Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1926

Browse

Now showing 1 - 20 of 141

Evaluating Large Language Models in Data Generation for Low-Resource Scenarios: A Case Study on Question Answering
(International Speech Communication Association, 2025) Arisoy, E.; Menevşe, M.U.; Manav, Y.; Özgür, A.
Large Language Models (LLMs) are powerful tools for generating synthetic data, offering a promising solution to data scarcity in low-resource scenarios. This study evaluates the effectiveness of LLMs in generating question-answer pairs to enhance the performance of question answering (QA) models trained with limited annotated data. While synthetic data generation has been widely explored for text-based QA, its impact on spoken QA remains underexplored. We specifically investigate the role of LLM-generated data in improving spoken QA models, showing performance gains across both text-based and spoken QA tasks. Experimental results on subsets of the SQuAD, Spoken SQuAD, and a Turkish spoken QA dataset demonstrate significant relative F1 score improvements of 7.8%, 7.0%, and 2.7%, respectively, over models trained solely on restricted human-annotated data. Furthermore, our findings highlight the robustness of LLM-generated data in spoken QA settings, even in the presence of noise. © 2025 International Speech Communication Association. All rights reserved.
Makine Öğrenimi ve Çok Boyutlu Anket Verileri Kullanılarak Öğrenci Başarısının Tahmini: Eğitim Programı Üzerine Bir Uygulama
(Institute of Electrical and Electronics Engineers Inc., 2025) Behsi, Zeynep; Dereli, Serhan; Çakar, Tuna ; Patel, Jay Nimish; Cicek, Gultekin; Drias, Yassine
This study develops a machine learning model integrating survey data and performance metrics to predict student success in the UpSchool education program. Students' personality traits assessed by DISC analysis, financial management, social, and emotional skills were clustered into "Successful,""Unsuccessful,"and "Moderately Successful"groups using K-means clustering. The SMOTE technique addressed data imbalance issues, and algorithms such as Logistic Regression, Random Forest, LightGBM, and AdaBoost were tested. After hyperparameter optimization, AdaBoost and LightGBM achieved the highest predictive performance. Results demonstrated the effectiveness of machine learning models in forecasting student success in educational programs. Future studies are recommended to enhance model performance through expanded datasets and to validate the model's applicability across diverse educational contexts. © 2025 Elsevier B.V., All rights reserved.
Conclusion: What We Found and What We Recommend
(Cambridge University Press, 2021) Kibaroğlu, Ayşegül; Schmandt, Jurgen; Ward, George H.
This interdisciplinary volume examines how nine arid or semi-arid river basins with thriving irrigated agriculture are doing now and how they may change between now and mid-century. The rivers studied are the Colorado, Euphrates-Tigris, Jucar, Limarí, Murray-Darling, Nile, Rio Grande, São Francisco, and Yellow. Engineered dams and distribution networks brought large benefits to farmers and cities, but now the water systems face multiple challenges, above all climate change, reservoir siltation, and decreased water flows. Unchecked, they will see reduced food production and endanger the economic livelihood of basin populations.
Citation - Scopus: 5
Turkey's EU Membership Process in the Aftermath of the Gezi Protests
(Taylor and Francis, 2025) Saatçioǧlu, B.
Exploring Generative AI and Unsupervised Learning for Digital Soil Classification: A Case Study of Algeria
(Institute of Electrical and Electronics Engineers Inc., 2025) Belkadi, W.H.; Drias, Y.; Drias, H.; Bouchelkia, H.; Hamdous, S.
Accurate soil type mapping is vital for sustainable agriculture and land management. Yet, Algeria remains under-represented in global soil databases. To address this, we propose a pipeline combining Generative AI for data extraction with unsupervised learning for soil classification. After harmonizing Algerian soil data, we evaluate four clustering algorithms - K-means, DBSCAN, HDBSCAN, and Self-Organizing Maps - under various preprocessing settings. Internal and external metrics guide model selection. K-means and DBSCAN produced the most coherent clusters, while SOM best aligned with FAO soil types. RuleFit was then used to extract interpretable rules defining each cluster. This work highlights the potential of AI-based, interpretable clustering for digital soil mapping in data-scarce regions like Algeria. © 2025 Elsevier B.V., All rights reserved.
