检索结果-内蒙古大学图书馆

2004 IEEE International Conference on Multimedia and Expo (ICME)

作者： Wu, Jinhai Zhu, Bin B. Li, Shipeng Lin, Fuzong State Key Lab Intelligent Tech./S. Tsinghua Univ. Beijing 100084 China Microsoft Research Asia Beijing 100080 China

ISBN: (纸本)0780386035

The Yeung-Mintzer (Y-M) image authentication scheme has been well studied. Several vulnerabilities and modified schemes to fix them have been reported. In this paper, we propose a novel oracle attack on the Y-M scheme and its variations. Our attack is very different from the previously proposed attacks. A single authenticated image plus access to a verifier (oracle) is enough in our attack. The verifier returns if a testing image is authentic or not. Locations of tampered pixels are not needed. To launch the attack, a single pixel is modified and the resulting image is sent to the verifier. Observation of outputs of the verifier is used to deduce the secret mapping functions and the embedded logo within an uncertainty of two possibilities. The deduced mapping functions are then used to modify the content of an authenticated image without detection or to authenticate an arbitrary image of the same size. Note that the logo is not used in the forgery so sophisticated protection of the logo cannot thwart the attack. Our attack is very efficient. Only 255 trials are needed to attack an 8-bit grayscale image and 765 trails for a 24-bit color image. The proposed attack can also be applied to attack pixel-wise variations of the Y-M scheme proposed to fix the previously reported vulnerabilities.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Reinforcement learning based on spatial and temporal association of states

Reinforcement learning based on spatial and temporal associa...

引用

2004 IEEE International Conference on systems, Man and Cybernetics, SMC 2004

作者： Zhuang, Xiao-Dong Meng, Qing-Chun Yin, Bo Gao, Yun Computer Science Department Ocean University of China Qingdao 266003 China State Key Lab. Intelligent Tech./S. Tsinghua University Beijing 100084 China

ISBN: (纸本)0780385667

In this paper, mechanisms in human learning are incorporated into the reinforcement learning to improve the learning efficiency. A new learning method is presented based on the spatial and temporal association of states, which is inspired by the analogy and recall in human learning. The fuzzy state is proposed to represent the spatial association of states in the state space. The delayed optimization of the control process is proposed for learning with temporally correlated states. In the experiment, the proposed method is applied to a maze problem, which shows that the proposed method has improved learning performance. © 2004 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

A new textual/non-textual classifier for document skew correction

Proceedings - International Conference on Pattern Recognitio...

引用

Proceedings - International Conference on Pattern Recognition 2002年第1期16卷 480-482页

作者： Xiaoyan, Zhu Xiaoxin, Yin IEEE State Key Lab. of Intelligent Tech. and Systems Dept. of Computer Science and Technology Tsinghua University Beijing 100084 China

A robust approach is proposed for document skew detection. We use Fourier analysis and SVM to classify textual areas from non-textual areas of documents. We also propose a robust method to determine the skew angle from textual areas. Our approach achieves good performance on documents with large area of non-textual contents. © 2002 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Correlation-Based Web Document Clustering for Adaptive Web Interface Design

引用

Knowledge and Information systems 2002年第2期4卷 151-167页

作者： Su, Zhong Yang, Qiang Zhang, Hongjiang Xu, Xiaowei Hu, Yu-Hen Ma, Shaoping State Key Lab of Intelligent Tech. and Systems Tsinghua University Beijing China School of Computing Science Simon Fraser University BurnabyBC Canada Microsoft Research China Beijing China Siemens AG Information and Communications Corporate Technology Munich Germany Department of Electrical and Computer Engineering University of Wisconsin–Madison MadisonWI United States

