9 results
Search Results
Now showing 1 - 9 of 9
Article Citation - WoS: 2Citation - Scopus: 3Implicit Learning With Certificate Warning Messages on Ssl Web Pages: What Are They Teaching?(Wiley-hindawi, 2016) Bostan, AtilaSSL-based web services are the most common technology in secure transactions on the Internet today. The security level of these services is inevitably related with that of digital certificates and user awareness. With the high number of nonconforming digital certificate usage, which eventually invokes warning messages on the Internet, users are implicitly forced to develop unsecure usage habits. In this study, we have studied the implicit learning effect of certificate warning messages on the SSL web pages. We have conducted two different experimental studies on university students and on instructors in IT departments. The results point to acquired indifference towards these warnings in users. Copyright (C) 2016 John Wiley & Sons, Ltd.Article Crack Detection on Asphalt Runway Using Unmanned Aerial Vehicle Data with Non-Crack Object Removal and Deep Learning Methods(Pontificia Univ Catolica Chile, Escuela Construccion Civil, 2025) Tapkin, Serkan; Tercan, Emre; Bostan, Atila; Sengul, GokhanUnmanned aerial vehicles are extensively utilized for image acquisition in a cheap, fast, and effective way. In this study, an automatic crack detection method with non-crack object removal and deep learning-based approaches are developed and tested on images captured by unmanned aerial vehicle. The motivation of this study is to detect either a crack exists or not in the asphalt-runway. The novelty of this study lies in integrating a non-crack artifact removal process with six classical edge detectors and comparing the resulting performance with four lightweight CNN models on the same UAV-acquired runway image dataset, enabling a unified evaluation of classical and learning-based approaches. For deep learning-based approach, four lightweight CNN models, namely GoogleNet, SqueezeNet, MobileNetv2, and ShuffleNet, are trained and the best accuracy of %87.9 is obtained whenever GoogleNet model is used. For the non-crack object removal approach, exclusion of non-crack objects from the images is the first step, where crack-detection which makes use of edge-detection techniques is the latter. In the study, Sobel, Prewitt, Canny, Laplacian of Gaussian, Roberts and Zero Cross edge detection algorithms are examined and their success rates in detecting cracks are comparatively presented. With sensitivity=0.981, specificity=0.744, accuracy=0.917, precision=0.912 and F-score=0.945 values Canny algorithm performs significantly better than others in detecting the cracks. This study provides enough evidence for the practicability of automated crack detection on unprocessed digital photographs by the results of the study conducted on asphalt runway.Conference Object Citation - WoS: 1An Undergraduate Curriculum for Deep Learning(Ieee, 2018) Tirkes, Guzin; Ekin, Cansu Cigdem; Sengul, Gokhan; Bostan, Atila; Karakaya, MuratDeep Learning (DL) is an interesting and rapidly developing field of research which has been currently utilized as a part of industry and in many disciplines to address a wide range of problems, from image classification, computer vision, video games, bioinformatics, and handwriting recognition to machine translation. The starting point of this study is the recognition of a big gap between the sector need of specialists in DL technology and the lack of sufficient education provided by the universities. Higher education institutions are the best environment to provide this expertise to the students. However, currently most universities do not provide specifically designed DL courses to their students. Thus, the main objective of this study is to design a novel curriculum including two courses to facilitate teaching and learning of DL topic. The proposed curriculum will enable students to solve real-world problems by applying DL approaches and gain necessary background to adapt their knowledge to more advanced, industry-specific fields.Conference Object Survey on the Usage of Digital Certificates in Ssl-Based Web Services(Turgut Ozal Univ, 2012) Yumsak, Ozkan; Bostan, Atila; Sekerci, Abdullah Sinan; Anameric, MunirSecurity of the communication on secure web services is provided with SSL (Secure Socket Layer) technology. SSL technology makes use of digital certificates and misuse of these digital certificates may cause security exploits. In this study, misuse ratio of certificates in university websites on the Internet is found out. To obtain this information, certificates which are used in the SSL web services are scanned. The conclusion of this study points out valid and invalid