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

Mobile Mars Habitation
(Springer International Publishing, 2023) Müge Halıcı, Süheyla; Özdemir, Kürşad
This chapter focuses on the concept of mobile habitation on Mars. A description of Mars’ surface features is followed by a review of early concepts of crewed mobility for the Moon and Mars. Wheeled concepts for crew mobility continue to be based on the success of the Lunar Roving Vehicle, and predominantly take the form of a pressurized rover on wheels. With the help of architectural diagrams, the chapter introduces a range of habitable and mobile Mars structures, and the technologies used, taking into account mission requirements. © Springer Nature Switzerland AG 2023, corrected publication 2023.
Citation - WoS: 2
Citation - Scopus: 5
Compositional Neural Network Language Models for Agglutinative Languages
(2016) Saraçlar, Murat; Arısoy, Ebru
Continuous space language models (CSLMs) have been proven to be successful in speech recognition. With proper training of the word embeddings, words that are semantically or syntactically related are expected to be mapped to nearby locations in the continuous space. In agglutinative languages, words are made up of concatenation of stems and suffixes and, as a result, compositional modeling is important. However, when trained on word tokens, CSLMs do not explicitly consider this structure. In this paper, we explore compositional modeling of stems and suffixes in a long short-term memory neural network language model. Our proposed models jointly learn distributed representations for stems and endings (concatenation of suffixes) and predict the probability for stem and ending sequences. Experiments on the Turkish Broadcast news transcription task show that further gains on top of a state-of-theart stem-ending-based n-gram language model can be obtained with the proposed models.
Testing Soft Power in Hard Politics: Turkish Public Diplomacy During “Operation Peace Spring”
(Palgrave Macmillan, 2025) Güleç Aras, Cansu; Kibaroğlu, Mustafa
Public diplomacy is used by governments to significantly enhance their capability to maintain national unity and integrity as well as to advance their foreign policy objectives by cultivating a favorable environment among foreign peoples. In conflictual situations where military force is used, it is important to create an impact in a short time to promote national interests by informing and influencing the public. This chapter will first introduce the fundamental tenets of public diplomacy to offer a conceptual framework to better understand its use during military conflicts. It will then explore the implementation of public diplomacy instruments by Turkish government during the “Operation Peace Spring”, which was launched in October 2019. The chapter will also assess the performance of Turkish public diplomacy in the face of the extent of criticism leveled against Türkiye from around the world, including allied countries and international organizations. © 2025 The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.
Citation - WoS: 8
Citation - Scopus: 5
Recognizing Non-Manual Signs in Turkish Sign Language
(IEEE, 2019) Gökberk, Berk; Akarun, Lale; Aktaş, Müjde
Recognition of non-manual components in sign language has been a neglected topic, partly due to the absence of annotated non-manual sign datasets. We have collected a dataset of videos with non-manual signs, displaying facial expressions and head movements and prepared frame-level annotations. In this paper, we present the Turkish Sign Language (TSL) non-manual signs dataset and provide a baseline system for non-manual sign recognition. A deep learning based recognition system is proposed, in which the pre-trained ResNet Convolutional Neural Network (CNN) is employed to recognize question, negation side to side and negation up-down, affirmation and pain movements and expressions. Our subject independent method achieves 78.49% overall frame-level accuracy on 483 TSL videos performed by six subjects, who are native TSL signers. Prediction results of consecutive frames are filtered for analyzing the qualitative results.
Citation - Scopus: 4
Multi-View Reconstruction of 3d Human Pose With Procrustes Analysis
(IEEE, 2019) Gökberk, Berk; Akarun, Lale; Temiz, Hüseyin
Recovery of 3D human pose from cameras has been the subject of intensive research in the last decade. Algorithms that can estimate the 3D pose from a single image have been developed. At the same time, many camera environments have an array of cameras. In this paper, after aligning the poses obtained from single images using Procrustes Analysis, median filtering is utilized to eliminate outliers to find final reconstructed 3D body joint coordinates. Experiments performed on the CMU Panoptic, and Human3.6M databases demonstrate that the proposed system achieves accurate 3D body joint reconstructions. Additionally, we observe that camera selection is useful to decrease the system complexity while attaining the same level of reconstruction performance.
