Bilgisayar Mühendisliği Bölümü Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.11779/1940

Browse

Now showing 1 - 15 of 15

Citation - WoS: 2
Citation - Scopus: 1
A Benchmark Dataset for Turkish Data-To Generation
(Elsevier, 2022) Demir, Şeniz; Öktem, Seza
In the last decades, data-to-text (D2T) systems that directly learn from data have gained a lot of attention in natural language generation. These systems need data with high quality and large volume, but unfortunately some natural languages suffer from the lack of readily available generation datasets. This article describes our efforts to create a new Turkish dataset (Tr-D2T) that consists of meaning representation and reference sentence pairs without fine-grained word alignments. We utilize Turkish web resources and existing datasets in other languages for producing meaning representations and collect reference sentences by crowdsourcing native speakers. We particularly focus on the generation of single-sentence biographies and dining venue descriptions. In order to motivate future Turkish D2T studies, we present detailed benchmarking results of different sequence-to-sequence neural models trained on this dataset. To the best of our knowledge, this work is the first of its kind that provides preliminary findings and lessons learned from the creation of a new Turkish D2T dataset. Moreover, our work is the first extensive study that presents generation performances of transformer and recurrent neural network models from meaning representations in this morphologically-rich language.
Citation - WoS: 5
Citation - Scopus: 8
A Data-Assisted Reliability Model for Carrier-Assisted Cold Data Storage Systems
(Elsevier, 2020) Arslan, Şuayb Şefik; Göker, Turguy; Peng, James
Cold data storage systems are used to allow long term digital preservation for institutions’ archive. The common functionality among cold and warm/hot data storage is that the data is stored on some physical medium for read-back at a later time. However in cold storage, write and read operations are not necessarily done in the same exact geographical location. Hence, a third party assistance is typically utilized to bring together the medium and the drive. On the other hand, the reliability modeling of such a decomposed system poses few challenges that do not necessarily exist in other warm/hot storage alternatives such as fault detection and absence of the carrier, all totaling up to the data unavailability issues. In this paper, we propose a generalized non-homogenous Markov model that encompasses the aging of the carriers in order to address the requirements of today's cold data storage systems in which the data is encoded and spread across multiple nodes for the long-term data retention. We have derived useful lower/upper bounds on the overall system availability. Furthermore, the collected field data is used to estimate parameters of a Weibull distribution to accurately predict the lifetime of the carriers in an example scale-out setting.
Citation - WoS: 6
Citation - Scopus: 7
A Reliability Model for Dependent and Distributed Mds Disk Array Units
(IEEE Transactions on Reliability, 2018) Arslan, Şuayb Şefik
Archiving and systematic backup of large digital data generates a quick demand for multi-petabyte scale storage systems. As drive capacities continue to grow beyond the few terabytes range to address the demands of today’s cloud, the likelihood of having multiple/simultaneous disk failures became a reality. Among the main factors causing catastrophic system failures, correlated disk failures and the network bandwidth are reported to be the two common source of performance degradation. The emerging trend is to use efficient/sophisticated erasure codes (EC) equipped with multiple parities and efficient repairs in order to meet the reliability/bandwidth requirements. It is known that mean time to failure and repair rates reported by the disk manufacturers cannot capture life-cycle patterns of distributed storage systems. In this study, we develop failure models based on generalized Markov chains that can accurately capture correlated performance degradations with multiparity protection schemes based on modern maximum distance separable EC. Furthermore, we use the proposed model in a distributed storage scenario to quantify two example use cases: Primarily, the common sense that adding more parity disks are only meaningful if we have a decent decorrelation between the failure domains of storage systems and the reliability of generic multiple single-dimensional EC protected storage systems.
Citation - WoS: 29
Citation - Scopus: 38
An Efficient Framework for Visible-Infrared Cross Modality Person Re-Identification
(Elsevier, 2020) Gökmen, Muhittin; Başaran, Emrah; Kamasak, Mustafa E.
Visible-infrared cross-modality person re-identification (VI-ReId) is an essential task for video surveillance in poorly illuminated or dark environments. Despite many recent studies on person re-identification in the visible domain (ReId), there are few studies dealing specifically with VI-ReId. Besides challenges that are common for both ReId and VI-ReId such as pose/illumination variations, background clutter and occlusion, VI-ReId has additional challenges as color information is not available in infrared images. As a result, the performance of VI-ReId systems is typically lower than that of ReId systems. In this work, we propose a four-stream framework to improve VI-ReId performance. We train a separate deep convolutional neural network in each stream using different representations of input images. We expect that different and complementary features can be learned from each stream. In our framework, grayscale and infrared input images are used to train the ResNet in the first stream. In the second stream, RGB and three-channel infrared images (created by repeating the infrared channel) are used. In the remaining two streams, we use local pattern maps as input images. These maps are generated utilizing local Zernike moments transformation. Local pattern maps are obtained from grayscale and infrared images in the third stream and from RGB and three-channel infrared images in the last stream. We improve the performance of the proposed framework by employing a re-ranking algorithm for post-processing. Our results indicate that the proposed framework outperforms current state-of-the-art with a large margin by improving Rank-1/mAP by 29.79%/30.91% on SYSU-MM01 dataset, and by 9.73%/16.36% on RegDB dataset.
