Graduate School of Informatics

The quantization of neural networks is essential to meet real-time requirements. Zero-shot quantization is a key approach when training data is unavailable. To the best of our knowledge, zero-shot quantization in the infrared domain has not been explored before. This thesis examines the performance of batch normalization statistics-based zero-shot quantization on models trained with infrared imagery. We fine-tuned models pretrained on RGB images using infrared images and carefully investigated the data generation process to achieve optimal results for YOLOv8 and RetinaNet. Our results demonstrate that zero-shot quantization is more effective in the infrared domain.

Date: 03.09.2024 / 11:00 Place: B-116

This thesis explores efficient pretraining methods for Vision Transformers by integrating progressive layer freezing with local masked image modeling. The study assesses the computational demands and extended training periods typical of self-supervised learning methods for ViTs. Key innovations include implementing the FreezeOut method within the LocalMIM architecture to significantly enhance training efficiency. Experimental results show a reduction in training time by about 12.5% while maintaining competitive accuracy, demonstrating the effectiveness of strategic layer freezing combined with tailored learning rate scheduling. This approach promotes more accessible self-supervised learning on constrained computational resources.

Date: 03.09.2024 / 09:30 Place: B-116

This study is about narrative comprehension. Narrative comprehension involves how the characters and events described in narratives are represented in readers’ mind, what kinds of inferences are activated while reading narratives, and what text factors affect comprehension of narratives. In particular, our research will concentrate on the comprehension of spatial cues and protagonist’s perspective in narratives. Several studies in the literature suggest that readers are sensitive to the spatial cues and can, under some conditions, adopt the perspective of the protagonist in narratives. For this thesis, we will investigate this issue further, by testing some new research questions.

Date: 06.09.2024 Place: II-06

This thesis introduces advanced methodologies for Land Use Mix (LUM) analysis in urban planning, GIS research, and disaster risk assessment. It addresses limitations in traditional approaches by leveraging point-based geospatial data and develops an open-source Python package, landusemix, for scalable and adaptable LUM calculation. The research extends LUM analysis to evaluate temporal variations in urban vulnerability, particularly concerning earthquake risk, offering insights for time-sensitive urban planning. This work enhances sustainable, resilient, and livable cities through innovative tools and approaches in urban studies.

Date: 03.09.2024 / 17:00 Place: B-116

Perimeter security is no longer barrier to access networks and critical data, making traditional security measures outdated. A robust security strategy is crucial to prevent and detect Active Directory (AD) attacks, which can be difficult to detect due to their blend in with normal network traffic. One such attack is the Kerberoasting attack, which exploits weaknesses in the Kerberos authentication protocol. To detect these attacks, supervised machine learning algorithms are being proposed. And also publicly available dataset to measure the efficiency of these algorithms for Kerberoasting attacks was created and shared.

Date: 05.09.2024 / 10:00 Place: II-06

This work investigates the meaning of the perfective/evidential suffix -mIş, focusing on its perfect interpretation. It has been argued that there are two distinct syntactic structures for simple verbal sentences [verb+past] and complex verbal sentences [verb+part+cop+past] (Kornfilt, 1996; Kelepir, 2001). Demirok and Sağ (2023) offer a compositional account for these two structures, taking the temporal relations as the basis. Building on that, we propose an Aktionsart-oriented analysis of the verb-participle relation. We offer a continuation-based compositional account within quantificational event semantics (Champollion, 2015) to reconcile the syntactic account of Kelepir (2001) and observations on the perfect meaning of -mIş.

Date: 06.09.2024 / 15:30 Place: A-212

This thesis aims to identify the factors influencing practitioners' continuance intention toward Agile methodology usage. The study also examines the influence of identified factors on the continuance intention of Agile methodology usage and proposes a model in the context of Agile methodology. The model was verified with the reliability tests, Exploratory Factor Analysis, Confirmatory Factor Analysis, and Structural Equation Modeling. By utilizing Structural Equation Modeling, the influencing factors and the relationships among these factors were analyzed and the final model is proposed.

Date: 05.09.2024 / 09:45 Place: A-108

This thesis explores the identification and prioritization of Critical Success Factors (CSFs) in data analytics projects. Through a systematic literature review and semi-structured interviews with data professionals, a comprehensive list of CSFs was developed, structured hierarchically, and refined based on expert feedback. The study addresses gaps in existing literature by providing a cross-disciplinary CSF framework applicable to various fields like AI, big data, and business intelligence. Additionally, the research prioritizes these factors through the semi-structured interviews based on organizational contexts such as company size, project complexity, and technological maturity.

Date: 05.09.2024 / 11:00 Place: A-212

In this thesis, a Bayesian cognitive model of Theory of Mind in communication is developed based on a prior experimental study on joint action and attention. Specifically, the model compares demonstrative utterances between individuals with high-functioning autism and typically developing, non-clinical controls. It applies the Rational Speech Act framework, incorporating visual (joint) attention measures obtained through dual eye-tracking. By parameterizing context-dependence, nestedness of inference, and the preference for different demonstrative systems, the model provides insights into group differences observed under conditions of high ecological validity.

Date: 05.09.2024 / 09:00 Place: B-116

In the present thesis, the social nature of learning in a verbal communication setting has been investigated by employing a multimodal hyperscanning method to correlate non-complex and replicable ocular and neural features with the socio-linguistic process of interlocutors establishing and sustaining conceptual common grounds. A dyadic interaction setting was formed with a dual-EEG, dual-fNIRS, and dual-eye tracking setup wherein experiment data were synchronized on the same time-domain to explicate these features. The results showed that replicable features for ocular, hemodynamic, and neuroelectric domains constituted both linear and non-linear relationships in between that correlate with linguistic behavioral data during dyadic verbal communication.

Date: 05.09.2024 / 15:00 Place: A-108