Citation - Scopus: 1
Sustainability of Engineered Rivers in Arid Lands: Challenge and Response
(Cambridge University Press, 2021) Schmandt, Jurgen; Kibaroğlu, Ayşegül; Buono, R.M.; Thomas, S.
This interdisciplinary volume examines how nine arid or semi-arid river basins with thriving irrigated agriculture are doing now and how they may change between now and mid-century. The rivers studied are the Colorado, Euphrates-Tigris, Jucar, Limarí, Murray-Darling, Nile, Rio Grande, São Francisco, and Yellow. Engineered dams and distribution networks brought large benefits to farmers and cities, but now the water systems face multiple challenges, above all climate change, reservoir siltation, and decreased water flows. Unchecked, they will see reduced food production and endanger the economic livelihood of basin populations. The authors suggest how to respond to these challenges without loss of food production, drinking water, or environmental health. The analysis of the political, hydrological, and environmental conditions within each basin gives policymakers, engineers, and researchers interested in the water/sustainability nexus a better understanding of engineered rivers in arid lands. © Jurgen Schmandt, Aysegu¨l Kibaroglu, Regina M. Buono and Sephra Thomas 2021.
Dil Modelleri ile Akademik Özet Üretimi
(Institute of Electrical and Electronics Engineers Inc., 2025) Bektas, Busra; Gultekin, Ali Ozgun; Ozdemiroglu, Emre; Yilmaz, Zeynep; Dikici, Buse; Demir, Seniz
In recent years, large language models have demonstrated extraordinary capabilities in natural language processing tasks. The integration of these models to text summarization has highlighted the need for evaluating varying model performances under a standardized benchmarking framework. In this study, the performance of different large language models in generating abstracts of scientific papers which has a common structure and unique language is compared through an extensive experimental analysis. The abstracts automatically generated by these models using prompt engineering were evaluated via various evaluation metrics based on content overlap and semantic similarity. The results that we obtained demonstrated the effectiveness of large language models in abstract generation. © 2025 Elsevier B.V., All rights reserved.
Citation - Scopus: 9
Çocuklarda Sınav Kaygısı Ölçeği'nin Türkçe Uyarlaması
(İlköğretim Online, 2017) Bulgan, Gökçe; Aydın, Utkun
The purpose of this study was to adapt the “Children’s Test Anxiet Scale (CTAS)” developed by Wren and Benson (2004) into Turkish. The original scale was in English and comprised of three factors including 30 items. Seven experts were involved in the adaptation process to translate the scale into Turkish and then back to English for providing evidence based on the consistency between the two forms. Following the translation process, a pilot study was conducted and the scale was given its final form. The Turkish form was administered to 1100 students who were attending to 3rd, 4th, 5th, and 6th grade classes in 3 public schools. Findings regarding the construct validity of the scale, which were obtained from the confirmatory analysis, supported the three-factor structure of the original scale. Subdimensions of the scale were Thoughts, Off-Task Behaviors, and Autonomic Reactions. Cronbach Alpha coefficients for the overall scale (???= .88) as well as the subdimensions of Thoughts (???= .82), Off-Task Behaviors (???= .72), and Autonomic Reactions (???= .75) were substantial in size. Regarding the discriminant validity analyses, there were no significant gender differences in students’ test anxiety while there were significant grade level differences. These results demonstrated that the Turkish version of the scale is a valid and reliable instrument, which may serve as useful in measuring elementary school students’ test anxiety levels. Directions for future research and practical implications for educational practice are discussed in terms of mathematics education.
Citation - WoS: 44
Citation - Scopus: 50
Unraveling the Roles of Distrust, Suspicion of Infidelity, and Jealousy in Cyber Dating Abuse Perpetration: an Attachment Theory Perspective
(SAGE Publications, 2020) Toplu-Demirtaş, Ezgi; Akcabozan-Kayabol, Nazlı Büşra; Araci-Iyiaydin, Ayşegül; Fincham, Frank D.