Citation - WoS: 19
Citation - Scopus: 27
An Evaluation of Recent Neural Sequence Tagging Models in Turkish Named Entity Recognition
(Elsevier, 2021) Makaroğlu, Didem; Demir, Şeniz; Aras, Gizem; Çakır, Altan
Named entity recognition (NER) is an extensively studied task that extracts and classifies named entities in a text. NER is crucial not only in downstream language processing applications such as relation extraction and question answering but also in large scale big data operations such as real-time analysis of online digital media content. Recent research efforts on Turkish, a less studied language with morphologically rich nature, have demonstrated the effectiveness of neural architectures on well-formed texts and yielded state-of-the art results by formulating the task as a sequence tagging problem. In this work, we empirically investigate the use of recent neural architectures (Bidirectional long short-term memory (BiLSTM) and Transformer-based networks) proposed for Turkish NER tagging in the same setting. Our results demonstrate that transformer-based networks which can model long-range context overcome the limitations of BiLSTM networks where different input features at the character, subword, and word levels are utilized. We also propose a transformer-based network with a conditional random field (CRF) layer that leads to the state-of-the-art result (95.95% f-measure) on a common dataset. Our study contributes to the literature that quantifies the impact of transfer learning on processing morphologically rich languages.
Citation - WoS: 9
Citation - Scopus: 16
Compress-Store on Blockchain: a Decentralized Data Processing and Immutable Storage for Multimedia Streaming
(Springer, 2022) Arslan, Şuayb Şefik; Turguy, Göker
Decentralization for data storage is a challenging problem for blockchain-based solutions as the blocksize plays a key role for scalability. In addition, specific requirements of multimedia data call for various changes in the blockchain technology internals. Considering one of the most popular applications of secure multimedia streaming, i.e., video surveillance, it is not clear how to judiciously encode incentivization, immutability, and compression into a viable ecosystem. In this study, we provide a genuine scheme that achieves this encoding for a video surveillance application. The proposed scheme provides a novel integration of data compression, immutable off-chain data storage using a new consensus protocol namely, Proof-of-WorkStore (PoWS) in order to enable fully useful work to be performed by the miner nodes of the network. The proposed idea is the first step towards achieving greener application of a blockchain-based environment to the video storage business that utilizes system resources efficiently.
Citation - WoS: 3
Citation - Scopus: 3
Designing restorative landscapes for students: A Kansei engineering approach enhanced by VR and EEG technologies
(Elsevier, 2024) Karaca, Elif; Çakar, Tuna; Karaca, Mehmet; Gul, Hasan Huseyin Mirac
This study explores the alignment of specific landscape features within school environments with the core elements of Attention Restoration Theory (ART) that includes Coherence, Fascination, Compatibility, and Being Away. Utilizing Kansei Engineering, this research integrates emotional analysis into landscape design by employing Virtual Reality (VR) and Electroencephalogram (EEG) technologies to record students' responses to different landscape simulations. Analytical techniques, including the Taguchi Method and Analysis of Variance (ANOVA), were applied to evaluate the data. The findings have revealed that students associate a sense of enclosure with a coherent landscape and openness with a fascinating landscape, the lawn's significance was also highlighted for coherent landscape. However, limited insights were gained regarding Compatibility and Being Away. The study advocates for diverse cognitive zones within school landscapes to promote mental restoration, emphasizing the need for varied design elements that cater to the elevated experience of students.
Citation - WoS: 6
Citation - Scopus: 12
During the Covid-19 Pandemic, Students' Opinions on Distance Education in Department of Engineering
(International Association of Online Engineering (IAOE), 2022) Zaripova, Zülfiya F.; Karahoca, Dilek; Chikileva, Lyudmila S.; Lyalyaev, Sergey V.; Xu, Baoyun; Bayanova, Almira R.
