WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7150

Browse

Filters

2001 - 2009162010 - 2019302020 - 20224

Settings

Department: search.filters.department.İzmir Institute of Technology. Computer EngineeringPublisher: search.filters.publisher.Institute of Electrical and Electronics Engineers Inc.

Search Results

Now showing 1 - 10 of 50
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 2
    Predicting the Soft Error Vulnerability of Gpgpu Applications
    (Institute of Electrical and Electronics Engineers Inc., 2022) Topçu, Burak; Öz, Işıl
    As Graphics Processing Units (GPUs) have evolved to deliver performance increases for general-purpose computations as well as graphics and multimedia applications, soft error reliability becomes an important concern. The soft error vulnerability of the applications is evaluated via fault injection experiments. Since performing fault injection takes impractical times to cover the fault locations in complex GPU hardware structures, prediction-based techniques have been proposed to evaluate the soft error vulnerability of General-Purpose GPU (GPGPU) programs based on the hardware performance characteristics.In this work, we propose ML-based prediction models for the soft error vulnerability evaluation of GPGPU programs. We consider both program characteristics and hardware performance metrics collected from either the simulation or the profiling tools. While we utilize regression models for the prediction of the masked fault rates, we build classification models to specify the vulnerability level of the programs based on their silent data corruption (SDC) and crash rates. Our prediction models achieve maximum prediction accuracy rates of 96.6%, 82.6%, and 87% for masked fault rates, SDCs, and crashes, respectively.
  • Article
    Citation - WoS: 3
    Citation - Scopus: 4
    A Novel Efficient Method for Tracking Evolution of Communities in Dynamic Networks
    (Institute of Electrical and Electronics Engineers Inc., 2022) Karataş, Arzum; Şahin, Serap
    Tracking community evolution can provide insights into significant changes in community interaction patterns, promote the understanding of structural changes, and predict the evolutionary behavior of networks. Therefore, it is a fundamental component of decision-making mechanisms in many fields such as marketing, public health, criminology, etc. However, in this problem domain, it is an open challenge to capture all possible events with high accuracy, memory efficiency, and reasonable execution times under a single solution. To address this gap, we propose a novel method for tracking the evolution of communities (TREC). TREC efficiently detects similar communities through a combination of Locality Sensitive Hashing and Minhashing. We provide experimental evidence on four benchmark datasets and real dynamic datasets such as AS, DBLP, Yelp, and Digg and compare them with the baseline work. The results show that TREC achieves an accuracy of about 98%, has a minimal space requirement, and is very close to the best performing work in terms of time complexity. Moreover, it can track all event types in a single solution.
  • Article
    Citation - WoS: 7
    Citation - Scopus: 8
    Tracking Code Bug Fix Ripple Effects Based on Change Patterns Using Markov Chain Models
    (Institute of Electrical and Electronics Engineers Inc., 2022) Ufuktepe, Ekincan; Tuğlular, Tuğkan; Palaniappan, Kanappan
    Change impact analysis evaluates the changes that are made in the software and finds the ripple effects, in other words, finds the affected software components. Code changes and bug fixes can have a high impact on code quality by introducing new vulnerabilities or increasing their severity. A recent high-visibility example of this is the code changes in the log4j web software CVE-2021-45105 to fix known vulnerabilities by removing and adding method called change types. This bug fix process exposed further code security concerns. In this article, we analyze the most common set of bug fix change patterns to have a better understanding of the distribution of software changes and their impact on code quality. To achieve this, we implemented a tool that compares two versions of the code and extracts the changes that have been made. Then, we investigated how these changes are related to change impact analysis. In our case study, we identified the change types for bug-inducing and bug fix changes using the Quixbugs dataset. Furthermore, we used 13 of the projects