People who are anxiously attached, distrustful and jealous of their partners, and suspect infidelity are more likely to use psychological dating violence. Is this also true for cyber dating abuse perpetration (CDAP)? This study investigated the prevalence of and gender differences in self-reported CDAP and whether trust, anticipated partner infidelity, and jealousy serially mediated the association between anxious attachment and CDAP in a sample of Turkish college students. College students (N = 390) completed the Cyber Dating Violence Inventory, Anxious Attachment subscale of the Experiences in Close Relationship Scale-Short Form, Dyadic Trust Scale, Cognitive Jealousy subscale of the Multidimensional Jealousy Scale, Partners’ Intentions Towards Infidelity Scale, and a Demographic Information Form. A total of 67% of the sample used at least one cyber abusive behavior with their partner over the last 6 months. A multiple serial mediation model indicated that greater anxious attachment was related to more dyadic distrust, the anticipation of partner infidelity, and jealousy, and, in turn, to the use of cyber dating abuse. Overall, results show that the prevalence of CDAP is high and that attachment theory offers a promising framework for identifying predictors of CDAP in emerging adults. These findings have implications for research, intervention, and prevention of CDAP by identifying potential risk factors for perpetrating cyber abuse.
Citation - WoS: 3
Citation - Scopus: 3
Microzonation With Respect To Ground Shaking Intensity
(CRC Press/Balkema, 2019) Tönük, Gökçe; Kurtuluş, Aslı; Ansal, Atilla
Seismic microzonation is conducted to assess the seismic hazard on the ground surface with respect to ground shaking intensity. A probabilistic seismic hazard study is conducted to define earthquake characteristics on the rock outcrop. A grid system is generated to divide the investigation area into cells according to geological and geotechnical data. Site characterizations are based on available information to define soil profiles for each cell with soil stratifications and shear wave velocities extending down to the engineering bedrock. Site-specific 1D site response analyses are carried out for all soil profiles, based on the engineering properties of encountered soil layers, selection and scaling of the sufficient number of input acceleration time histories compatible with the regional seismicity and earthquake source characteristics. The microzonation study carried out for Zeytinburnu town on the European side of Istanbul with respect to ground shaking intensity is presented. The importance of the selection of the microzonation parameters for assessing ground shaking intensity is discussed. © 2019 Associazione Geotecnica Italiana, Rome, Italy.
Citation - Scopus: 5
The Euphrates–Tigris River Basin
(Cambridge University Press, 2021) Kibaroğlu, Ayşegül
This interdisciplinary volume examines how nine arid or semi-arid river basins with thriving irrigated agriculture are doing now and how they may change between now and mid-century. The rivers studied are the Colorado, Euphrates-Tigris, Jucar, Limarí, Murray-Darling, Nile, Rio Grande, São Francisco, and Yellow. Engineered dams and distribution networks brought large benefits to farmers and cities, but now the water systems face multiple challenges, above all climate change, reservoir siltation, and decreased water flows. Unchecked, they will see reduced food production and endanger the economic livelihood of basin populations. The authors suggest how to respond to these challenges without loss of food production, drinking water, or environmental health. The analysis of the political, hydrological, and environmental conditions within each basin gives policymakers, engineers, and researchers interested in the water/sustainability nexus a better understanding of engineered rivers in arid lands.
Analyzing Consumer Behavior: the Impact of Retro Music in Advertisements on a Chocolate Brand and Consumer Engagement
(IEEE, 2023) Girişken, Yener; Soyaltın, Tuğçe Ezgi; Filiz, Gözde; Çakar, Tuna; Türkyılmaz, Ceyda Aysuna
This study presents research utilizing binary classification models to analyze consumer behaviors such as chocolate consumption and retro music ad viewing. Retro music, with its potential to evoke nostalgic feelings in consumers, is used in advertisements, which can have a significant impact on brand perception and consumer engagement. Firstly, a model focusing on chocolate consumption was developed and tested. The model yields significant outcomes. Secondly, a model based on retro music ad viewing status was developed and tested. Significant potential findings were obtained. This study emphasizes the applicability of effective classification models that can be used to understand and predict consumer behaviors, yielding significant outcomes.