A great challenge for web site designers is how to ensure users' easy access to important web pages efficiently. In this paper we present a clustering-based approach to address this problem. Our approach to this challenge is to perform efficient and effective correlation analysis based on web logs and construct clusters of web pages to reflect the co-visit behavior of web site users. We present a novel approach for adapting previous clustering algorithms that are designed for databases in the problem domain of web page clustering, and show that our new methods can generate high-quality clusters for very large web logs when previous methods fail. Based on the high-quality clustering results, we then apply the data-mined clustering knowledge to the problem of adapting web interfaces to improve users' performance. We develop an automatic method for web interface adaptation: by introducing index pages that minimize overall user browsing costs. The index pages are aimed at providing short cuts for users to ensure that users get to their objective web pages fast, and we solve a previously open problem of how to determine an optimal number of index pages. We empirically show that our approach performs better than many of the previous algorithms based on experiments on several realistic web log files. © 2002, Springer-Verlag London Limited.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

3D positioning principle and 3D reflected wave field modeling

引用

Kuangwu Yanshi 2002年第3期22卷 93-97页

作者： Xiong, Gao-jun Zhang, Xue-gong He, Zhen-hua Wu, Zheng-bo Automation Dept. of Tsingua Univ. State Key Lab. of Intelligent Tech. Beijing 100084 China

3-dmension positioning principle of forward modeling was presented on the basis of extrapolating wave field by one-way acoustic wave equation. The method of 3-dimension pre-stack reflection wave field modeling, whichcould completely solve the three problems of full acoustic wave forward modeling was deduced. In the course of wave field extrapolation, analytic method of wave equation was employed, and numeric method was also used as complement under the condition of lateral velocity variation. The whole process is accurate, speedy, and can deal with complex structure and random velocity variation.

关键词： Acoustic fields

来源：评论

学校读者我要写书评

暂无评论

A Fast Hybrid Algorithm of Global Optimization for Feedforward Neural Networks

引用

中国电子杂志（英文版） 2001年第2期10卷 214-218页

作者： JIANG Minghu ZHANG Bo ZHU Xiaoyan JINAG Mingyan Lab of Computational Linguistics Dept. of Chinese Language Tsinghua University Beijing 100084 China State Key Lab of Intelligent Tech. & Systems Dept. of Computer Tsinghua University Beijing 100084 China Dept. of Electronic Engineering Shandong University Jinan 250100 China

This paper presents the hybrid algorithm of global optimization of dynamic learning rate for multilayer feedforward neural networks (MLFNN).The effect of inexact line search on conjugacy was studied, based on which a generalized conjugate gradient method was proposed, showing global convergence for error backpagation of MLFNN. It overcomes the drawback of conventional BP and Polak-Ribieve conjugate gradient algorithms that maybe plunge into local minima. The hybrid algorithm's recognition rate is higher than that of Polak-Ribieve algorithm and convergence BP for test data, its training time is less than that of Fletcher-Reeves algorithm and far less than that of convergence BP, and it has a less complicated and stronger robustness to real speech data.

关键词： The conjugate gradient algorithm Global convergence Backpropagation.

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Mandarin Braille word and Braille translation based on multi-knowledge

Segmentation of Mandarin Braille word and Braille translatio...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Jiang Minghu Zhu Xiaoyan Xia Ying Tan Gang Yuan Baozong Tang Xiaofang Institute of Information Sceince Northern Jiaotong University Beijing China State Key Laboratory of Intelligent Tech. & Systems Department of Computer Tsinghua University Beijing China

This paper is about the segmentation of Braille words and the transformation from Mandarin Braille to Chinese characters. Braille word segmentation consists of the rules base, the signs base of segmentation and knowledge base for disambiguation and mistakes. By using adjacency constraints and bidirectional maximum matching with a dictionary, our system's segmentation precision is better than 99% for the common text. By incorporating a pinyin knowledge dictionary into the system, we perfectly solved the problem of ambiguity in the translation from Braille to pinyin and developed a statistical language model based on the transformation of pinyin into characters. By using a multi-knowledge base to carry out the disambiguation process for each pinyin sentence, we built a multi-level graph and used a Viterbi search to find the sequence of Chinese characters with maximum likelihood, and used an N-best algorithm to get the N most likely character sequences. The experimental results show that the system's overall precision for translation from Braille codes to Chinese characters is 94.38%.

