WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/256

Browse

Now showing 1 - 20 of 122

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.
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.
Energy Consumption at Home: Insights for Sustainable Smart Home Marketing
(Springer International Publishing Ag, 2023) Köse, Şirin Gizem; Cizer, Ece Ozer; Kazancoglu, Ipek
Energy consumption has been a vital subject for both energy producers and consumers. The intersection of energy consumption and home words are of increasing importance in both literature and practice. Households try to utilize energy in the most efficient and sustainable way. On the other hand, smart home technologies which let the households control their houses are on the rise. Those technologies also help balance the energy consumption and live in a more sustainable way. This study aims to underline the importance of smart home technologies to increase energy efficiency and pave the way for a more sustainable energy management. In line with this purpose, a bibliometric study has been conducted to enlighten the literature development in energy consumption and home subjects. The results are expected to be helpful for both literature and practice as well as energy providers and consumers.
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.
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.
Supporting Flipped Learning: Digital Pedagogy, Training, and Resources
(Emerald Group Publishing Ltd., 2016) Kurban, Caroline Fell; Şahin, Muhammed
…
Citation - WoS: 12
Citation - Scopus: 12
Bilevel Models on the Competitive Facility Location Problem
(Springer, 2017) Küçükaydın, Hande; Aras, Necati
Facility location and allocation problems have been a major area of research for decades, which has led to a vast and still growing literature. Although there are many variants of these problems, there exist two common features: finding the best locations for one or more facilities and allocating demand points to these facilities. A considerable number of studies assume a monopolistic viewpoint and formulate a mathematical model to optimize an objective function of a single decision maker. In contrast, competitive facility location (CFL) problem is based on the premise that there exist competition in the market among different firms. When one of the competing firms acts as the leader and the other firm, called the follower, reacts to the decision of the leader, a sequential-entry CFL problem is obtained, which gives rise to a Stackelberg type of game between two players. A successful and widely applied framework to formulate this type of CFL problems is bilevel programming (BP). In this chapter, the literature on BP models for CFL problems is reviewed, existing works are categorized with respect to defined criteria, and information is provided for each work.
Fading Boundaries: Insights on Learning "in Between" the Classroom Spaces
(Springer international Publishing Ag, 2021) Soygeniş, Sema Esen; Baloglu, Yasemin Burcu; Baloğlu, Yasemin Burcu; Soygenis, Sema Esen
Along with the advancements in technology and shifts in approaches to education in our day, school architecture began to undergo significant transformations. Learning beyond the classrooms has emerged as a highlighted concern as well as the children's interaction with each other and their environment. Articulation of the changing pedagogical approaches and visions of the innovative, student-centered ideas of the twenty-first century through the physical characters of learning spaces has become a significant issue for research regarding the design of contemporary schools. The evolution of the formation of boundaries, borders, and thresholds defining the distinctions and establishing the relationships and hierarchies between the learning spaces at school settings constitutes a critical part of this process, which deserves attention. This chapter aims to search for boundary-related design suggestions for primary schools in Turkey, based on the data obtained through a field study conducted in Istanbul, which aimed to derive the current issues regarding the spatial use patterns in prototype-based, conventionally designed schools. It is believed that the effective inhabitation of spaces beyond the classrooms has a high potential to contribute to the realization of diverse educational activities and the introduction of more permeable physical and visual boundaries can support the enrichment of school environments.
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.
Anamorphic Projection as a Novel Game Mechanic for Investigating Impossible Spaces in 3D Puzzle Games
(IEEE Computer Society, 2025) Aydındoğan, Irem; Alaçam, Sema
This study introduces a novel game mechanic for 3D puzzle games based on anamorphic projection to explore impossible spaces. By using perspective-driven spatial interactions, the mechanic creates environments that challenge conventional Euclidean logic. Players advance by aligning their viewpoint with distorted projections, making perception a central element of gameplay. A usability test with 33 participants assessed the mechanic's effectiveness through a structured questionnaire focusing on six dimensions: Ease of Control, Goals and Rules, Challenge, Mastery, Curiosity, and Immersion. Results indicate high engagement and cognitive stimulation, especially in mastery and goal clarity. These findings highlight the potential of anamorphic projection to support perceptually rich and mentally engaging puzzle experiences in future game design. © 2025 IEEE.
Evaluating a Model From Two Perspectives: Teachers and University Scholars
(2016) Aktekin, Nafiye Çiğdem
Productive strategies for evaluating outcomes are becoming increasingly important for the improvement of teacher education [1] and for any model that claims to offer the best practice. The University within School (UwS) model suggests that teacher education must be done through collaboration between universities and schools. According to Ozcan [2], the model combines two models of professional education: one is the traditional "apprenticeship-journeyman-master's" model, which is practice-based; the other is modern professional education, which is mostly based on theoretical knowledge and is implemented through formal schooling. Students and academicians of an education faculty of a foundation university have been practicing to this end in a workplace for two years. Teachers of the partner school have been part of this model as mentor teachers, role models, and participants. This study aims to evaluate the model from the perspectives of teachers and college faculty since the model aims to prepare the conceptual framework of teacher education through the participation of all partners. The perceptions of two faculty members and three teachers were investigated through interviews. The evaluation of the model will help to design the model more effectively.
Introduction To the Papers of Twg19: Mathematics Teachers and Classroom Practices
(Dublin City Univ Glasnevin Campus, 2017) Mosvold, Reidar; Skott, Jeppe; Taylan, Rukiye Didem; Drageset, Ove Gunnar; Sakonidis, Charalampos
…
The Flipped Approach To Higher Education Designing Universities for Today's Knowledge Economies and Societies Preface
(Emerald Group Publishing Ltd, 2016) Sahin, Muhammed; Kurban, Caroline Fell
Strategic Financial Management for Small and Medium Sized Companies Conclusion
(Emerald Group Publishing Ltd., 2015) Karadağ, Hande
...
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.
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 WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection by WoS Q "N/A"