Computer Engineering / Bilgisayar Mühendisliği
Permanent URI for this collectionhttps://hdl.handle.net/11147/10
Browse
45 results
Search Results
Conference Object Citation - Scopus: 1Distributed Identity Based Private Key Generation for Scada Systems(Springer, 2013) Kılınç, Görkem; Nai Fovino, IgorThe security of the ICT (Information Communications Technology) components of industrial systems is gaining great importance in the context of their criticality for society at large. There is an urgent need for the consideration of security in their design, and for the analysis of the related vulnerabilities and potential threats. The high exposure of industrial critical infrastructure to such threats is mainly due to the intrinsic weakness of the communication protocols used to control the process network. The peculiarities of the industrial protocols (low computational power, large geographical distribution, near to real-time constraints) make hard the effective use of traditional cryptographic schemes and in particular the implementation of a effective key management infrastructure supporting a cryptographic layer. In this paper we present the first working prototype of a distributed key generation infrastructure for SCADA systems based on the well known identity based crypto-paradigm. © 2013 Springer-Verlag.Conference Object On-board applications development via symbolic user interfaces(Springer, 2014) Kumova, Bora İsmailbecerik is a functional language consisting of symbolic commands for managing and composing applications. Application commands consist of symbols that are associated with reading sensor values, computing those values and executing actuator values. It is the result of a co-design of mechatronic functionality and robotic behaviour. The requirements given for mechatronic functionality were those of simple robotics kits that are used in school education or as toys. The requirements given for the behaviour were to provide a reflexive one, consisting of triggering simple computations and actuations from simple sensor values. becerik currently lives as a leJOS application on NXT robots and enables developing simple applications using the standard display and buttons of the NXT brick. In this paper we introduce the symbolic user interfaces of becerik. © 2014 Springer International Publishing Switzerland.Article Citation - WoS: 9Citation - Scopus: 14Rule-Based Automatic Question Generation Using Semantic Role Labeling(Institute of Electronics, Information and Communication Engineers, 2019) Keklik, Onur; Tuğlular, Tuğkan; Tekir, SelmaThis paper proposes a new rule-based approach to automatic question generation. The proposed approach focuses on analysis of both syntactic and semantic structure of a sentence. Although the primary objective of the designed system is question generation from sentences, automatic evaluation results shows that, it also achieves great performance on reading comprehension datasets, which focus on question generation from paragraphs. Especially, with respect to METEOR metric, the designed system significantly outperforms all other systems in automatic evaluation. As for human evaluation, the designed system exhibits similar performance by generating the most natural (human-like) questions.Article Citation - Scopus: 1Curve Description by Histograms of Tangent Directions(Institution of Engineering and Technology, 2019) Köksal, Ali; Özuysal, MustafaThe authors propose a novel approach for the description of objects based on contours in their images using real-valued feature vectors. The approach is particularly suitable when objects of interest have high contrast and texture-free images or when the texture variations are high so textural cues are nuisance factors for classification. The proposed descriptor is suitable for nearest neighbour classification still popular in embedded vision applications when the power considerations outweigh the performance requirements. They describe object outlines purely based on the histograms of contour tangent directions mimicking many of the design heuristics of texture-based descriptors such as scale-invariant feature transform (SIFT). However, unlike SIFT and its variants, the proposed approach is directly designed to work with contour data and it is robust to variations inside and outside the object outline as well as the sampling of the contour itself. They show that relying on tangent direction estimation as opposed to gradient computation yields a more robust description and higher nearest neighbour classification rates in a variety of classification problems.Conference Object Citation - Scopus: 1Fuzzy-Syllogistic Systems: a Generic Model for Approximate Reasoning(Springer, 2016) Kumova, Bora İsmailThe well known Aristotelian syllogistic system S consists of 256 moods. We have found earlier that 136 moods are distinct in terms of equal truth ratios that range in tau = [ 0,1]. The truth ratio of a particular mood is calculated by relating the number of true and false syllogistic cases that the mood matches. The introduction of (n -1) fuzzy existential quantifiers, extends the system to fuzzy-syllogistic systems S-n, 1 < n, of which every fuzzy-syllogistic mood can be interpreted as a vague inference with a generic truth ratio, which is determined by its syllogistic structure. Here we introduce two new concepts, the relative truth ratio (r)tau = [ 0,1] that is calculated from the cardinalities of the syllogistic cases of the mood and fuzzy-syllogistic ontology (FSO). We experimentally apply the fuzzy-syllogistic systems S-2 and S-6 as underlying logic of a FSO reasoner (FSR) and discuss sample cases for approximate reasoning.yArticle Citation - WoS: 1Citation - Scopus: 2Dynamic Itemset Hiding Algorithm for Multiple Sensitive Support Thresholds(IGI Global, 2018) Öztürk, Ahmet Cumhur; Ergenç, BelginThis article describes how association rule mining is used for extracting relations between items in transactional databases and is beneficial for decision-making. However, association rule mining can pose a threat to the privacy of the knowledge when the data is shared without hiding the confidential association rules of the data owner. One of the ways hiding an