Dog Walker Segmentation
(IEEE, 2022) Ercan, Alperen; Karan, Baris; Çakar, Tuna
In this study dog walkers were separated into clusters according to walkers' walk habits. Due to the fact that the distributions were non-normal, normalization algorithms were applied before the onset of clustering. After normalizing, K Means algorithm and Gaussian Mixture Models used for finding optimum cluster count. According to these clusters, walkers' consecutive months separated to follow-up their behavioral traits. This part of the study adds value to the project to examine walkers' behaviors closer.
Citation - Scopus: 6
On the Difficulties in Manufacturing of Luffa Fibers Reinforced Biocomposites and Variations in Their Dynamic Properties
(Institute of Noise Control Engineering, 2016) Genç, Garip; Körük, Hasan
Defects in raw bio materials such as luffa plant effect the characteristics of the composites of these materials. These defects results in structural differences and large scattering mechanical properties such as density, damping and elasticity modulus. There are difficulties during the manufacturing of the composites from bio materials inherent to their nature. The major problems and restrictions encountered with the use of green luffa materials as reinforcement are studied in this study. First, the structural differences in the raw luffa plants are presented and the difficulties in their manufacturing are discussed. After that, the variations in measured modal parameters of luffa composites such as natural frequencies and loss factors and mechanical properties such as density and elasticity modulus are presented. Some solutions are provided to minimize the problems in manufacturing and identifying properties of luffa composites. The results show that the luffa composites can be produced with similar properties without any special selection of fibers to homogenize the batches of fibers for controlling the defects. However, a preliminary selection of fibers is required if the mechanical or dynamic properties of the luffa composites are desired to have small variations.
İnternet Trafik Hızının Tahmininde Derin Öğrenme ve Ağaç Tabanlı Modellerin Karşılaştırılması
(Institute of Electrical and Electronics Engineers Inc., 2025) Filiz, Gozde; Altıntaş, Suat; Yıldız, Ayşenur; Kara, Erkan; Drias, Yassine; Çakar, Tuna
This study addresses the prediction of internet traffic speed using time-dependent data from an internet service provider through different modeling approaches. On an anonymized dataset, the performance of the moving average method, various deep learning models (N-BEATS, N-HITS, TimesNet, TSMixer, LSTM), and the XGBoost regression model enhanced with feature engineering was compared. Time series cross-validation and random hyperparameter search were used for model training. According to the results, the XGBoost model achieved the highest accuracy with 98.7% explained variance (R2), while among the deep learning models, N-BEATS and N-HITS achieved the best performance with R2 values around 90%. The findings indicate that tree-based methods supported by carefully selected features can offer higher accuracy and computational efficiency compared to complex deep learning models in internet traffic forecasting. © 2025 Elsevier B.V., All rights reserved.
A Practical PCB-Based Framework for Spiking Neural Networks with a Half-Adder Example
(IEEE, 2025) Cikikci, Sevde Vuslat; Orek, Eren; Aysoy, Ayhan; Ozgen, Ali Kagan; Yavuz, Arda; Ayhan, Tuba
This paper addresses the half-adder problem using Spiking Neural Networks (SNNs). In a previous study, the XOR operation was successfully realized on a breadboard and in this study it is integrated into the half-adder structure. The system uses input signals at frequencies of 50 Hz and 100 Hz and the neurons are generated by the Leaky Integrate and Fire (LIF) model. Unlike other neuron models, the LIF model is less complex. In addition, it was preferred because of its biological meaningfulness compared to the Integrate and Fire model. The network, consisting of 18 neurons in total, shows that basic arithmetic operations can be performed with SNN. Overall, this study demonstrates that basic logic operations can be implemented in neural networks, thus providing new perspectives for digital calculation. The successful solution of the Half Adder problem using SNNs not only proves the calculation capabilities of SNNs, but also opens new perspectives for the development of more complex logical circuits using these biologically inspired neural circuits.