Highlighting of Lecture Video Closed Captions
(IEEE, 2020) Yıldırım, Göktuğ; Öztufan, Huseyin Efe; Arısoy, Ebru
The main purpose of this study is to automatically highlight important regions of lecture video subtitles. Even though watching videos is an effective way of learning, the main disadvantage of video-based education is limited interaction between the learner and the video. With the developed system, important regions that are automatically determined in lecture subtitles will be highlighted with the aim of increasing the learner's attention to these regions. In this paper first the lecture videos are converted into text by using an automatic speech recognition system. Then continuous space representations for sentences or word sequences in the transcriptions are generated using Bidirectional Encoder Representations from Transformers (BERT). Important regions of the subtitles are selected using a clustering method based on the similarity of these representations. The developed system is applied to the lecture videos and it is found that using word sequence representations in determining the important regions of subtitles gives higher performance than using sentence representations. This result is encouraging in terms of automatic highlighting of speech recognition outputs where sentence boundaries are not defined explicitly.
Observations From Geotechnical Arrays in Istanbul
(2015) Tönük, Gökçe; Kurtuluş, Aslı; Cetiner, Barbaros; Ansal, Atilla
Few small earthquakes with local magnitude slightly larger than M-L = 4 were recorded by geotechnical downhole arrays that have been recently deployed in the west side of Istanbul. Same events were also recorded by Istanbul Rapid Response Network (IRRN) which comprises of 55 surface strong motion stations in the European side of Istanbul. The strongest one of these earthquakes took place on 12/3/2008 in Cinarcik with local magnitude of M-L = 4.8. Even though the observed PGAs were not exceeding 0.01 g, an effort is made to model the recorded response at the downhole array sites as well as the at the IRRN stations using the acceleration records obtained by the deepest sensors, i.e. on the engineering bedrock, at the downhole array sites as input bedrock motions. 1D equivalent linear site response analysis that is generally adopted for site-specific response analysis is used for modelling. Observations from the recorded response and results from 1D modelling of ground response have yielded in general good agreement between the observed and recorded soil response at the station sites.
Citation - Scopus: 3
Emg-Based Bci for Picar Mobilization
(IEEE, 2022) Yilmaz, Yasin; Günden, Burak Bahri; Ertekin, Efe; Sayar, Alperen; Çakar, Tuna; Arslan, Şefik Şuayb
In this study, the main scope was to develop a brain-computer interface (BCI) with the use of PiCar and EEG/ERP devices. Thus, it is aimed to facilitate the lives of people with certain diseases and disabilities. The ultimate goal of this project has been to direct and control a BCI-based PiCar concerning the signals captured via the EEG/ERP device. With the EEG headset, the EMG signals of the gestures (facial expressions) of the participant were captured. With the collected data, filtering and other preprocessing methods were applied to have noise-free signals. In the preprocessing, the detrending method was used to clean the data set which showed a constantly increasing trend, to a certain range, and zero trends. The denoising (Wavelet Denoising) and outlier detection/elimination methods (OneClassSVM) were used for noise elimination. The SMOTE oversampling method was used for data augmentation. Welch's method was used to get band powers from the signals. With the use of augmented data, several machine learning algorithms were applied such as Support Vector Machine, Logistic Regression, Linear Discriminant Analysis, Random forest Classifier, Gradient Boosting Classifier, Multinomial Naive Bayes, Decision tree, K-Nearest Neighbor, and voting classifier. The developed models were used to predict the direction that is passed as an input to PiCar's API. After that, PiCar was controlled concerning the predicted direction with HTTP GET requests. In this project, the OpenBCI headset and the Brainflow library for EEG/EMG signal obtaining and processing were used. Also, the Tkinter library was used for the Graphical user interface and Django for establishing a server on PiCar's brain which is RaspberryPi. © 2022 IEEE.
