检索结果-内蒙古大学图书馆

Iris recognition using genetic algorithms and asymmetrical SVMs

Machine Graphics and Vision 2010年第1期19卷 33-62页

作者： Roy, Kaushik Bhattacharya, Prabir Department of Computer Science and Software Engineering Concordia University Montreal QC H3G1M8 Canada Department of Computer Science College of Engineering and Applied Sciences University of Cincinnati Cincinnati OH 45221-0030 United States

With the increasing demand for enhanced security, iris biometrics-based personal identification has become an interesting research topic in the field of pattern recognition. While most state-of-the-art iris recognition algorithms are focused on preprocessing iris images, important new directions have been identified recently in iris biometrics research. These include optimal feature selection and iris pattern classification. In this paper, we propose an iris recognition scheme based on Genetic algorithms (GAs) and asymmetrical Support Vector Machines (SVMs). Instead of using the whole iris region, we elicit the iris information between the collarette and the pupillary boundaries to suppress effects of eyelids and eyelashes occlusions, and pupil dilation, and to minimize the matching error. To select the optimal feature subset together with increasing the overall recognition accuracy, we apply GAs with a new fitness function. The traditional SVMs are modified into asymmetrical SVMs to handle: (1) highly unbalanced sample proportion between two classes, and 2) different types of misclassification error that lead to different misclassification losses. Furthermore, the parameters of SVMs are optimized in order to improve the generalization performance. The proposed technique is computationally effective, with recognition rates of 97.80% and 95.70% on the Iris Challenge Evaluation (ICE) and the West Virginia University (WVU) iris datasets, respectively.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Evaluating neural network intrusion detection approaches using Analytic Hierarchy Process

Evaluating neural network intrusion detection approaches usi...

引用

International Symposium on Information Technology, ITSim

作者： Iftikhar Ahmad Azween B Abdullah Abdullah S alghamdi Department of Computer and Information Sciences Universiti Teknologi Petronas Bandar Seri Iskandar Tronoh Perak Malaysia Department of Software Engineering College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia

At present age, security in computer and network systems is a pressing concern because a solo attack may cause an immense destruction in computer and network systems. Various intrusion detection approaches be present to resolve this serious issue but the dilemma is which one is more appropriate in the field of intrusion. Therefore, in this paper, we evaluated and compared different neural network (NN) approaches to intrusion detection. This work describes the concepts, tool and methodology being used for assay of different NN intrusion detection approaches using Analytic Hierarchy Process (AHP). Further, conclusion on results is made and direction for future works is presented. The outcome of this work may help and guide the security implementers in two possible ways, either by using the results directly obtained in this paper or by extracting the results using similar mechanism but on different intrusion detection systems or approaches.

关键词： Artificial neural networks Modems Subspace constraints

来源：评论

学校读者我要写书评

暂无评论

Remote to Local attack detection using supervised neural network

Remote to Local attack detection using supervised neural net...

引用

International Conference for Internet Technology and Secured Transactions (ICITST)

作者： Iftikhar Ahmad Azween B Abdullah Abdullah S alghamdi King Saud University Saudi Arabia Department of Computer and Information Sciences Universiti Teknologi MARA Bandar Perak Malaysia Department of Software Engineering College of Computer and Information Sciences King Saud University Saudi Arabia

In order to determine Remote to Local (R2L) attack, an intrusion detection technique based on artificial neural network is presented. This technique uses sampled dataset from Kddcup99 that is standard for benchmarking of attack detection tools. The backpropagation algorithm is used for training the feedforward neural network. The developed system is applied to R2L attacks. Moreover, experiment indicates this technique has comparatively low false positive rate and false negative rate, consequently it effectively resolves the deficiency of existing intrusion detection approaches.