and 621 bugs from Defects4J to identify the common change types in bug fixes. Then, to find the change types that cause an impact on the software, we performed an impact analysis on a subset of projects and bugs of Defects4J. The results have shown that, on average, 90% of the bug fix change types are adding a new method declaration and changing the method body. Then, we investigated if these changes cause an impact or a ripple effect in the software by performing a Markov chain-based change impact analysis. The results show that the bug fix changes had only impact rates within a range of 0.4-5%. Furthermore, we performed a statistical correlation analysis to find if any of the bug fixes have a significant correlation with the impact of change. The results have shown that there is a negative correlation between caused impact with the change types adding new method declaration and changing method body. On the other hand, we found that there is a positive correlation between caused impact and changing the field type.
  • Conference Object
    Doğal Dil Çıkarımı Modellerinde Bert Vektörlerinin Başarım Değerlendirmesi
    (Institute of Electrical and Electronics Engineers Inc., 2021) Oğul, İskender Ülgen; Tekir, Selma
    Doğal dil çıkarımı, düşünce ifade eden cümlelerin arasındaki ilişkiyi; karşıtlık, gerekseme veya tarafsızlık olarak sınıflandırmayı hedefler. Sınıflandırma görevini gerçekleştirmek için metinsel kaynaklar, vektör ya da gömme olarak adlandırılan matematiksel gösterimlere dönüştürülür. Bu çalışmada, hem statik (Glove, OntoNotes5) hem de bağlamsal (BERT) kelime gömme yöntemleri kullanılmıştır. Fikirsel cümleler arasındaki mantıksal ilişkilerin sınıflandırılması zordur zira cümleler karmaşık gramer yapılarına sahiptir ve cümlelerin işlenerek mantıksal gösterimlere dönüştürülmesi geleneksel doğal dil işleme çözümleri ile yetersiz kalmaktadır. Bu çalışma, sınıflandırma görevini gerçekleştirmek için ayrıştırılabilir ilgi ve doğal dil çıkarımı için gelişmiş LSTM (ESIM) derin öğrenme modellerini kullanmıştır. En iyi sonuç olan %88 doğruluk değeri SNLI veri kümesi üzerinde ESIM-BERT ile elde edilmiştir.
  • Conference Object
    Citation - WoS: 6
    Car Detection With Omnidirectional Cameras Using Haar-Like Features and Cascaded Boosting
    (Institute of Electrical and Electronics Engineers Inc., 2014) Karaimer, Hakkı Can; Baştanlar, Yalın
    This paper presents an approach to detects cars in omnidirectional images. We first go through the conventional method of using Haar-like features and cascaded boosting for conventional camera images. Then, to apply this method for omnidirectional cameras, we generate panoramic images from omnidirectional ones. In this way we perform car detection on a single image without generating numerous perspective images from the omnidirectional view. We also discuss two different ways of panoramic image generation and conclude that spherical profile panoramas are more convenient than cylindrical panoramas. We present our car detection experiments on real omnidirectional images.
  • Conference Object
    Citation - WoS: 1
    Citation - Scopus: 2
    Scene text localization using keypoints
    (Institute of Electrical and Electronics Engineers Inc., 2015) Erdoğmuş, Nesli; Özuysal, Mustafa
    Scene text localization and recognition (also known as text localization and recognition in real-world images, nature scene OCR or text-in-the-wild problem) is an open problem, attracting increasing interest from researchers. In this paper, we address the localization issue and leave the recognition part out of its scope. For the purpose of scene text localization, Scale-Invariant Feature Transform (SIFT) keypoints are extracted from the images and classified as text and non-text. Subsequently, the text keypoints are utilized to compute the bounding boxes around text regions. The proposed technique is tested on the database of ICDAR 2013 Robust Reading Competition-Challenge 2 and the experimental results are reported in detail. Although the idea introduced here is still at its infancy, it is observed to achieve remarkable results and due to the fact that there is a large room for improvement, it is found to be promising.
  • Conference Object
    A Detailed Analysis of Mser and Fast Repeatibility
    (Institute of Electrical and Electronics Engineers Inc., 2015) Uzyıldırım, Furkan Eren; Köksal, Ali; Özuysal, Mustafa
