Graduate School of Informatics

The goal of this thesis is to evaluate the skills mismatch in the curricula of HPC MSc's programs for some of the most relevant positions in the HPC areas in light of the ESCO database criteria and industry requirements. The four separate profiles "Data Science, Computer Architecture, Parallel Programming, and DevOps" that are thought to be crucial in HPC are the focus of this research. The methodology of this contribution explicitly examines the key responsibilities for the aforementioned positions and conducts a gap analysis based on Natural Language Processing (NLP) techniques for the competencies required for each in the MSc degree curriculum. The goal of applying NLP is to determine the degree to which the occupational skills stated in the ESCO and the HPC graduate courses’ syllabuses are semantically similar, as well as the level at which they overlap.

Date: 16.01.2023 / 13:00 Place: B-116

This thesis demonstrates research towards innovating a novel framework that (i) could be trained by supervised learning of discourse parsing from annotated and parsed relations, (ii) makes it easy to build end-to-end shallow discourse parsing system, (iii) forms a discourse relation detector benchmark for low resourced languages. Our modern neural network approach, integrated with contextualized text embedding, produced by pretrained language models, accomplished two sub-tasks of shallow discourse parsing, namely, identification of discourse relation realization types and the sense classification of explicit and implicit relations. The effect of multilingual data aggregation on the classification of discourse relation type through Cross-lingual Transfer Learning experiments is researched too.

Date: 25.01.2023 / 10:00 Place: A-108

Building on an extensive review of the psycholinguistics literature and Turkish Derivational Morphology (DM), we propose a novel structure for representing DM in three hierarchical layers: segmentation, lexical selection and derivation. This proposal involves laying a conventionalized structure over the traditional morphological structure of DM. We develop a computational model of morphology processing based on this structure using Bayesian Belief Networks (BBN). We present an algorithmic implementation for this model that learns and accurately represents new lexical items, recognizes affixes and tracks the salience of each item probabilistically. We carry out trials on this model with realistic observation lists and observe that model predictions are in line with the findings in studies in psycholinguistics.

Date: 25.01.2023 / 12:00 Place: A-108

Musical conducting is the art of making real time manipulations on a musical piece as if the instruments are the musicians themselves. Orchestra responses affect the conductor’s actions while a musical piece is being played. Therefore there is a significant information flow on the stage. In this research, we focused on the causality relations between the conductor, orchestra and the musical scores. We collected data from an actual orchestral practice and processed the collected data for causality measurements using the Transfer Entropy method. We utilized the method also for unsupervised detection of conducting commands.

Date: 20.01.2023 / 10:00 Place: A-108

In Türkiye, Social Security Institution is the primary healthcare insurer. Turkish citizens are registered under General Medicare Insurance coverage. In 2003, Ministry of Health (MoH) has initiated the “Health Transformation Program”, and implemented the interoperable health data exchange standards. The MoH is focusing on collecting medical data in a coded, structured, and electronic format, generated at all healthcare providers. Contrarily, genetic test results are exchanged in narrative, unstructured form among governmental and private health care providers. In this dissertation, we lay out the bottlenecks and put forward a conceptual model for meaningful genomic data exchange for Turkish Electronic Health Records.

Date: 18.01.2023 / 15:00 Place: B-116

Communicating uncertainty is a challenging task. Personal differences such as culture, cognitive load and even feelings of the user can impact the interpretation of an uncertain situation. Decision support models such as Bayesian networks can aid dealing with uncertainty. However, the outputs of these models are probability distributions, their interpretation can be challenging and visualisations can help with this task. The aim of the study is to investigate how effective visual aids communicating BN predictions are and users preferences regarding these visual aids. Model’s prediction and performance are needed to communicate BN predictions. Hence, in this study both model’s prediction and performance are investigated. BN model that has been developed to make predictions on a medical condition namely, Trauma Induced Coagulopathy (TIC BN) are used as a case study.

Date: 16.01.2023 / 14:00 Place: A212

In this thesis, we proposed new region proposal network to eliminate the traditional region proposal network’s disadvantages. Region Proposal Networks are used for generating object candidate boxes for two stage object detection algorithms to detect objects with higher accuracy rate on Deep Learning area. With this proposed method, the accuracy of the classical methods is passed on MS-COCO dataset.

Date: 19.01.2023 / 13:30 Place: -

The emerging destructive Technologies such as big data, internet of things (IoT), cloud have revealed the Industry 4.0 revolution. Although Industry 4.0 technologies have very important benefits to the manufacturing sector, various obstacles may arise against the application of these technologies. The aim of this thesis is to make detailed studies on the Industry 4.0 revolution and to reveal the obstacles that may arise during the application of Industry 4.0 technologies to the Turkish manufacturing sector. Interpretive Structural Modeling (ISM) technique was used while establishing the relationship between the barriers in front of IE 4.0 adaptation. ISM Framework was obtained with the findings obtained as a result of the study.

Date: 25.01.2023 / 10:30 Place: A212

The fusion of information coming from different sensors (e.g., optics, audio, accelerometer) to recognize egocentric activities is still an active research area. Although the increase in sensor diversity brings out the need for adaptive fusion, there is a limited number of studies. In this work, we proposed two novel multi-modal decision fusion frameworks for egocentric activity recognition. The first framework combines hand-crafted features using Multi-Kernel Learning. The other framework utilizes deep features using a two-stage decision fusion mechanism. Additionally, a new egocentric activity dataset, named Egocentric Outdoor Activity Dataset (EOAD), was populated, containing 30 egocentric activities and 1392 video clips.

Date: 18.01.2023 / 14:00 Place: A108