatibility with trending technologies and optimization strategies as a comprehensive guide.

Date: 08.07.2025 / 10:00 Place: B-116

This thesis investigates the demographic history of Anatolian sheep. Sheep are among the most important livestock species, supplying meat, milk and wool. Analysing new genome data from ancient and present-day Anatolian sheep reveals a substantial eastern-related genetic influx after the Neolithic and uncovers a population structure in present-day Turkish breeds defined by geography and tail morphology. Fat-tailed breeds, mainly from eastern Türkiye, show greater genetic affinity to Iron Age Anatolian sheep than thin-tailed breeds do. Conversely, thin-tailed breeds, from western Türkiye, retain more Neolithic-like ancestry than fat-tailed breeds. These findings show how Anatolian sheep gene pool shaped over thousands of years.

Date: 07.07.2025 / 11:00 Place: A-212

This thesis proposes a transformer-based framework with post-inference strategies designed to improve temporal coherence and semantic consistency in range-based, multiclass anomaly localization for multivariate time series.

Date: 25.06.2025 / 09:00 Place: A-212

As next-generation avionic platforms become increasingly connected, systems that were once isolated are now exposed to cyber threats. Communication standards like MIL-STD-1553, widely used in commercial, military, and aerospace platforms, were originally designed without security considerations, resulting in growing vulnerabilities. Implementing conventional security upgrades is costly and brings certification challenges. Intrusion Detection Systems (IDS) offer a non-intrusive alternative, requiring no hardware or software changes. This study aims to enhance the security of MIL-STD-1553 communication buses by integrating a hardware fingerprinting-based IDS and evaluates the effectiveness of machine and deep learning methods in detecting unauthorized devices on the bus.

Date: 02.06.2025 / 11:00 Place: A-212

This thesis aims to reduce the need for pixel-level labeled data for semantic segmentation. A DeepLabV3+ based model trained on synthetic images is supplemented with a Domain-Adversarial Neural Network (DANN), an adversarial domain adaptation method, to adapt to real images. The model is applied in unsupervised and semi-supervised domain adaptation scenarios. In the semi-supervised adaptation method in particular, similar performance was achieved using 92% less labeled real data compared to the DeepLabV3+ method trained with supervised learning and without domain adaptation. This study provides an effective solution that reduces the burden of image labeling.

Date: 26.05.2025 / 15:00 Place: A-212

In this thesis, a forecasting model has been developed for cooling and freezing products of a home appliance company. Economic fluctuations, global events, and market competition increase demand variability, complicating supply chain management. In this context, various clustering techniques have been utilized to improve product and country groupings, aiming to enhance forecasting accuracy and optimize supply chain strategies. Additionally, external factors such as the impact of Covid-19, economic indicators, and stock levels have been incorporated into the forecasting model.

Date: 26.05.2025 / 10:30 Place: B-116

This thesis explores the critical role of people and culture-related capabilities in the success of Advanced Data Analytics (ADA) projects, addressing a gap in current literature that predominantly focuses on technical aspects. By conducting a systematic literature review and semi-structured interviews, the study identifies and categorizes these capabilities, integrating them into structured processes tailored from the People Capability Maturity Model (Curtis et al., 2009). The research contributes actionable frameworks and practices to enhance workforce readiness, collaboration, and organizational culture, enabling businesses to align ADA initiatives with strategic goals and achieve sustainable success.

Date: 10.01.2025 / 13:30 Place: A-212

Somatic mutations in non-coding regions can disrupt transcription factor (TF)-DNA interactions, affecting gene regulation and contributing to cancer. This thesis introduces an in silico pipeline to assess the impact of these mutations on TF binding affinities. Using k-mer-based linear regression models trained on ChIP-seq and PBM data for 403 TFs, we analyzed somatic mutations in 560 breast cancer samples. Predicted TF binding changes were classified as gain or loss of function and linked to oncogene and tumor suppressor dysregulation using enhancer-target gene maps. Signature-specific and statistical analyses highlight distinct patterns, providing insights into the regulatory role of mutations in cancer.

Date: 07.01.2025 / 10:00 Place: A-212

This thesis introduces a methodology for training context-invariant autoencoders using unsupervised domain adaptation to enhance model generalizability under varying contexts. By employing domain-adversarial training and data augmentation, the approach extracts domain-invariant representations while disregarding contextual variations. Experiments utilize the CARLA simulator, generating diverse image datasets across weather conditions and times of day. The proposed framework improves reconstruction loss and feature robustness, demonstrating its efficacy in achieving reliable machine learning performance in dynamic environments. The study emphasizes the utility of domain adaptation techniques in addressing domain shifts, offering a foundation for robust applications in autonomous systems.

Date: 06.01.2025 / 14:30 Place: A-212