关键词： computers Monitoring Informatics Books Testing Telecommunications Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigating supervised neural networks to intrusion detection

引用

ICIC Express Letters 2010年第6 A期4卷 2133-2138页

作者： Ahmad, Iftikhar Abdullah, Azween alghamdi, Abdullah Department of Software Engineering College of Computer and Information Sciences King Saud University P. O. Box 51178 Riyadh 11543 Saudi Arabia Department of Computer and Information Sciences Universiti Teknologi PETRONAS Bandar Seri Iskandar 31750 Tronoh Perak Malaysia

The application of neural networks towards intrusion detection is becoming a mainstream and a useful approach to deal with several current issues in this area. Currently, security in computer and network is a main problem because a single intrusion may cause a very big harm. A variety of neural networks is applied to intrusion detection approaches during last few years and still is being used in this area. In this paper, we investigated different supervised neural networks (SNN) to intrusion detection. This work describes an analysis of different supervised neural network applied to intrusion detection mechanisms using Multi-criteria analysis (MCA) technique. Further, conclusion on results is made and direction for future works is presented. The outcome of this effort may assist and direct the security implementers in the area of intrusion detection systems or approaches. ICIC International © 2010 ISSN 1881-803X.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Bézier curve based dynamic obstacle avoidance and trajectory learning for autonomous mobile robots

Bézier curve based dynamic obstacle avoidance and trajector...

引用

International Conference on Intelligent Systems Design and Applications (ISDA)

作者： Tayyab Chaudhry Tauseef Gulrez ali Zia Shyba Zaheer Intelligent Machines & Robotics Research Group Department of Computer Science Comsats Institute of Information Technology Lahore Pakistan Department of Electrical Engineering College of Engineering and Applied Sciences Al Ghurair University Dubai UAE

This paper addresses the problem of avoiding dynamic obstacles while following the learned trajectory through non-point based maps directly through laser data. The geometric representation of free configuration area changes while a moving obstacle enters into the safety region of autonomous mobile robot. We have applied the Bézier curve properties to the free configuration eigenspaces to satisfy the dynamic obstacle avoidance path constraints. The algorithm is designed to accurately represent the mobile robot's characteristics while avoiding obstacle such as minimum turning radius. Moreover, we also discuss the obstacle avoided path feasibility as a vectorial combination of free configuration eigen-vectors at discrete time scan-frames to manifest a trajectory, which once followed and mapped onto the two control signals of mobile robot will enable it to build an efficient and accurate online environment map. Preliminary results in Matlab have been shown to validate the idea, while the same has been implemented in Player/stage (robotics real-time software) to analyze the performance of the proposed system.

关键词： Trajectory Vehicles Robot sensing systems Mobile robots Mathematical model Lasers

来源：评论

学校读者我要写书评

暂无评论

Re-thinking virtual universities

引用

Procedia - Social and Behavioral sciences 2010年第2期2卷 5769-5774页

作者： İlker Yengin Dilek Karahoca Adem Karahoca Huseyin Uzunboylu College of Education and Human Sciences University of Nebraska-Lincoln Lincoln USA Software Engineering Department Bahcesehir University Ciragan 34353 Besiktas Istanbul Turkey Department of Computer Education and Instructional Technologies Near East University Lefkosa 98010 Northern Cyprus

The purpose of this paper is to review the key issues in the virtual universities and to provide general overview of the concepts based on the latest trends for the academic decision makers, e-learning designers and teaching professionals. In the rest of the paper author summarizes the key issues in the virtual learning in universities and the other factors that are important in that area.

关键词： Virtual Universities virtual education distance learnin e-learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Intrusion Detection Approaches

Comparative Analysis of Intrusion Detection Approaches

引用

International Conference on computer Modeling and Simulation, UKSIM

作者： Iftikhar Ahmad Azween B. Abdullah Abdullah S. alghamdi DSE CCIS King Saud University Riyadh Saudi Arabia Department of Computer & Information Sciences Universiti Teknologi Malaysia Perak Malaysia Department of Software Engineering College of Computer & Information King Saud University Riyadh Saudi Arabia

ISBN: (纸本)9781424466146;9780769540160

Information security is a serious issue especially in present age because a solo attack may cause a big harm in computer and network systems. Several intrusion detection approaches exist to tackle this critical issue but the problem is which one is more suitable in the field of intrusion. Further, these approaches are used in intrusion detection systems. Therefore, in this paper, we evaluated them so that a suitable approach may be advised to intrusion detection systems. This work describes the concepts, tool and methodology being used for evaluation analysis of different intrusion detection approaches using multi-criteria decision making technique. Moreover, conclusion on results is made and direction for future works is presented.

