Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

Settings

Access type: Open accessPublisher: search.filters.publisher.Institute of Electrical and Electronics Engineers Inc.

Search Results

Now showing 1 - 10 of 317
  • Conference Object
    A Comparative Study of Attention-Augmented YOLO Architectures for Defect Detection in Fused Deposition Modelling
    (Institute of Electrical and Electronics Engineers Inc., 2025) Cezayirli, H.; Tetik, H.; Dede, M.I.C.; Phone, W.L.; Alkan, B.
    Additive manufacturing (AM), particularly fused deposition modelling (FDM), facilitates the fabrication of complex geometries with increasing flexibility and efficiency. Ensuring consistent print quality in FDM processes necessitates the development of accurate defect detection mechanisms. Attention-augmented YOLO (You Only Look Once) models have emerged as a promising solution for addressing this challenge. In this study, we systematically benchmark and evaluate the performance of YOLO architectures enhanced with attention mechanisms within the context of FDM 3D printing applications. The models were trained and evaluated using representative defect datasets. The attention-augmented models demonstrate improved detection performance. © 2025 IEEE.
  • Conference Object
    Machine Learning-Based Antenna Selection and Secrecy Capacity Analysis
    (Institute of Electrical and Electronics Engineers Inc., 2025) Erdurak, Burak; Erdoǧan, Eylem; Gürkan, Filiz
    The performance of machine learning methods was analyzed to optimize antenna selection in wireless communication systems, and system's secrecy performance was observed. To enhance the antenna selection process, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), and the KNearest Neighbors (KNN) algorithm were utilized. Channel vectors were used as model inputs, aiming to select the most optimal transmission path among N possible candidates. During the training phase, the antenna with the highest Signal-to-Noise Ratio (SNR) was selected for data labeling. The performance of Single-Input Multiple-Output (SIMO), Multiple-Input SingleOutput (MISO), and Multiple-Input Multiple-Output (MIMO) system architectures was evaluated using model accuracy and the F1-score. Additionally, the secrecy capacity corresponding to the selected antennas was computed, demonstrating the feasibility of secure communication. The results indicate that deep learningbased methods achieved higher accuracy, with the CNN model emerging as the most successful approach, reaching an accuracy of over 95% across all system configurations. © 2025 Elsevier B.V., All rights reserved.
  • Article
    Technology-Enhanced Multimodal Learning Analytics in Higher Education: a Systematic Literature Review
    (Institute of Electrical and Electronics Engineers Inc., 2025) Raşıt Yürüm, O.
    Multimodal learning analytics (MMLA) is an emerging field of learning analytics and promises a more comprehensive analysis of the learning process thanks to advances in technological devices and data science. The purpose of this study was to explore technology-enhanced multimodal learning analytics in higher education systematically. A systematic literature review was performed using the PRISMA guidelines, and 45 studies published between January 2012 and June 2024 were determined. The findings demonstrated that China, the USA, Australia, and Chile were the leading contributors to MMLA research, with a notable surge in publications in 2021. Audio recorders, cameras, webcams, eye trackers, and wristbands were the most used devices. Most studies were conducted in experiment rooms or laboratories, though studies in authentic classroom settings have been growing. Data were primarily collected during activities such as programming, simulation exercises, presentations, discussions, writing, watching videos, reading, or exams, as well as throughout the entire instructional process, predominantly in computer science, health, and engineering courses. The studies were mainly predictive or descriptive whereas quite a few studies were prescriptive. Frequently tracked data types included audio, gaze, log, facial expression, physiological, and behavioral data. Traditional machine learning and basic statistics were the commonly used analytical methods whilst advanced statistics and deep learning were relatively less utilized. Test performance, engagement, emotional state, debugging performance, and learning experience were the popular target variables. The studies also pointed out several implications and future directions, with a significant portion highlighting the development of interventions, frameworks, or adaptive systems using MMLA. © 2013 IEEE.
