King Khalid University Hospital

King Saud University Repository
Not a member yet
    13949 research outputs found

    BLIND COPY MOVE IMAGE FORGERY DETECTION USING DYADIC UNDECIMATED WAVELET TRANSFORM

    No full text
    In this paper, we propose a blind copy move image forgery detection method using dyadic wavelet transform (DyWT). DyWT is shift invariant and therefore more suitable than discrete wavelet transform (DWT) for data analysis. First we decompose the input image into approximation (LL1) and detail (HH1) subbands. Then we divide LL1 and HH1 subbands into overlapping blocks and measure the similarity between blocks. The key idea is that the similarity between the copied and moved blocks from the LL1 subband should be high, while the one from the HH1 subband should be low due to noise inconsistency in the moved block. We sort pairs of blocks based on high similarity using the LL1 subband and high dissimilarity using the HH1 subband. Using thresholding, we obtain matched pairs from the sorted list as copied and moved blocks. Experimental results show the effectiveness of the proposed method over competitive methods using DWT and the LL1 or HH1 subbands only

    Centralized Buffering and Wavelength Conversion in Multistage Interconnection Networks

    No full text
    In this paper, methods to alleviate the problem of internal blocking in interconnection networks based on WDM are studied. In an ordinary 8x8 Omega network, only 10% of all permutations are permissible in one pass, and it gets worse with larger switches. However, using WDM technology, the performance of these networks can be improved. In this paper, several architectures based on Omega network using the WDM technology are considered and in turn algorithms to resolve the problem of internal blocking in a centralized fashion are introduced. Performance of the Omega network is analyzed by simulation. It is shown that by using a few buffers and lookahead wavelength converters a considerable amount of improvement in the system performance is achieve

    BorderSense: Border Patrol through Advanced Wireless Sensor Networks

    No full text
    The conventional border patrol systems suffer from intensive human involvement. Recently, unmanned border patrol systems employ high-tech devices, such as unmanned aerial vehicles, unattended ground sensors, and surveillance towers equipped with camera sensors. However, any single technique encounters inextricable problems, such as high false alarm rate and line-of-sight-constraints. There lacks a coherent system that coordinates various technologies to improve the system accuracy. In this paper, the concept of BorderSense, a hybrid wireless sensor network architecture for border patrol systems, is introduced. BorderSense utilizes the most advanced sensor network technologies, including the wireless multimedia sensor networks and the wireless underground sensor networks. The framework to deploy and operate BorderSense is developed. Based on the framework, research challenges and open research issues are discussed

    Indexing Size Approximation of WWW Repository with Leading Information Retrieval and Web Filtering Robots

    No full text
    The biggest information system of World Wide Web indexing is critical to estimate. Web is the beneficial and growing scientific utility like digital library to explore electronic literature to its lovers. Indexing estimation of WWW information is an open problem since 1998. Yahoo has claimed 19 billion web documents as its indexed size on which Google is not satisfied because in accordance with last published study by Gulli and Signorini the total indexed web size was around 11.5 billion pages. Web is growing hastily; what is the current size of web? Which search engine possesses large indexing of authentic information (PDF files)? Which search engine provides large indexing of all types of Web pages? This review article provides the answers of all above questions. We estimated the index size of leading search engines (Google, Yahoo and MSN) under easy and cost effective approach because if easy way persists then why we select tough heuristics. Our technique relies on querying over the search engines with selected common affixes that can be a part of each and every document or web page. This review paper concludes the total size of present indexed web contents and provides comparative analysis to support scholars which search engine has more authentic information and large indexing size

    Effective Training for ES Implementation: A Comparative Study

    No full text
    Local and global collaboration in term of people and resources are working together in a professional way to have more benefits for an organization in the success of ES projects. ES projects involve many factors in order for an organization to benefit from the system. ES training is one of the important factors in the ES projects. Beside a comprehensive, early, and continuous training plan that attached to the ES implementation plan, there should be a criterion to measure the quality of such training. As far as the organizations are concern they should be aware of the training methods. In this paper we have discussed the important issues related to an efficient ES training and highlight some training evaluation models that are necessary for organizations to have a successful training