关键词： Intrusion detection computer networks Decision making Artificial neural networks Information analysis Resource management Computational modeling Analytical models computer simulation Radiofrequency interference

来源：评论

学校读者我要写书评

暂无评论

Applying neural network to U2R attacks

Applying neural network to U2R attacks

引用

IEEE Symposium on Industrial Electronics & Applications (ISIEA)

作者： Iftikhar Ahmad Azween B Abdullah Abdullah S alghamdi King Saud University Riyadh Saudi Arabia Department of Computer & Information Sciences Universiti Teknologi Petronas Bandar Seri Iskandar Iskandar Perak Malaysia Department of Software Engineering College of Computer & Information King Saud University Riyadh Saudi Arabia

Intrusion detection using artificial neural networks is an ongoing area and thus interest in this field has increased among the researchers. Therefore, in this paper we present a system for tackling User to Root (U2R) attacks using generalized feedforward neural network. A backpropagation algorithm is used for training and testing purpose. The system uses sampled data from Kddcup99 dataset, an attack database that is a standard for evaluating the security detection mechanisms. The system is implemented in two phases such as training phase and testing phase. The developed system is applied to different U2R attacks to test its performance. Furthermore, the results indicate that this approach is more precise and accurate in case of false positive, false negative and detection rate.

关键词： Artificial neural networks Intrusion detection Training Testing Feedforward neural networks computers

来源：评论

学校读者我要写书评

暂无评论

IP core logic fault test simulation environment

IP core logic fault test simulation environment

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Mansour H. Assaf Leslie-Ann Moore Sunil R. Das Emil M. Petriu Satyendra N. Biswas Department of Information Communications Technology University of Trinidad and Tobago Arima Trinidad and Tobago School of Information Technology and Engineering Faculty of Engineering University of Ottawa Ottawa ONT Canada Department of Computer Science College of Arts and Sciences Troy University Montgomery AL USA Department of Electronics Engineering Norfolk State University Norfolk VA USA

A low-level logic fault test simulation environment for embedded systems directed specifically towards application-specific integrated circuits (ASICs) and intellectual property (IP) cores is proposed in the paper. The developed simulation environment emulates a typical builtin self-testing (BIST) architecture with automatic test pattern generator (ATPG) that sends its outputs to a circuit (core) under test (CUT) and the output streams from the CUT are fed into an output response analyzer (ORA). The paper delineates the development of the test architecture, test application and fault injection including the relevance of the logic fault *** great details. Some results on simulation on specific IP cores designed using combinations from ISCAS 85 combinational and ISCAS 89 sequential benchmark circuits are provided as well for evaluation.

关键词： Logic testing Circuit testing Circuit simulation Circuit faults Built-in self-test Logic circuits Integrated circuit testing System testing Embedded system Application specific integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Urdu noun phrase chunking: HMM based approach

Urdu noun phrase chunking: HMM based approach

引用

International Conference on Educational and Information Technology (ICEIT)

作者： Wajid ali M. Kamran Malik Sarmad Hussain Shahid Siddiq Aasim ali Department of Computer Sciences National University of Computer and Emerging Sciences Lahore Pakistan Institute of Business and Information Technology (IBIT) University of Punjab Lahore Pakistan Center of Language Engineering Al-Khawarizmi Institute of Computer Sciences UET Taxila Lahore Pakistan Punjab University College of Information Technology (PUCIT) University of Punjab Lahore Pakistan

Extraction of noun phrase (NP) from text is useful for many natural language processing applications, such as name entity recognition, indexing, searching, parsing etc. We present a noun phrase chunker for Urdu which is based on a statistical approach. A 100,000 words Urdu corpus is manually tagged with NP chunk tags. The corpus is used to develop a statistical approach. Initially, a statistical approach based on standard HMM model is developed for automatics NP chunking. In Urdu phrases, the case marker (CM) indicates the end of a noun phrase and is appended at its end. Thus, if one scans the sentence in reverse order, one may be able to better predict phrase endings. So, the technique is enhanced by changing scanning direction. The technique is further enhanced by merging chunk and POS tags to achieve maximum accuracy. The results of all experiments are reported with maximum overall accuracy of 97.61% achieved using HMM based approach with extended tagset and right to left (RTL) scanning.

关键词： Hidden Markov models Testing Random access memory Cardiology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：