Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
246 results
Search Results
Conference Object A News Chain Evaluation Methodology Along With a Lattice-Based Approach for News Chain Construction(Association for Computational Linguistics (ACL), 2017) Toprak, Mustafa; Toprak, Mustafa; Özkahraman,Ö.; Tekir, Selma; Tekir, Selma; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyChain construction is an important requirement for understanding news and establishing the context. A news chain can be defined as a coherent set of articles that explains an event or a story. There's a lack of well-established methods in this area. In this work, we propose a methodology to evaluate the "goodness" of a given news chain and implement a concept latticebased news chain construction method by Hossain et al. The methodology part is vital as it directly affects the growth of research in this area. Our proposed methodology consists of collected news chains from different studies and two "goodness" metrics, minedge and dispersion coefficient respectively. We assess the utility of the lattice-based news chain construction method by our proposed methodology. © EMNLP 2017.All right reserved.Conference Object Citation - WoS: 2Citation - Scopus: 3Impact of Variations in Synthetic Training Data on Fingerprint Classification(IEEE, 2019) İrtem, Pelin; Erdoğmuş, Nesli; İrtem, Emre; Erdoğmuş, Nesli; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyCreating and labeling data can be extremely time consuming and labor intensive. For this reason, lack of sufficiently large datasets for training deep structures is often noted as a major obstacle and instead, synthetic data generation is proposed. With their high acquisition and labeling complexity, this also applies to fingerprints. In the literature, a number of synthetic fingerprint generation systems have been proposed, but mostly for algorithm evaluation purposes. In this paper, we aim to analyze the use of synthetic fingerprint data with different levels of degradation for training deep neural networks. Fingerprint classification problem is selected as a case-study and the experiments are conducted on a public domain database, NIST SD4. A positive correlation between the synthetic data variation and the classification rate is observed while achieving state-of-the-art results.Article Citation - WoS: 4Citation - Scopus: 5Dma: Matrix Based Dynamic Itemset Mining Algorithm(IGI Global Publishing, 2013) Oğuz, Damla; Oğuz, Damla; Yıldız, Baroş; Ergenç Bostanoğlu, Belgin; Ergenç, Belgin; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyUpdates on an operational database bring forth the challenge of keeping the frequent itemsets up-to-date without re-running the itemset mining algorithms. Studies on dynamic itemset mining, which is the solution to such an update problem, have to address some challenges as handling i) updates without re-running the base algorithm, ii) changes in the support threshold, iii) new items and iv) additions/deletions in updates. The study in this paper is the extension of the Incremental Matrix Apriori Algorithm which proposes solutions to the first three challenges besides inheriting the advantages of the base algorithm which works without candidate generation. In the authors' current work, the authors have improved a former algorithm as to handle updates that are composed of additions and deletions. The authors have also carried out a detailed performance evaluation study on a real and two benchmark datasets.Editorial Message From Tain Symposium Organizing Committee(Institute of Electrical and Electronics Engineers Inc., 2015) Tuğlular, Tuğkan; Tuğlular, Tuğkan; Cai, Y.; Dustdar, S.; Yamazaki, K.; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyIt is a pleasure to welcome you to COMPSAC 2015 Symposium on Technologies and Applications of the Internet (TAIN). This year, first time in its history, COMPSAC is organized as a series of symposiums under the main theme of “Mobile and Cloud Systems – Challenges and Applications”. TAIN Symposium providing a forum to share latest innovations on Internet technologies and applications perfectly matches with the main theme. Topics of interest for TAIN include all types of networks with their architectures and applications as well as their management, performance, and security. Moreover, TAIN Symposium addresses Internet of things (IoT), machine-to-machine (M2M) and peer-to-peer (P2P) communications, content distribution networks (CDN) and also emerging network technologies such as software defined networks (SDN). A vast array of challenges for Internet technologies and applications and proposals for solutions will be discussed in TAIN Symposium.Conference Object Duyarga Ağları için Bir Γ Eşuyumcusu Tasarım ve Uygulaması(IEEE, 