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Practical and Cost-Effective Approach for Thermal Light Characterization Based on Confined Area Measurements
    (Institute of Electrical and Electronics Engineers Inc., 2025) Atac, Enes; Dinleyici, Mehmet Salih
    Photon statistics and optical coherence measurements are essential in understanding light sources' properties and behaviors. However, the measurement setups require sophisticated detectors with short integration times. Otherwise, the results are indeed time average, which poses a significant challenge, particularly for thermal light sources due to their very short coherence times. In this article, we present a novel, practical, and low-cost measurement procedure for characterizing photon statistics and the second-order coherence function of thermal light using an ordinary charge-coupled device (CCD) camera. We focus on single-pixel analysis through the experiments since measurements of randomly distributed light in a confined region follow Bose-Einstein statistics. This way, the likelihood of averaging during detection is reduced, allowing us to extract statistical information from the spatially distributed intensity values. The outcomes prove the effectiveness of confined area measurements method by overcoming the detector's long exposure time issue.
  • Conference Object
    Citation - Scopus: 1
    Applying Weighted Graph Embeddings To Turkish Metaphor Detection
    (Institute of Electrical and Electronics Engineers Inc., 2024) İnan, Emrah
    Metaphor is a common literary mechanism that allows abstract concepts to be conceptualised using more concrete terminology. Existing methods rely on either end-to-end models or hand-crafted pre-processing steps. Generating well-defined training datasets for supervised models is a time-consuming operation for this type of problem. There is also a lack of pre-processing steps for resource-poor natural languages. In this study, we propose an approach for detecting Turkish metaphorical concepts. Initially, we collect non-literal concepts including their meaning and reference sentences by employing a Turkish dictionary. Secondly, we generate a graph by discovering super-sense relations between sample texts including target metaphorical expressions in Turkish WordNet. We also compute weights for relations based on the path closeness and word occurrences. Finally, we classify the texts by leveraging a weighted graph embedding model. The evaluation setup indicates that the proposed approach reaches the best F1 and Gmean scores of 0.83 and 0.68 for the generated test sets when we use feature vector representations of the Node2Vec model as the input of the logistic regression for detecting metaphors in Turkish texts. © 2024 IEEE.
  • Conference Object
    Optimizing Integrated Shading Device and Light Shelf for Daylight Performance and Visual Comfort in Architecture Studio
    (Institute of Electrical and Electronics Engineers Inc., 2024) Avci, P.; Ekici, B.; Kazanasmaz, Z.T.
    To provide a sustainable interior, it is essential to consider visual comfort and energy efficiency for the occupants' well-being. Daylight is crucial in providing visual comfort while proposing energy-efficient design alternatives. Using daylight as a primary source is one of the most crucial strategies. However, controlling daylight for unwanted situations such as discomfort glare is important. There have been several research studies on daylighting, visual comfort, and shading techniques. Shading devices are façade configurations to control daylight, while light shelves distribute daylight evenly through the space. There are two types of classifications for shading devices: adaptive ones and non-adaptive ones. Numerous research studies have been conducted on daylighting, energy consumption, occupancy performance, and shading systems. Shading technologies, whether adaptive or not, provide benefits and drawbacks. Even though optimizing them is one way to design non-adaptive shading devices, they require minimal maintenance. This study aims to integrate adaptive shading devices and light shelves for university campus buildings to provide lighting design strategies. The aim is to create a study environment that promotes well-being and academic achievement. To pursue this study, three optimization algorithms were run to find the nearly optimal solution. The goal was to both maximize Daylight Autonomy and uniformity values. Results showed that HypE and SPEA2 results discovered near-optimal DA above 75% and uniformity between 0.6 and 0.7. © 2024 IEEE.
  • Conference Object
    Citation - Scopus: 2
    Deception Through Cloning Against Web Site Attacks
    (Institute of Electrical and Electronics Engineers Inc., 2021) Arslan,M.; Carikci,B.; Erten,Y.M.