association rule from the database is to conceal the itemsets (co-occurring items) from which the sensitive association rules are generated. These sensitive itemsets are sanitized by the itemset hiding processes. Most of the existing solutions consider single support thresholds and assume that the databases are static, which is not true in real life. In this article, the authors propose a novel itemset hiding algorithm designed for the dynamic database environment and consider multiple itemset support thresholds. Performance comparisons of the algorithm is done with two dynamic algorithms on six different databases. Findings show that their dynamic algorithm is more efficient in terms of execution time and information loss and guarantees to hide all sensitive itemsets.Article Citation - WoS: 3Citation - Scopus: 3Regression-Based Prediction for Task-Based Program Performance(World Scientific Publishing, 2019) Öz, Işıl; Bhatti, Muhammad Khurram; Popov, Konstantin; Brorsson, MatsAs multicore systems evolve by increasing the number of parallel execution units, parallel programming models have been released to exploit parallelism in the applications. Task-based programming model uses task abstractions to specify parallel tasks and schedules tasks onto processors at runtime. In order to increase the efficiency and get the highest performance, it is required to identify which runtime configuration is needed and how processor cores must be shared among tasks. Exploring design space for all possible scheduling and runtime options, especially for large input data, becomes infeasible and requires statistical modeling. Regression-based modeling determines the effects of multiple factors on a response variable, and makes predictions based on statistical analysis. In this work, we propose a regression-based modeling approach to predict the task-based program performance for different scheduling parameters with variable data size. We execute a set of task-based programs by varying the runtime parameters, and conduct a systematic measurement for influencing factors on execution time. Our approach uses executions with different configurations for a set of input data, and derives different regression models to predict execution time for larger input data. Our results show that regression models provide accurate predictions for validation inputs with mean error rate as low as 6.3%, and 14% on average among four task-based programs.Conference Object Citation - Scopus: 1A Digital Interaction Framework for Managing Knowledge Intensive Business Processes(Springer, 2019) Bandara, Madhushi; Rabhi, Fethi A.; Meymandpour, Rouzbeh; Demirörs, OnurMany business processes present in modern enterprises are loosely defined, highly interactive, involve frequent human interventions and coupled with a multitude of abstract entities defined within an enterprise architecture. Further, they demand agility and responsiveness to address the frequently changing business requirements. Traditional business process modelling and knowledge management technologies are not adequate to represent and support those processes. In this paper, we propose a framework for modelling such processes in a service-oriented fashion, extending an ontology-based enterprise architecture modelling platform. Finally, we discuss how our solution can be used as a stepping stone to cater for the management and execution of knowledge-intensive business processes in a broader context. © 2019, Springer Nature Switzerland AG.Conference Object Citation - Scopus: 7From Requirements to Data Analytics Process: An Ontology-Based Approach(Springer International Publishing AG, 2019) Bandara, Madhushi; Behnaz, Ali; Rabhi, Fethi A.; Demirors, OnurComprehensively describing data analytics requirements is becoming an integral part of developing enterprise information systems. It is a challenging task for analysts to completely elicit all requirements shared by the organization's decision makers. With a multitude of data available from e-commerce sites, social media and data warehouses selecting the correct set of data and suitable techniques for an analysis itself is difficult and time-consuming. The reason is that analysts have to comprehend multiple dimensions such as existing analytics techniques, background knowledge in the domain of interest and the quality of available data. In this paper, we propose to use semantic models to represent different spheres of knowledge related to data analytics space and use them to assist in analytics requirements definition. By following this approach users can create a sound analytics requirements specification, linked with concepts from the operation domain, available data, analytics techniques and their implementations. Such requirements specifications can be used to drive the creation and management of analytics solutions, well aligned with organizational objectives. We demonstrate the capabilities of the proposed method by applying on a data analytics project for house price prediction.Article Citation - WoS: 9Citation - Scopus: 13Training Cnns With Image Patches for Object Localisation(Institution of Engineering and Technology, 2018) Orhan, Semih; Baştanlar, YalınRecently, convolutional neural networks (CNNs) have shown great performance in different problems of computer vision including object detection and localisation. A novel training approach is proposed for CNNs to localise some animal species whose bodies have distinctive patterns such as leopards and zebras. To learn characteristic patterns, small patches which are taken from different body parts of animals are used to train models. To find object location, in a test image, all locations are visited in a sliding window fashion. Crops are fed into trained CNN and their classification scores are combined into a heat map. Later on, heat maps are converted to bounding box estimates for varying confidence scores. The localisation performance of the patch-based training approach is compared with Faster R-CNN – a state-of-the-art CNN-based object detection and localisation method. Experimental results reveal that the patch-based training outperforms Faster R-CNN, especially for classes with distinctive patterns.