Citation - WoS: 536
Citation - Scopus: 652
Human Semantic Parsing for Person Re-Identification
(2018) Kalayeh, Mahdi M; Başaran, Emrah; Shah, Mubarak; Kamasak, Mustafa E; Gökmen, Muhittin
Person re-identification is a challenging task mainly dueto factors such as background clutter, pose, illuminationand camera point of view variations. These elements hinder the process of extracting robust and discriminative representations, hence preventing different identities from being successfully distinguished. To improve the representation learning, usually local features from human body partsare extracted. However, the common practice for such aprocess has been based on bounding box part detection.In this paper, we propose to adopt human semantic parsing which, due to its pixel-level accuracy and capabilityof modeling arbitrary contours, is naturally a better alternative. Our proposed SPReID integrates human semanticparsing in person re-identification and not only considerably outperforms its counter baseline, but achieves stateof-the-art performance. We also show that, by employinga simple yet effective training strategy, standard populardeep convolutional architectures such as Inception-V3 andResNet-152, with no modification, while operating solelyon full image, can dramatically outperform current stateof-the-art. Our proposed methods improve state-of-the-artperson re-identification on: Market-1501 [48] by ~17% inmAP and ~6% in rank-1, CUHK03 [24] by ~4% in rank-1and DukeMTMC-reID [50] by ~24% in mAP and ~10% inrank-1.
Design-Build Build/Design: an Inquiry-Based Approach To Teaching Beginning Design Students
(Taylor and Francis, 2018) Subotincic, Natalija
This chapter describes an alternate design studio approach that eschews the concept first pedagogy universally adopted in design studio education, avoiding the resulting trap of the seemingly endless formal manipulations that all too often displace the more inclusive material and technical development of a design. The introduction of "design-build" studios and programs into the academic architectural curricula of many schools worldwide reflects recognition of the unhealthy and artificial separation made between design studio culture and the content of technical courses and constitutes an important way of bridging this self-imposed gap. Preserving the simultaneity of concerns and relationships during the design process, although difficult, is rather crucial to an "inquiry-based" approach to learning. When beginning design students start a project without a particular building system in mind, they tend to flounder with respect to design decisions about the tectonic constraints and technical/constructional possibilities of their designs. © 2019 Taylor and Francis.
Fault Detection Model Using Measurement Data in Fiber Optic Internet Lines
(IEEE, 2023) Çakar, Tuna; Savaş, Kerem; Battal, Eray; Özkan, Gözde
In this study, a model has been developed to predict potential faults in advance based on performance metrics of various fiber-optic internet lines, as well as alarm (fault data) and performance measurement values from the 5 hours prior to the occurrence of the alarm. Performance metrics that vary over time have been analyzed in a time-series format based on alarm numbers, and anomaly detection methods have been used to label the data for any potential patterns that may occur in the performance metrics specific to the alarm. The labeled data was then fed into a classification model to create a model that enables to detect possible patterns in the relevant performance values for the specific fault type. The best performing model was Random Forest Classifier with accuracy and F1 scores of 0.89 and 0.84 respectively.
Citation - Scopus: 2
A Visualization Platfom for Disk Failure Analysis
(IEEE, 2018) Arslan, Şuayb Şefik; Yiğit, İbrahim Onuralp; Zeydan, Engin
It has become a norm rather than an exception to observe multiple disks malfunctioning or whole disk failures in places like big data centers where thousands of drives operate simultaneously. Data that resides on these devices is typically protected by replication or erasure coding for long-term durable storage. However, to be able to optimize data protection methods, real life disk failure trends need to be modeled. Modelling helps us build insights while in the design phase and properly optimize protection methods for a given application. In this study, we developed a visualization platform in light of disk failure data provided by BackBlaze, and extracted useful statistical information such as failure rate and model-based time to failure distributions. Finally, simple modeling is performed for disk failure predictions to alarm and take necessary system-wide precautions.