    In this study, a deception-based solution to the web site attacks is proposed. No fake entity is created to attract the intruders. The suggested solution involves cloning the web site under attack after the intrusion is detected and diverting the attacker to this cloned web page. Intrusion detection system (IDS) is used for detecting the attacks and Docker is used as the virtualization technology to create the cloned web site. While the intruder is connected to the clone, information is gathered on her/his activities. The system is implemented and tested for different attack types, and performance measurements were carried out. The results show that the system implementation for static pages is feasible and the system performance is not significantly affected. © 2021 IEEE.
  • Conference Object
    Citation - Scopus: 3
    Behavior-Driven Development of Software Product Lines
    (Institute of Electrical and Electronics Engineers Inc., 2021) Tuglular,T.; Coskun,D.E.
    Software product lines (SPLs) develop families of similar software products, which share a standard set of features, and they build in variety via optional features. That means customers can select features according to their needs and come up with a product configuration. Then the SPL is expected automatically to generate and test the software product for the chosen configuration. There are various SPL solutions for the automatic generation of software products, but those SPLs lack automatic testing of the generated product. To overcome this shortcoming, the SPL should automatically compose a test suite according to the selected features, automatically execute the test suite on the product, and automatically generate a test report delivered to the customer with the product. This paper proposes such an approach through behavior driven development. The proposed method is evaluated with a smart home SPL. © 2021 IEEE.
  • Conference Object
    Citation - Scopus: 1
    Electroluminesence Properties and Stability of Super Yellow on Zaz and Ito Anodes
    (Institute of Electrical and Electronics Engineers Inc., 2021) Bozkurt,H.; Ekmekcioglu,M.; Ozdemir,M.; Aygun,G.; Ozyuzer,L.; Varlikli,C.
    Transparent conductive oxides (TCEs) are essential and important part of many optoelectronic devices. They could affect efficiencies due to their optical and electrical properties. In this work, commercially available Indium Tin Oxide (ITO) and generously provided ZTO/Ag/ZTO (ZAZ) multilayer thin film coated glasses are utilized as anodes in a Super Yellow (SY) based Organic Light Emitting Diode (OLED). ZAZ electrode presented comparable transparency with the ITO and although, it was much thinner, its sheet resistance was more than 20% lower than the ITO electrode. The electroluminescence wavelength range of SY was almost identical with both electrodes. Due to the obtained higher turn-on voltage, the power efficiency value was slightly lower with the ZAZ electrode, and a negligible full width of half-maximum increase was detected. Nevertheless, ZAZ electrode presented higher luminous and external quantum efficiencies, color stability with applied voltage, and therefore addressed as a good candidate for ITO-free OLEDs. © 2021 IEEE.
  • Conference Object
    Citation - Scopus: 2
    Magnetron Sputtering Deposition of Sb2se3thin Films: Physical Property Characterizations and Its Relevance for Photovoltaics
    (Institute of Electrical and Electronics Engineers Inc., 2020) Gundogan,S.H.; Ozyuzer,L.; Aygun,G.; Cantas,A.
    The absorber layer is a significant part of the solar cell configuration because of its role in determining the efficiency. Since the properties of the chalcogenides have been studied intensively, the Sb2Se3 material has come into prominence. In thin film technology, the most effective ways of increasing the performance are the rate of photon absorption, long material life, carrier efficiency and the quality of the interface. Sb2Se3 gets more attention than others due to its optoelectronic properties. Sb2Se3 has a suitable band gap (Eg), long term material stability, and a relatively simple composition with non-Toxic and earth abundant elements. All these features make Sb2Se3 a promising candidate for use as an absorber layer in thin film photovoltaics (PVs). In this study, Sb2Se3 films have been grown with DC magnetron sputtering method onto soda lime glass (SLG) substrates with different time durations. Morphological, structural, and optical properties of Sb2Se3 thin films were systematically investigated as a function of the thickness for photovoltaic applications. Our results indicate that the optical transmission, absorption behavior, and bandgap energy are strongly dependent on the thickness of the film. © 2020 IEEE.