The decision regarding the distance education method in Turkey on March 15, 2020, has completely changed the learning and teaching methodology of all university students and educators, and it has been seen that all courses have started to be given with distance education. The purpose of this research is to examine the perspectives of engineering university students towards distance education during the Covid-19 pandemic. The research consists of engineering faculty students studying at various universities in the Aegean region and Russian Federation. In the research, a scanning model was used. The data of the research were collected from 520 engineering department university students from various universities in our country, according to the convenience sampling method, and through an online questionnaire filled out by the students. Thanks to this wide participation, results have been obtained that will explain the Covid-19 process related to distance education in a good way. In general, it has been concluded that students are happy to see them in distance education model courses, so they do not fall behind in their education, and university students watch their courses mostly with the help of smart devices.
Citation - WoS: 8
Citation - Scopus: 7
Enhanced Primordial Gravitational Waves From a Stiff Postinflationary Era Due To an Oscillating Inflaton
(Amer Physical Soc, 2024) Chen, Chao; Dimopoulos, Konstantinos; Eroncel, Cem; Ghoshal, Anish
We investigate two classes of inflationary models, which lead to a stiff period after inflation that boosts the signal of primordial gravitational waves (GWs). In both families of models studied, we consider an oscillating scalar condensate, which when far away from the minimum is overdamped by a warped kinetic term, a la alpha-attractors. This leads to successful inflation. The oscillating condensate is in danger of becoming fragmented by resonant effects when nonlinearities take over. Consequently, the stiff phase cannot be prolonged enough to enhance primordial GWs at frequencies observable in the near future for low orders of the envisaged scalar potential. However, this is not the case for a higher-order scalar potential. Indeed, we show that this case results in a boosted GW spectrum that overlaps with future observations without generating too much GW radiation to destabilize big bang nucleosynthesis. For example, taking alpha=O(1), we find that the GW signal can be safely enhanced up to Omega(GW) (f)similar to 10(-11) at frequency f similar to 10(2) Hz, which will be observable by the Einstein Telescope. Our mechanism ends up with a characteristic GW spectrum, which if observed, can lead to the determination of the inflation energy scale, the reheating temperature, and the shape (steepness) of the scalar potential around the minimum.
Citation - WoS: 3
Citation - Scopus: 3
Exact Construction of Bs-Assisted Mscr Codes With Link Constraints
(IEEE Communications Letters, 2021) Arslan, Şuayb Şefik
It is clear that 5G network resources would be consumed by heavy data traffic owing to increased mobility, slicing, and layered/distributed storage system architecture. The problem is elevated when multiple node failures are repaired to address service quality requirements. Typical approaches include individual or cooperative data regeneration to efficiently utilize the available bandwidth. It is observed that storage systems of 5G and beyond technologies shall have a multi–layer architecture in which base stations (BS) would be present. Moreover, communication with each layer would be subject to various communication costs and link constraints. Under limited BS assistance and cooperation, the trade-off between storage per node and communication bandwidth has been established. In this trade–off, two operating points, namely minimum storage, and bandwidth regeneration are particularly important. In this study, we first identify the optimal number of BS use at the minimum storage regeneration point. An explicit code construction is provided subsequently for the exact minimum storage regeneration whereby each layer may help the repair process subject to a communication link constraint.
Citation - WoS: 12
Citation - Scopus: 15
Face Recognition With Patch-Based Local Walsh Transform
(Elsevier, 2018) Uzun-Per, Meryem; Gökmen, Muhittin
In this paper, we present a novel dense local image representation method called Local Walsh Transform (LWT)by applying the well-known Walsh Transform (WT) to each pixel of an image. The LWT decomposes an image into multiple components, and produces LWT complex images by using the symmetrical relationship between them. Cascaded LWT (CLWT) is also a dense local image representation obtained by applying the LWT again to real and imaginary parts of LWT complex images. Applying the LWT once more to real and imaginary parts of LWT complex images increases the success rate especially on low resolution images. In order to combine the advantages of sparse and dense local image representations, we present Patch-based LWT (PLWT) and Patch-based CLWT (PCLWT) by applying the LWT and CLWT, respectively, to patches extracted around landmarks of multi-scaled face images. The extracted high dimensional features of the patches are reduced through the application of the Whitened Principal Component Analysis (WPCA). Experimental results show that both thePLWT and PCLWT are robust to illumination and expression changes, occlusion and low resolution. The state-of-the-art performance is achieved on the FERET and SCface databases, and the second best unsupervised category result is achieved on the LFW database.
