Bilgisayar Mühendisliği Bölümü Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/58

Browse

Now showing 1 - 5 of 5

Citation - WoS: 0
A model for adopting cloud computing in government sector: Case study in Iraq
(Nadia, 2020) Hassanpour, Reza; Hassanpour, Reza; Yazılım Mühendisliği
Cloud computing is an on-demand delivery system of computing resources, such as servers, databases, storage, networking, software, and analytics, over the Internet on a pay-for-use basis. This technology is not currently widely utilized in government institutions, especially in the case of Iraq, for different factors. The main objective of this research is to identify the most critical factors that prevent the adoption of cloud computing, through developing a conceptual model that integrates the Technology Organization, and Environment (TOE) framework, Iacovou et al.' s model, and the Diffusion of Innovation (DOI) theory. The key factors influencing the adoption of cloud technology have been determined through literature review. The results show that the most significant concerns that can have a negative impact in the decision of adoption are as follows: feasibility, trust, regulatory concerns, IT readiness, privacy, compatibility, government support, availability and reliability, industry type, security, cost, complexity, organization size, organization culture, as well as direct benefits and indirect benefits have a positive impact in the decision of cloud adoption. Moreover, the researchers used the CloudAnalyst simulator to identify the real time performance of the cloud technology environment, and applied two algorithms via this tool, namely the Analytical Hierarchy Process (AHP) technique, which used to obtain the weight of variables depending on the questionnaire results, and the Elliptic Curve Digital Signature Algorithm (ECDSA), which used to identify the privacy and security of cloud technology. Finally, the researchers have proposed guidelines to help government institutions to move to the cloud environment in an effective manner.
Citation - Scopus: 5
Active defense strategy against jamming attack in wireless sensor networks
(Modern Education and Computer Science Press, 2019) Al-Shai, N.F.A.; Hassanpour, R.
Wireless Sensor Networks WSNs are being utilized increasingly nowadays due to their ability to collect data from stationary, moving, reachable or unreachable fields. Progressive developments in WSN techniques add efficiency, reliability and better power management possibility, but they are still vulnerable and sensitive to security threats. The most effective threat to WSN is DOS attacks, which are detectable but in many cases unpreventable yet. An authentication-based defensive approach against DOS attack combined with jamming attack that prevents transferring data between attacked nodes in a cluster and cluster head node is proposed in this study. The proposed method encompasses developing an algorithm with ability to bypass attacked path via alternative safe one under control of cluster head to mitigate the False Node Excluding DOS due to jamming attack. The proposed method has been experimentally tested against similar methods from the literature with arbitrary study cases. Our proposed algorithm shows promising results in mitigating False Node Exclusion DOS (FNEDOS) attack where a full recovery of the attacked node is achieved in case of isolated nodes, and improvement between 36% and 52% is obtained when the attack affects a group of nodes at proxim © 2019 MECS.
Citation - Scopus: 4
Deep learning methods with pre-trained word embeddings and pre-trained transformers for extreme multi label text classification
(Institute of Electrical and Electronics Engineers Inc., 2021) Erciyes, N.E.; Görür, A.K.
In recent years, there has been a considerable increase in textual documents online. This increase requires the creation of highly improved machine learning methods to classify text in many different domains. The effectiveness of these machine learning methods depends on the model capacity to understand the complex nature of the unstructured data and the relations of features that exist. Many different machine learning methods were proposed for a long time to solve text classification problems, such as SVM, kNN, and Rocchio classification. These shallow learning methods have achieved doubtless success in many different domains. For big and unstructured data like text, deep learning methods which can learn representations and features from the input data wtihout using any feature extraction methods have shown to be one of the major solutions. In this study, we explore the accuracy of recent recommended deep learning methods for multi-label text classification starting with simple RNN, CNN models to pretrained transformer models. We evaluated these methods' performances by computing multi-label evaluation metrics and compared the results with the previous studies. © 2021 IEEE
Citation - Scopus: 0
Expert systems in access telecommunication networks
(2009) Şahin, S.; Tolun, M.R.; Baykal, Y.
Access telecommunication systems are categorized as digital subscriber line (xDSL), fiber-to-the-home (FTTH), hybrid fiber-coaxial (HFC), power line systems, local multipoint distribution system (LMDS), free space optics (FSO), satellite and worldwide interoperability for microwave access (WIMAX) systems. Basic specifications, such as the rate of information for upstream and downstream, access link length, frequency licence requirement for these access telecommunication networks are defined. Expert system analysis is applied to find out the possible systems that can be employed among the abovementioned choices of access telecommunication within the user defined inputs describing the requirements of the end user. The rule-based structure of the expert system is formed by using the Exsys expert system development tool. © 2008 IEEE.
Citation - Scopus: 5
Investigating end user errors in oil and gas critical control systems
(Association for Computing Machinery, 2020) Alrawi, L.N.; Pusatli, T.; 51704
System availability and efficiency are critical in the petroleum sector as any fault affecting those systems may negatively impact operations resources, such as money, human resources and time. Therefore, it has become important to investigate the reasons for such errors. In this study, human error has been targeted since a number of these errors is projected to increase in the sector. The factors that affect end user behavior are investigated in addition to an evaluation of the relation between system availability and human behavior. An investigation has been performed following the descriptive methodology in order to gain insights into human error factors. Questionnaires related to software/hardware errors and errors due to the end user were collected from 81 site workers. The findings indicate a potential relation between end user behavior and system availability. Training, experience, education, work shifts, system interface, usage of memory sticks and I/O devices were identified as factors affecting end user behavior, hence system availability and efficiency. © 2020 ACM.

Browse

Browsing Bilgisayar Mühendisliği Bölümü Tezleri by Department "Çankaya University"