Citation - Scopus: 9
Bilinçli-farkındalık Temelli Öz-yeterlik Ölçeği-yenilenmiş (bföö-y): Türkiye Uyarlama Çalışması
(2017) Taylan, Rukiye Didem; Bulgan, Gökçe; Atalay, Zümra; Aydın, Utkun
Bu araştırmanın amacı, Cayoun, Francis, Kasselis ve Skilbeck (2012) tarafından geliştirilen "Bilinçli- Farkındalık Temelli Öz-yeterlik Ölçeği-Yenilenmiş"i (Mindfulness-Based Self Efficacy Scale-Revised) Türkçe'ye uyarlayarak geçerlik ve güvenirliğini araştırmaktır. Özgün ölçek İngilizce'dir ve altı boyutta toplam 22 maddeden oluşan beşli likert tipi bir ölçme aracıdır. Uyarlanan Türkçe form iki farklı devlet okulunun 5., 6. ve 7. sınıflarında okuyan 713 öğrenciye uygulanmıştır. Tüm ölçek (?= .72) ve ölçeğin Duygu Düzenleme (?= .73), Duygusal Denge (?= .68), Sosyal Beceriler (?= .65), Sıkıntı Tahammülü (?= .62), Sorumluluk Alma (?= .61) ve Kişilerarası Etkenlik (?= .65) alt boyutları için Cronbach Alfa içtutarlık katsayıları her bir alt boyutta yer alan düşük madde sayısı göz önüne alındığında kabul edilebilir seviyededir. Ayırt edici geçerlik analizleri kız ve erkeklerin bilinçli-farkındalık temelli öz-yeterlik ortalama puanları arasında anlamlı bir fark olmadığını gösterirken sınıf düzeyi açısından anlamlı farklılıklar gözlemlenmiştir. Analiz sonuçları, Türkçe'ye uyarlama çalışması gerçekleştirilen bu ölçeğin öğrencilerin bilinçli-farkındalık temelli öz-yeterlik düzeylerini belirlemede geçerli ve güvenilir bir ölçme aracı olduğunu göstermektedir. Sonuçların kuramsal ve yöntemsel uygulamaları tartışılmıştır
Citation - Scopus: 9
Steel Surface Defect Classification Via Deep Learning
(IEEE, 2022) Yildiz, Ahmet; Çakar, Tuna; Tunal, Mustafa Mert
Deep learning and image processing methods have taken place in many parts of our lives, as well as in the quality control stages of production lines. The aim of this study is to train and use a deep learning model to improve quality management using limited data and computing power. To achieve that, deep learning for quality control models were trained by classifying six different steel surface defect images in the NEU-DET dataset. Xception, ResNetV2 152, VGG19 and InceptionV3 architectures were used to train the model. High accuracy was obtained with both Xception and ResNetV2 152. © 2022 IEEE.
Citation - WoS: 5
Citation - Scopus: 7
Cloud2hdd: Large-Scale Hdd Data Analysis on Cloud for Cloud Datacenters
(IEEE, 2020) Zeydan, Engin; Arslan, Şefik Şuayb
The main focus of this paper is to develop a distributed large scale data analysis platform for the opensource data of Backblaze cloud datacenter which consists of operational hard disk drive (HDD) information collected over an observable period of 2272 days (over 74 months). To carefully analyze the intrinsic characteristics of the hard disk behavior, we have exploited a large bolume of data and the benefits of Hadoop ecosystem as our big data processing engine. In other words, we have utilized a special distributed scheme on cloud for cloud HDD data, which is termed as Cloud2HDD. To classify the remaining lifetime of hard disk drives based on health indicators such as in-built S.M.A.R.T (Self-Monitoring, Analysis, and Reporting Technology) features, we used some of the state-of-the-art classification algorithms and compared their accuracy, precision, and recall rates simultaneously. In addition, importance of various S.M.A.R.T. features in predicting the true remaining lifetime of HDDs are identified. For instance, our analysis results indicate that Random Forest Classifier (RFC) can yield up to 94% accuracy with the highest precision and recall at a reasonable time by classifying the remaining lifetime of drives into one of three different classes, namely critical, high and low ideal states in comparison to other classification approaches based on a specific subset of S.M.A.R.T. features.