    An Ontology Based Information Security Requirements Engineering Framework

    No full text
    Software Requirement Specification (SRS) is frequently evolving to reflect requirements change during project development. Therefore, it needs enhancement to facilitate its authoring and reuse. This paper proposes a framework for building a part of SRS related to information security requirements (ISR) using ontologies. Such a framework allows ensuring ISRs traceability and reuse. The framework uses three kinds of generic ontologies as a solution to this problem – software requirement ontology, application domain ontology, information security ontology. We propose to enhance SRS by associating the ISR with specific entities within ontologies. We aim to facilitate a semantic-based interpretation of ISR by restricting their interpretation through the three previous ontologies. Semantic form is used to improve our ability to create, manage, and maintain information security requirements. We anticipate that the proposed framework would be very helpful for requirements engineers to create and understand the ISRs

    Association Mining of Dependency between Time Series using Genetic Algorithm and Discretization

    No full text
    Association rule mining is one of the most popular data-mining techniques used to find associations existing between a set of objects or data. A time series is a sequence of observations stamped over the time; Time-series analysis has been used in a variety of applications like: business and health. The application of association mining to time series is very promised. The purpose of this article is to propose a new fast algorithm to discover the association that can exist between two time series. We use discretisation to segment time series to a number of shapes, and we classify these shapes to pre-defined shape classes to generate association rules using Genetic Algorithm (GA)

    An Effective Feature Selection Method for On-line Signature based Authentication

    No full text
    In this paper, we tackle the problem of identifying the relevant set of features that helps achieving accurate on-line signature based authentication. There exists a large set of features that can be acquired from the original signal or derived from it. Taking into account the whole set of features in the authentication process is time consuming. Furthermore, not all features are relevant and some of them are redundant. Consequently, finding the minimal set of relevant features is a prerequisite to perform fast authentication while achieving better accuracy. This feature selection task is combinatorial in nature. In our work, we handle it using a Discrete Quantum behaved Particle Swarm Optimization strategy (DQPSO). The space of possible feature sets is explored according to a QPSO dynamic where each set is encoded in terms of a binary representation. Data sets from SVC 2004 data base have been used in our experiments. Very encouraging results have been obtained

    Ensemble Classifiers for Dynamic Signature Authentication

    No full text
    Rapid advances in technology, that made almost everything goes digital have entailed a persistent need for a stronger means of information security. Furthermore, new advanced devices are now available to capture the dynamic of a person’s signature. Therefore, the reliance on the dynamic signature for authenticating entities in secure system became crucial. In this paper, we investigate the problem of dynamic signature verification and recognition using Ensemble of Classifiers, where we used multiple Fisher based probabilistic neural networks as the component classifiers to construct the Ensemble. Two key issues are studied; the first issue is how to construct the Ensemble. The second issue is how to combine the predictions of the component classifiers in order to accomplish the decision-making process. Data sets from SVC dataset have been used to assess the performance of the proposed ensemble of classifiers. Obtained results are very encouraging and show the ability of ensemble classifiers to deal with the tackled proble

    An Effective Feature Selection Method for On-line Signature based Authentication

    No full text
    In this paper, we tackle the problem of identifying the relevant set of features that helps achieving accurate on-line signature based authentication. There exists a large set of features that can be acquired from the original signal or derived from it. Taking into account the whole set of features in the authentication process is time consuming. Furthermore, not all features are relevant and some of them are redundant. Consequently, finding the minimal set of relevant features is a prerequisite to perform fast authentication while achieving better accuracy. This feature selection task is combinatorial in nature. In our work, we handle it using a Discrete Quantum behaved Particle Swarm Optimization strategy (DQPSO). The space of possible feature sets is explored according to a QPSO dynamic where each set is encoded in terms of a binary representation. Data sets from SVC 2004 data base have been used in our experiments. Very encouraging results have been obtained

    0

    full texts

    13,949

    metadata records
    Updated in last 30 days.
    King Saud University Repository
    Access Repository Dashboard
    Do you manage Open Research Online? Become a CORE Member to access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard! 👇