关键词： Dictionaries intelligent systems Natural languages Viterbi algorithm Smoothing methods Writing Law Legal factors Statistics Joining processes

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Mandarin Braille Word and Braille Translation Based on Multi-knowledge

Segmentation of Mandarin Braille Word and Braille Translatio...

引用

2000年第16届世界计算机大会

作者： Jiang Minghu Zhu Xiaoyan Xia Ying Tan Gang Yuan Baozong Tang Xiaofang Institute of Information Sceince Northern Jiaotong University State Key Lab of Intelligent Tech.& Systems Department of ComputerTsinghua University

This paper is about the segmentation of Braille words and the transformation from Mandarin Braille to Chinese *** word segmentation consists of rules base,the signs base of segmentation and knowledge base for disambiguation and mistakes,by using adjacency constraints and bidirectional maximum matching with a dictionary,our system's segmentation precision is better than 99%for the common *** incorporating a pinyin knowledge dictionary into the system,we perfectly solved the problem of ambiguity in the translation from Braille to pinyin and developed a statistical language model based on the transformation of pinyin into *** using a multi-knowledge base to carry out the disambiguation process for each pinyin sentence,we built a multi-level graph and used Viterbi search to find the sequence of Chinese characters with maximum likelihood,and used an N-Best algorithm to get the N most likely character *** experimental results show that the system's overall precision for translation from Braille codes to Chinese characters is 94.38%.

关键词： Braille translation Virterbi algorithm smoothing method multi-knowledge

来源：评论

学校读者我要写书评

暂无评论

A Fast Hybrid Algorithm of Global Optimization for Feedforward Neural Networks

A Fast Hybrid Algorithm of Global Optimization for Feedforwa...

引用

2000年第16届世界计算机大会

作者： Jiang Minghu Zhu Xiaoyan Yuan Baozong Tang Xiaofang Lin Biqin Ruan Qiuqi Jiang Mingyan Institute of Information Sceince Northern Jiaotong University State Key Lab of Intelligent Tech & Systems Dept.of ComputerTsinghua University Dept of Electronic Shandong University

This paper presents the hybrid algorithm of global optimization of dynamic learning rate for multilayer feedforward neural networks(MLFNN). The effect of inexact line search on conjugacy was studied and a generalized conjugate gradient method based on this effect was proposed and shown to have global convergence for error backpagation of *** descent property and global convergence was given for the improved hybrid algrithm of conjugate gradient algorithm, the results of the proposed algorithm show a considerable improvement over the FletcherRreeves algorithm and conventional BP algorithm, it overcomes the drawback of conventional BP and Polak-Ribieve conjugate gradient algorithm that maybe plung into local minima.

关键词： the conjugate gradient algorithm global convergence backpropagation inexact line search

来源：评论

学校读者我要写书评

暂无评论

Analysis of the effects of quantization in high-order function neural network

Analysis of the effects of quantization in high-order functi...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Jiang Minghu Zhu Xiaoyan Lin Ying Yuan Baozong Tang Xiaofang Lin Biqin Ruan Qiuqi Jiang Mingyan Institute of Information Sceince Northern Jiaotong University Beijing China State Key Laboratory of Intelligent Tech. & Systems Department of Computer Tsinghua University Beijing China Department of Electronic ShanDong University Jinan China

A statistical quantization model is used to analyze of the effects of quantization in digital implementation of high-order function neural network. From the theory we analyse the performance degradation and fault tolerance of the neural network caused by the number of quantization bits and by changing the order. We try to predict the error in the high-order function neural network (HOFNN) given the properties of the network and the number of quantization bits. Experimental results show the error rate is inversely proportional to quantized bits M for HRFNN. The recognition performance of the backpropagation (BP) network and the HRFNN are almost the same for different quantization bits. The network's performance degradation gets worse when the number of bits is lower than 4-bit quantization. The network's performance degradation gets worse when the number of bits is lower than 4-bit quantization.

关键词： Quantization intelligent networks Neural networks Degradation Neurons intelligent systems Computer networks Information analysis Performance analysis Fault tolerance

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：