Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
164 results
Search Results
Conference Object Citation - WoS: 2Word2vec Kullanarak Eş Anlamlılık Temelinde Anahtar Kelime Çıkarımı(IEEE, 2019) Oğul, İskender Ülgen; Özcan, Caner; Hakdağlı, ÖzlemNowadays, the data revealed by the online individuals are increasing exponentially. The raw information that increasing data holds, transformed into meaningful outputs using machine learning and deep learning methods. Generally, supervised learning methods are used for information extraction and classification. Supervised learning is based on the training set that classification algorithms are trained. In the proposed approach, keyword extraction solution is proposed to classify text data more convenient. The developed solution is based on the Word2Vec algorithm, which works by taking into consideration the semantic meaning of the words unlike general approaches that based on word frequency. A new approach, word embedding algorithm named Word2Vec, works by calculating the word weights, semantic relationship, and the final weights of vectors. The obtained keywords are trained with Name Bayes and Decision Trees methods and the performance of the proposed method is shown by classification example.Conference Object Citation - WoS: 2Citation - Scopus: 3Impact of Variations in Synthetic Training Data on Fingerprint Classification(IEEE, 2019) İrtem, Pelin; İrtem, Emre; Erdoğmuş, NesliCreating 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.Conference Object Citation - WoS: 1On Defining Security Metrics for Information Systems(Brill Academic Publishers, 2005) Koltuksuz, Ahmet[No abstract available]Conference Object Citation - WoS: 37Graph Theoretic Clustering Algorithms in Mobile Ad Hoc Networks and Wireless Sensor Networks (survey)(Azerbaijan National Academy of Sciences, 2007) Erciyeş, Kayhan; Dağdeviren, Orhan; Çokuslu, Deniz; Özsoyeller, DenizClustering in mobile ad hoc networks (MANETs) and wireless sensor networks (WSNs) is an important method to ease topology management and routing in such networks. Once the clusters are formed, the leaders (coordinators) of the clusters may be used to form a backbone for efficient routing and communication purposes. A set of clusters may also provide the underlying physical structure for multicast communication for a higher level group communication module which may effectively be used for fault tolerance and key management for security purposes. We survey graph theoretic approaches for clustering in MANETs and WSNS and show that although there is a wide range of such algorithms, each may be suitable for a different cross-layer design objective.Conference Object Duyarga Ağları için Bir Γ Eşuyumcusu Tasarım ve Uygulaması(IEEE, 2008) Özsoyeller, Deniz; Erciyeş, Kayhan; Dağdeviren, OrhanImplementation 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, KayhanMobile 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: 1Automatic Enforcement of Location Aware User Based Network Access Control Policies(World Scientific and Engineering Academy and Society, 2008) Tuğlular, TuğkanMultiple interconnected network segments distributed across various locations, such as corporate networks, where users or employees constantly travel among segments and require to access servers, need to have network access control mechanisms that are able to adapt to these location changes. The idea of a firewall changing or adapting its rules depending on the location of users is presented by an architecture in this paper. This architecture proposes deployment of a policy server at the management level and policy agents at the firewall level, so that policy-driven network security management is enabled by specifying location aware user based network access control policies at the network security management and enforcing them at the managed firewalls. The architecture presented in this paper utilizes user VPN connection event triggers for dynamic policy configuration and automated policy deployment to firewalls. Location aware user based network access control policies, which are management level policies, are implemented using XACML. A network level policy is usually a configuration, or policy, file local to the firewall. The policy agent incorporated into the firewall performs the mapping from management level policy to firewall policy.Conference Object Citation - WoS: 3Citation - Scopus: 6Truth Ratios of Syllogistic Moods(Institute of Electrical and Electronics Engineers, 2015) Zarechnev, Mikhail; Kumova, Bora İsmailThe 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 Zamanda ortalaması alınmış ikili önplan imgeleri kullanarak taşıt sınıflandırması(IEEE, 2015) Karaimer, Hakkı Can; Baştanlar, YalınWe 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.Conference Object Citation - WoS: 10Citation - Scopus: 12Random Test Generation From Regular Expressions for Graphical User Interface (gui) Testing(Institute of Electrical and Electronics Engineers, 2019) Kılınççeker, Onur; Silistre, Alper; Challenger, Moharram; Belli, FevziGeneration of test sequences, that is, (user) inputs - expected (system) outputs, is an important task of testing of graphical user interfaces (GUI). This work proposes an approach to randomly generate test sequences that might he used for comparison with existing GUI testing techniques to evaluate their efficiency. The proposed approach first models CUI under test by a finite state machine (FSM) and then converts it to a regular expression (RE). A tool based on a special technique we developed analyzes the RE to fulfill missing context information such as the position of a symbol in the RE. The result is a context table representing the RE. The proposed approach traverses the context table to generate the test sequences. To do this, the approach repeatedly selects a symbol in the table, starting from the initial symbol, in a random manner until reaching a special, finalizing symbol for constructing a test sequence. Thus, the approach uses a symbol coverage criterion to assess the adequacy of the test generation. To evaluate the approach, mutation testing is used. The proposed technique is to a great extent implemented and is available as a tool called PQ-Ran Test (PQ-analysis based Random Test Generation). A case study demonstrates the proposed approach and analyzes its effectiveness by mutation testing.