ratios of digital certificate usage in Internet based SSL web services.Article Citation - WoS: 4Citation - Scopus: 3Role of E-government in Reducing Disasters(Uikten - Assoc information Communication Technology Education & Science, 2019) Ibrahim, Thaer; Mishra, Alok; Bostan, AtilaDisasters affect three-quarters of the world, they cause huge losses of life and property every year. Information and communication technology (ICT) - as the backbone of e-government is one of the factors that reduce the damage caused by these disasters. This paper discusses the impact of demographic factors on citizens' readiness towards ICTs and disaster management, by conducting a questionnaire form that tests the readiness of the Iraqi citizen and the extent of their interest in this technology being threatened by disaster.Conference Object Citation - WoS: 1Analyzing the Requirements for E-Government Transition of Iraqi Ics Services(Ieee, 2017) Alameri, Mohammed Abdulbasit; Bostan, Atila; Akman, IbrahimIraqi Correction Services (ICS) is a department within the Ministry of Justice. Most services are provided through traditional paper and pen system. This system causes delays in service provision lime and work over-load on ICS staff which translates into a high cost of service provision. E-government applications represent an opportunity to automate governmental services while improving both effectiveness and efficiency. This work presents the approach taken to determine the priority to automate ICS service from the perspective of service beneficiaries. The research is yet to be completed, however, up to this point we developed four different questionnaire-sets in order to collect the requirements from the shareholders, verified them and implemented the actual survey in the field. The experience gained throughout these steps and the future analysis plan is reported in this paper.Article Citation - WoS: 6Citation - Scopus: 7Impact of Education on Security Practices in Ict(Univ Osijek, Tech Fac, 2015) Bostan, Atila; Akman, IbrahimIn assuring the security in information technology, user awareness and acquired-user habits are inevitable components, yet they may be qualified as the feeblest ones. As the information technology tries to put its best in providing maximum security, user awareness plays a key-role. Additionally, although the literature provides studies on approaches for teaching information security, there are not many evidences on the impact of education level. Therefore, this study investigates the impact of the education level on user security awareness in using the Information and Communication Technology (ICT) products. For this purpose, a survey was conducted among 433 citizens from different layers of the society. Interestingly, the results indicated that education level has significant impact on all security issues included in the analysis regarding computer usage, web usage and e-mail usage.Conference Object Citation - WoS: 1Ict User and Usage Characteristics and E-Mail Security Awareness(Ieee, 2013) Bostan, Atila; Akman, IbrahimIn spite of the fact that e-mail is the oldest service on the Internet, it is still one of the network services which are in widespread usage. The extensive usage of e-mail services has turned it into a target for digital intruders. The information and communication technology tries its best in providing maximum security in e-mail services. However, the research regarding relationships between user demographic factors, reason of ICT usage and e-mail security is not matured yet and needs further exploration. Therefore, this study investigates demographic factors, information and communication technology usage characteristics of users on providing secure e-mail usage. For this purpose, a survey was conducted among 466 citizens from different layers of the society. The results indicated existence of significant relations between factors related to socio-demographics, reason and frequency of ICT usage and e-mail security.Conference Object Deep Learning and Current Trends in Machine Learning(Ieee, 2018) Bostan, Atila; Sengul, Gokhan; Tirkes, Guzin; Ekin, Cansu; Karakaya, MuratAcademic interest and commercial attention can be used to identify how much potential a novel technology may have. Since the prospective advantages in it may help solving some problems that are not solved yet or improving the performance of readily available ones. In this study, we have investigated the Web of Science (WOS) indexing service database for the publications on Deep Learning (DL), Machine Learning (ML), Convolutional Neural Networks (CNN), and Image Processing to reveal out the current trend. The figures indicate the strong potential in DL approach especially in image processing domain.