2008) Özsoyeller, Deniz; Erciyeş, Kayhan; Erciyeş, Kayhan; Dağdeviren, Orhan; Dağdeviren, Orhan; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyImplementation of synchronous algorithms in distributed systems in general is less troublesome than the implementation of asynchronous algorithms. Synchronizers provide synchronous execution of an asynchronous algorithm in distributed systems. In this study, we propose a gamma synchronizer for Wireless Sensor Networks (WSNs). This synchronizer consists of a and beta synchronizers. In our work, the WSN is first divided into clusters and then these clusters are connected using a ring protocol. Synchronization is provided using the beta synchronizer in the cluster and a synchronizer among the clusters. We describe the clustering algorithm and the ring formation algorithm for the WSNs and give the results obtained so far.Conference Object Citation - Scopus: 15Gezgin Tasarsız Ağlar için Taşırma Tabanlı Yönlendirme Yordamı(IEEE, 2008) Çokuslu, Deniz; Erciyeş, Kayhan; Erciyeş, Kayhan; Çokuslu, Deniz; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyMobile Ad Hoc Networks (MANETs) are videly in use in rescue, military operations, scientific and business areas. Many studies are addressed in MANETs because of their need to long lasting liveness, fault tolerance, dynamic addressing, collusion prevention, mobility management and security. Especially, self clustering, backbone construction and routing are the most interesting academic and industrial research areas in MANETs. A wide range of studies addressed the routing problem in MANETs. Many previous studies address the clustering and routing problems as seperate subjects. However, rowing approaches which are specific to the clustering methodologies may have many advantages in terms of efficiency and availability. In this study, a flooding based routing algorithm is proposed. First, a detailed description of the algorithm is explained, then the analysis and test results using the ns2 simulator are given which show that the designed algorithm is scalable and has favorable performance.Conference Object Citation - WoS: 1Citation - Scopus: 2Scene text localization using keypoints(Institute of Electrical and Electronics Engineers Inc., 2015) Erdoğmuş, Nesli; Özuysal, Mustafa; Özuysal, Mustafa; Erdoğmuş, Nesli; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyScene 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 Citation - WoS: 3Citation - Scopus: 6Truth Ratios of Syllogistic Moods(Institute of Electrical and Electronics Engineers, 2015) Zarechnev, Mikhail; Kumova, Bora İsmail; Kumova, Bora İsmail; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyThe syllogistic system consists of 256 moods, of which only 24 have been recognized as true. From a set-theoretical point of view, a mood can be represented with three sets and their possible relationships. Three sets can have up to seven sub-sets or spaces. In an earlier work we have used 41 permutations of the spaces, out of which every mood matches an individual number as true or false cases. The truth ratio of a mood is then calculated, by relating the true and false cases with each other. In this work we revise the previously presented properties of the moods and the syllogistic system, this time by using the maximum possible cover, which consists of 96 distinct space permutations. Our results mostly verify our previous findings, like the additional true mood anasoy, the inherently symmetric truth distribution of the moods. Additionally we have revealed some new properties, like the equivalence of some moods, which reduces the system to 136 distinct moods.Conference Object A Detailed Analysis of Mser and Fast Repeatibility(Institute of Electrical and Electronics Engineers Inc., 2015) Uzyıldırım, Furkan Eren; Köksal, Ali; Köksal, Ali; Özuysal, Mustafa; Özuysal, Mustafa; Uzyıldırım, Furkan Eren; 01. Izmir Institute of Technology; 03.04. Department of Computer Engineering; 01.01. Units Affiliated to the Rectorate; 03. Faculty of EngineeringThis 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 Zamanda ortalaması alınmış ikili önplan imgeleri kullanarak taşıt sınıflandırması(IEEE, 2015) Karaimer, Hakkı Can; Baştanlar, Yalın; Baştanlar, Yalın; 03.04. Department of Computer Engineering; 03. Faculty of Engineering; 01. Izmir Institute of TechnologyWe describe a shape-based method for classification of vehicles from omnidirectional videos. Different from similar approaches, the binary images of vehicles obtained by background subtraction in a sequence of frames are averaged over time. We show with experiments that using the average shape of the object results in a more accurate classification than using a single frame. The vehicle types we classify are motorcycle, car and van. We created an omnidirectional video dataset and repeated experiments with shuffled train-test sets to ensure randomization.