Citation - WoS: 1
Citation - Scopus: 1
Security Analysis of Revocable and Bipartite Biotokens
(2015) Sarıer, Neyire Deniz
In this paper, we analyze the security of bipartite biotokens that release a secret key hidden in the biotoken by using biometrics. We show that the biotoken encoding of 80/112/128-bit symmetric encryption keys are vulnerable to brute force attacks, whose complexity is lower than cryptographic security. Also, we present the weaknesses in the design of revocable biotokens that form the basis for bipartite biotokens. Finally, we propose countermeasures to prevent these attacks and discuss the employment of other efficient cryptographic techniques that possess provable security guarantees.
Discourse of Reflections on Instant Joint Engagement in Online Elt Graduate Courses (chapter 17)
(Multilingual Matters, 2022) Çiftçi, Hatime; Dikilitaş, Kenan
In this chapter, we investigate the discourse of post-course reflections by in-service teachers on instant joint engagement in online ELT graduate courses. Our findings demonstrate that engagement for teacher reflection might be promoted in synchronous interactions during online teacher education courses. We argue that in-service teachers’ cognitive, socio-constructive, affective and interactive engagement can foster their critically reflective voice.
Citation - WoS: 3
Citation - Scopus: 10
An Fpga Implementation of a Risc-V Based Soc System for Image Processing Applications
(IEEE, 2021) Gholizadehazari, Erfan; Ayhan, Tuba; Ors, Berna
The Laplacian filter is one of the fundamental applications in image processing. In our work, the Laplacian filter has been applied to an image, and both hardware and software implementation of the filter has been studied. Our system consists of an OV7670 Camera module, Nexys 4 DDR FPGA board and VGA monitor to display the processed video stream. Mentioned process has forwarding tasks: camera module captures raw RGB data and writes to RAM, Laplacian filter IP processes raw image and the results written back to memory. VGA modules show output images to monitor. The Laplacian filter part considered in hardware and software implementation is compared in terms of time and area.
Citation - WoS: 1
Citation - Scopus: 1
Hata Düzeltme Çıktı Kodları: Genel Bakış, Zorluklar ve Gelecek Yönelimler
(IEEE, 2019) Arslan, Şuayb Şefik; Güney, Osman B.
Çok sınıflı sınıflandırma problemini çözmenin en etkili yollarından biri, bir grup akıllıca tasarlanmıs ikili sınıflandırıcı kullanarak, sınıflandırıcı sonuçlarını belli bir kritere göre bir araya getirmektir. Hata Düzeltme Çıktı Kodları (HDÇK) birden fazla ikili sınıflandırma yoluyla is bölümü saglayan basarılı tekniklerden biridir. Bu çalışmamızın amacı modern HDÇK tiplerine kısa bir giris yapmak, ikili sınıflandırma sonuçlarını birlestiren çesitli kod çözme yöntemleri ve zorlukları, avantajları ve dezavantajlarını ortaya koyan karsılastırmalı bir çalısma sunmaktır. Ayrıca HDÇK tekniğinin birkaç önemli uygulaması, MNIST veri seti üzerindeki performansı ve gelecekteki egilimlerin bazıları sunulmaktadır.
Corner Detection by Local Zernike Moments
(2015) Ozbulak, Gokhan; Gökmen, Muhittin
In this paper, our corner-based interest point detector, Robust Local Zernike Moment based Features (R-LZMF), which was proved to be scale, rotation and translation-invariant, is investigated for invariance against affine transformation, lighting and blurring. Furthermore, R-LZMF's corner detection capability with Zernike moments of order 4 is theoretically explained in detail. Experimental results on the Inria Dataset show that R-LZMF outperforms SIFT, CenSurE, ORB, BRISK and competes with SURF in terms of repeatability for images under affine transformation and photometric deformation such as lighting and blurring.

Browse

Browsing Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection by Scopus Q "N/A"