Ensemble-Based Stock Prediction for Retail - XGBoost and LightGBM with Rolling Window Training
(Institute of Electrical and Electronics Engineers Inc., 2025) Patel, Jay Nimish; Kizilay, Ayse; Şahin, Zeynep; Sercan, Busra; Toprak, Samet; Çakar, Tuna
Stock prediction in retail settings is a critical challenge that impacts numerous businesses globally, that require precise and timely forecasts to optimize inventory management and enhance customer satisfaction. State-of-the-art approaches for accurate stock prediction leverage machine learning (ML) models, which require large amounts of historical sales data for effective training. Such detailed datasets are often hard to obtain, limiting the performance and scalability of these approaches. In this paper, we propose various strategies to tackle this limitation. Initially, we adopt a transfer-learning approach, utilizing pre-trained models like XGBoost and LightGBM, which are fine-tuned for stock prediction in retail environments. To further boost model performance, we incorporate an ensemble method that combines predictions from both models to improve accuracy and manage outliers. Experiments conducted on an extremely large dataset, comprising millions of retail transactions, highlight the presence of significant outliers. Our models, augmented with ensemble strategies, significantly outperform traditional models in handling these complexities and improving prediction accuracy. © 2025 Elsevier B.V., All rights reserved.
Citation - WoS: 15
Citation - Scopus: 40
An Overview of Blockchain Technologies: Principles, Opportunities and Challenges
(IEEE, 2018) Arslan, Şuayb Şefik; Mermer, Gültekin Berahan; Zeydan, Engin
Blokzincir, toplumumuzun birbiriyle iletişim kurma ve ticaret yapma biçiminde devrim yapma potansiyeline sahip, yakın zamanda ortaya çıkmış olan bir teknolojidir. Bu teknolojinin sağladığı en önemli avantaj aracı gerektiren bir oluşumda güvenilir bir merkezi kuruma ihtiyaç duymadan değer taşıyan işlemleri değiş tokuş edebilmesidir. Ayrıca, veri bütünlüğü, dahili orijinallik ve kullanıcı şeffaflığı sağlayabilir. Blokzincir, birçok yenilikçi uygulamanın temel alınacağı yeni internet olarak görülebilir. Bu çalışmada, genel çalışma prensibi, oluşan fırsatlar ve ileride karşılaşılabilecek zorlukları içerecek şekilde güncel blokzincir teknolojilerinin genel bir görünümünü sunmaktayız.
The Application of Two Bayesian Personalized Ranking Approaches Based on Item Recommendation From Implicit Feedback
(Ieee, 2024) Tagtekin, Burak; Sahin, Zeynep; Çakar, Tuna; Drias, Yassine
The present study has aimed to provide a different ranking approach that will be used actively in a sector-specific application regarding the optimization of item ranking presented to the users. The current online approach in several different applications still holds a manual ranking algorithm whose parameters are determined by the data specialists with adequate domain-knowledge. The obtained findings from the present study indicate that the optimized Bayesian Personalized Ranking models will be used for providing a suitable, data-driven input for the ranking system that would serve to be personalized. The outcomes of the present study also demonstrate that the model using LearnBPR optimized with a stochastic gradient descent algorithm outperform the other similar methods. The sample model outputs were also investigated by a user sample to ensure that the algorithm was working correctly. The next potential step is to provide a normalization process to include the extracted information to the current ranking system and observe the performance of this new algorithm with the A/B tests conducted.
Citation - WoS: 1
Citation - Scopus: 1
Adaptive Boosting of Dnn Ensembles for Brain-Computer Interface Spellers
(IEEE, 2021) Çatak, Yiğit; Aksoy, Can; Özkan, Hüseyin; Güney, Osman Berke; Koç, Emirhan; Arslan, Şuayb Şefik
Steady-state visual evoked potentials (SSVEP) are commonly used in brain computer interface (BCI) applications such as spelling systems, due to their advantages over other paradigms. In this study, we develop a method for SSVEP-based BCI speller systems, using a known deep neural network (DNN), which includes transfer and ensemble learning techniques. We test performance of our method on publicly available benchmark and BETA datasets with leave-one-subject-out procedure. Our method consists of two stages. In the first stage, a global DNN is trained using data from all subjects except one subject that is excluded for testing. In the second stage, the global model is fine-tuned to each subject whose data are used in the training. Combining the responses of trained DNNs with different weights for each test subject, rather than an equal weight, provide better performance as brain signals may differ significantly between individuals. To this end, weights of DNNs are learnt with SAMME algorithm with using data belonging to the test subject. Our method significantly outperforms canonical correlation analysis (CCA) and filter bank canonical correlation analysis (FBCCA) methods.

Browse

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