Citation - WoS: 5
Citation - Scopus: 9
Graph-Based Turkish Text Normalization and Its Impact on Noisy Text Processing
(Elsevier, 2022) Topçu, Berkay; Demir, Şeniz
User generated texts on the web are freely-available and lucrative sources of data for language technology researchers. Unfortunately, these texts are often dominated by informal writing styles and the language used in user generated content poses processing difficulties for natural language tools. Experienced performance drops and processing issues can be addressed either by adapting language tools to user generated content or by normalizing noisy texts before being processed. In this article, we propose a Turkish text normalizer that maps non-standard words to their appropriate standard forms using a graph-based methodology and a context-tailoring approach. Our normalizer benefits from both contextual and lexical similarities between normalization pairs as identified by a graph-based subnormalizer and a transformation-based subnormalizer. The performance of our normalizer is demonstrated on a tweet dataset in the most comprehensive intrinsic and extrinsic evaluations reported so far for Turkish. In this article, we present the first graph-based solution to Turkish text normalization with a novel context-tailoring approach, which advances the state-of-the-art results by outperforming other publicly available normalizers. For the first time in the literature, we measure the extent to which the accuracy of a Turkish language processing tool is affected by normalizing noisy texts before being processed. An analysis of these extrinsic evaluations that focus on more than one Turkish NLP task (i.e., part-of-speech tagger and dependency parser) reveals that Turkish language tools are not robust to noisy texts and a normalizer leads to remarkable performance improvements once used as a preprocessing tool in this morphologically-rich language.
Citation - WoS: 3
Citation - Scopus: 5
On the Distribution Modeling of Heavy-Tailed Disk Failure Lifetime in Big Data Centers
(IEEE, 2021) Arslan, Şuayb Şefik; Zeydan, Engin
It has become commonplace to observe frequent multiple disk failures in big data centers in which thousands of drives operate simultaneously. Disks are typically protected by replication or erasure coding to guarantee a predetermined reliability. However, in order to optimize data protection, real life disk failure trends need to be modeled appropriately. The classical approach to modeling is to estimate the probability density function of failures using nonparametric estimation techniques such as kernel density estimation (KDE). However, these techniques are suboptimal in the absence of the true underlying density function. Moreover, insufficient data may lead to overfitting. In this article, we propose to use a set of transformations to the collected failure data for almost perfect regression in the transform domain. Then, by inverse transformation, we analytically estimated the failure density through the efficient computation of moment generating functions, and hence, the density functions. Moreover, we developed a visualization platform to extract useful statistical information such as model-based mean time to failure. Our results indicate that for other heavy-tailed data, the complex Gaussian hypergeometric distribution and classical KDE approach can perform best if the overfitting problem can be avoided and the complexity burden is overtaken. On the other hand, we show that the failure distribution exhibits less complex Argus-like distribution after performing the Box–Cox transformation up to appropriate scaling and shifting operations.
Citation - WoS: 27
Citation - Scopus: 30
Service-Aware Multi-Resource Allocation in Software-Defined Next Generation Cellular Networks
(2018) Arslan, Şuayb Şefik; Zeydan, Engin; Narmanloğlu, Ömer
Network slicing is one of the major solutions needed to meet the requirements of next generation cellular networks, under one common network infrastructure, in supporting multiple vertical services provided by mobile network operators. Network slicing makes one shared physical network infrastructure appear as multiple logically isolated virtual networks dedicated to different service types where each Network Slice (NS) benefits from on-demand allocated resources. Typically, the available resources distributed among NSs are correlated and one needs to allocate them judiciously in order to guarantee the service, MNO, and overall system qualities. In this paper, we consider a joint resource allocation strategy that weights the significance of the resources per a given NS by leveraging the correlation structure of different quality-of-service (QoS) requirements of the services. After defining the joint resource allocation problem including the correlation structure, we propose three novel scheduling mechanisms that allocate available network resources to the generated NSs based on different type of services with different QoS requirements. Performance of the proposed schedulers are then investigated through Monte-Carlo simulations and compared with each other as well as against a traditional max-min fairness algorithm benchmark. The results reveal that our schedulers, which have different complexities, outperform the benchmark traditional method in terms of service-based and overall satisfaction ratios, while achieving different fairness index levels.
Citation - WoS: 1
Citation - Scopus: 1
Warning Notes in a Learner’s Dictionary: a Study of the Effectiveness of Different Formats
(International Journal of Lexicography, 2022) Çakar, Tuna; Nesi, Hilary; Nural, Şükrü
This study used an online correction task to explore the extent to which different types of warning notes in Longman Dictionary of Contemporary English Online were heeded when users tried to correct errors in the use of L2 target words. The task was completed by 332 participants, yielding 1,819 answers produced after clicking on links to relevant entries. Warning notes were categorised in terms of their formatting features, but there were found to be inconsistencies in the way the dictionary associated different categories with different kinds of learner error. Participants judged warning notes with more visual enhancements to be more useful, but in the correction task the position of the warning notes also seemed to affect the degree to which the warnings were successfully applied. Different types of warning notes in learners’ dictionaries have not been examined previously in any depth, and the results suggest that some adjustments to formatting and placement might make them more effective.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Koleksiyonu by Scopus Q "Q1"