http://hdl.handle.net/123456789/2167 البحث عن قناة بحث http://repository.ksu.edu.sa/jspui/simple-search http://hdl.handle.net/123456789/6344 العنوان: DoS attacks intelligent detection using neural networks<br/><br/>المؤلفون: Alfantookh, Abdulkader A.<br/><br/>ملخص: The potential damage to computer networks keeps increasing dueto a growing reliance on the Internet and more extensiveconnectivity. Intrusion detection systems (IDSs) have become anessential component of computer security to detect attacks thatoccur despite the best preventative measures. A problem withcurrent intrusion detection systems is that they have many falsepositive and false negative events. Most of the existing Intrusiondetection systems implemented nowadays depend on rule-basedexpert systems where new attacks are not detectable.In this paper, a possible application of Neural Networks ispresented as a component of an intrusion detection system. Anintrusion detection system called Denial of Service IntelligentDetection (DoSID) is developed. The type of Neural Network usedto implement DoSID is feed forward which uses thebackpropagation learning algorithm. The data used in training andtesting is the data collected by Lincoln Labs at MIT for an intrusiondetection system evaluation sponsored by the U.S. DefenseAdvanced Research Projects Agency (DARPA). Special featuresof connection records have been identified to be used in DoS(Denial-of-Service) attacks. Several experiments have beenconducted to test the ability of the neural network to distinguishknown and unknown attacks from normal traffic. Results showthat normal traffic and know attacks are discovered 91% and100% respectively. Also it has been shown in the final experimentthat the false negative of the system has been reducedconsiderably.<br/><br/>وصف: Computer Science DepartmentCollege of Computer and Information Sciences,King Saud UniversityP.O. Box 301334, Riyadh 11372, Saudi Arabia Sun, 01 Jan 2006 00:00:00 GMT http://hdl.handle.net/123456789/3293 العنوان: Relative distance vector neural network (RDVNN) model: a hybrid approach to speech recognition<br/><br/>المؤلفون: Elgasim, Elamin Elnima<br/><br/>ملخص: This paper introduces a novel insight to the problem of Automatic Speech Recognition (ASR).Worldwide many practical systems had been developed for ASR. Most of these systems were based on HiddenMarkov Models (HMM). This is state-of-the-art paradigm in ASR. Despite the fact that HMMs are successfulunder a diversity of conditions, they do suffer from some limitations that limit their applicability to real-worldnoisy environments. As a result, several researchers moved to Artificial Neural Networks (ANNs) as analternative technique for ASR, in order to overcome the limitations encountered in pure HMM implementation.Soon after, interest moved over to hybrid systems that combine HMMs and ANNs within a single unifyinghybrid architecture. In this study a hybrid DTW/ANN ASR system will be introduced, explained, implementedand analyzed, which has been given the name Relative Distance Vector Neural Network (RDVNN) Model.Adequate experiments had been performed to reveal the main characteristics of the present novelhybrid ASR system. The results are believed to be encouraging and the system is easy to implement. Forspeaker dependent the accuracy is near perfect (error rate is less than 1%). For speaker independent models theresults attained are comparable with most world-wide results known for the state-of-the-art ASR small tasksystems. Many aspects of the RDVNN technique are illustrated through experimental work to demonstratethese findings. One of the main advantages of the RDVNN method is that it can be applied to various othersimilar problem domains. Thu, 01 Jan 2004 00:00:00 GMT http://hdl.handle.net/123456789/1532 العنوان: Building a microcontroller virtual lab using web-based and mobile agents approaches<br/><br/>المؤلفون: Al-Shehriand, Saleh A.; Al-Oqeely, Mohammed<br/><br/>ملخص: Among the recent applications of Internet technology is virtual labs which enable users to conduct experiments trom a distance. Most of the existing virtual lab applications fall into one of the following categories: lab simulators, telerobotic control, weather readings, database management, real-time video photo transferring and vending machines control. In all of these systems, the user either has a limited interaction with the remote system, or is forced to deal with simulators instead of real devices. In order to make the most benefit of remote experimenting, the user should have sufficient power over actual lab devices and equipment. Furthennore, the student should not worry about restrictions on access times or a failure of one of the lab equipment. In this paper we present the design and implementation of a computer engineering lab that applies both web and mobile agents technologies. The novel proposed mobile agents design offers flexibility and failure tolerance and overcomes some of the pitfalls of many existing virtual labs. Furthermore, the study concludes with a comparison and analysis of the proposed approaches. Tue, 01 Jan 2002 00:00:00 GMT http://hdl.handle.net/123456789/1533 العنوان: E-Commerce enabled supply chain management: a proposed model based on retailing experience<br/><br/>المؤلفون: Zairi, Mohamed; Al-Mashari, Majed<br/><br/>ملخص: This paper discusses the concepts of Electronic Commerce (EC) and Supply Chain Management (SCM) as they apply to the retailing sector. In particular, the paper looks at the evolution of the supply chain concept ITom upstream logistics all the way towards an integrated approach based primarily on the principles of partnerships with core suppliers. Evaluations of partnerships between retailers and their suppliers are addressed by looking at Quick Response (QR), Vendor Managed Inventory (VMI) and in particular, the growth of Efficient Consumer Response (ECR). The retailing experience in relation to the previously mentioned concepts is covered in the paper through highlighting the experiences of Sainsbury, Safeway, Tesco and Wal-Mart. Finally, a proposed model for Effective Supplier-Retailer relationships is discussed, based on a benchmarking project of several organizations. Tue, 01 Jan 2002 00:00:00 GMT