    This paper investigates the relationship between the MSER and FAST repeatability and changes in various camera parameters. By employing a realistic view synthesis methodology, it is possible to observe the effect of small parameter changes on the repeatability. Furthermore, for the analysis of MSER repeatability, a convex hull approach is proposed instead of fitting ellipses to the MSER region. This yields a better approximation to the MSER region without significantly increasing computation time.
  • Conference Object
    Citation - WoS: 2
    Stream Text Data Analysis on Twitter Using Apache Spark Streaming
    (Institute of Electrical and Electronics Engineers Inc., 2018) Hakdağlı, Özlem; Özcan, Caner; Oğul, İskender Ülgen
    With today's developing technology, people's access to information and its production have reached a very fast level. These generated and obtained information are instantly created, entered into data systems and updated. Sources of streaming data can be transformed into valuable analysis results when they are handled with targeted methods. In this study, a text data field is determined to perform analysis on instantaneous generated data and Twitter, the richest platform for instant text data, is used. Twitter instantly generates a variety of data in large quantities and it presents it as open source using an API. A machine learning framework Apache Spark's stream analysis environment is used to analyze these resources. Situation analysis was performed using Support Vector Machine, Decision Trees and Logistic Regression algorithms presented under this environment. The results are presented in tables.
  • Conference Object
    Citation - Scopus: 2
    Telsiz Duyarga Ağlarında Hızlı Hareket Eden Hedefler için Küme Tabanlı Hedef İzleme Algoritması
    (Institute of Electrical and Electronics Engineers Inc., 2009) Alaybeyoğlu, Ayşegül; Dağdeviren, Orhan; Kantarcı, Aylin; Erciyes, Kayhan
    Kablosuz iletişim teknolojilerindeki ilerlemelerle birlikte telsiz duyarga ağları (TDA) birçok sivil ve askeri uygulamalarda özellikle de hareketli hedefin takibi gibi konularda yaygın olarak kullanılmaya başlanmıştır. Bu çalışmada da TDA’da hızlı hareket eden nesneler için küme tabanlı bir hedef izleme algoritması önerilmiştir. Literatürde bulunan mevcut çalışmalarda lider düğüm, hedefin sadece t+1 anında yaklaşacağı konumu tahminleyerek bu konuma en yakın düğümü uyandırır. Hedefin çok hızlı hareket etmesi durumunda ise hedefin kısa süre içerisinde bir grup düğümün yakınlarından algılanmadan geçip gitmesi söz konusudur. Önermiş olduğumuz algoritma ile hedefin hızına bağlı olarak, hedefin tahmini gideceği yöndeki düğümler önceden uyandırılarak, kümeler önceden oluşturulmaktadır. Böylece hedefin ani hızlanması durumunda, önceden oluşturmuş olduğumuz kümeler sayesinde hedefin kaybolma riskini azaltmış bulunmaktayız.
  • Conference Object
    Citation - WoS: 5
    Citation - Scopus: 8
    Lensless Digital In-Line Holographic Microscopy for Space Biotechnology Applications
    (Institute of Electrical and Electronics Engineers Inc., 2019) Delikoyun, Kerem; Çine, Ersin; Anıl İnevi, Müge; Özuysal, Mustafa; Özçivici, Engin; Tekin, Hüseyin Cumhur
    Biomechanical changes at cellular level can dramatically affect living organisms in both aviation and space applications. Weightlessness induces morphological alteration of cells, which leads to tissue loss. Therefore, scientists have been studying the effect of weightlessness using cell culture based biological experiments using conventional microscopes. However, strict requirements regarding cost, weight and functionality limit the use of conventional microscopes in space environment. Lensless digital in-line holographic microscopy enables to use low-weight, low-cost and robust elements, such as a light emitting diode (LED), an aperture and an imaging sensor, instead of bulky, expensive and fragile optical elements, such as lenses, mirrors and filters. This technology offers a high field of view compared to conventional microscopes without affecting the resolution and it is also suitable for remote sensing applications with automated imaging capabilities. Here, we present a portable digital in-line holographic microscopy platform that allows to visualize cells and to analyze their viability in a microfluidic chip. The platform offers microscopic imaging with 1.55 mu m spatial resolution, 21.7 mm(2) field of view and image coloring capability. This platform could potentially play an important role in space biotechnology applications by enabling low-cost, high-resolution and portable monitoring of cells.