检索结果-内蒙古大学图书馆

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： Wei, Jin-Mao Yi, Wei-Guo Wang, Ming-Yang Institute of Computational Intelligence Northeast Normal University ChangChun Jilin 130024 China Open Symbol Computation and Knowledge Engineering Laboratory State Education Department Jilin University

ISBN: (纸本)078039092X

In this paper, we analyze the method of support-confidence framework when mining association rules. In order to avoid the limitation in the criterion, we propose a new method of match as the substitution of confidence. We analyze in detail the property of the proposed measurement. Experimental results show that there is higher correlation between the antecedent and the consequent of the rules produced by the improved method compared with the rules produced by the support-confidence framework. Furthermore, the improved method decreases the generation of redundancy rules. © 2005 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

An integration of cotraining and KNN for LPU problem

An integration of cotraining and KNN for LPU problem

引用

2nd Indian International Conference on Artificial Intelligence, IICAI 2005

作者： Xin, RuiMing Zuo, WanLi Yang, Ping Key Laboratory of Symbol Computation and Knowledge Engineering College of Computer Science and Technology JiLin University Changchun 130012 China

ISBN: (纸本)0972741216

Under the framework of LPU (learning from positive data and unlabeled data), this paper originally proposes a three-step algorithm. First, Co-Training is employed for filtering out the "suspect positive" data from the unlabeled dataset U. If CoTraining filter out the most of positive data mixed in U, the remainder of U can be viewed as a negative set with a little noise. Second, a constrained KNN approach attempts to pick out the positive data from "suspect positive" dataset which is produced in first step. Those data picked out can be supplied to positive dataset P. Finally, a linear SVM will learn from both the purified U as negative and the expanded P as positive. Because of the algorithm's characteristic of automatic expanding positive dataset, the proposed algorithm especially performs well in situations where given positive dataset P is insufficient. A comprehensive experiment proves that our algorithm is preferable to the existing ones. Copyright © IICAI 2005.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Canonical Huffman code based full-text index

引用

Progress in Natural Science:Materials International 2008年第3期18卷 325-330页

作者： Yi Zhang a,b, Zhili Pei a, Jinhui Yanga, Yanchun Liang a, a College of Computer Science and Technology, Jilin University, Key laboratory of symbol computation and knowledge engineering of the Ministry of Education, Changchun 130012, China b Department of Computer Science, Jilin Technology and Business College, Changchun 130062, China College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun 130012 China Department of Computer Science Jilin Technology and Business College Changchun 130062 China

Full-text indices are data structures that can be used to find any substring of a given string. Many full-text indices require space larger than the original string. In this paper, we introduce the canonical Huffman code to the wavelet tree of a string T[1. . .n]. Compared with Huffman code based wavelet tree, the memory space used to represent the shape of wavelet tree is not needed. In case of large alphabet, this part of memory is not negligible. The operations of wavelet tree are also simpler and more efficient due to the canonical Huffman code. Based on the resulting structure, the multi-key rank and select functions can be performed using at most nH0 + jRj(lglgn + lgn lgjRj)+O(nH0) bits and in O(H0) time for average cases, where H0 is the zeroth order empirical entropy of T. In the end, we present an efficient construction algorithm for this index, which is on-line and linear.

关键词： Full-text index Su?x automaton Canonical Hu?man code

来源：评论

学校读者我要写书评

暂无评论

Improved filter feature selection methods by samples localization

引用

Journal of Bionanoscience 2013年第4期7卷 371-377页

作者： Sun, Ying Wang, Yan Chen, Liang Du, Wei Cao, Zhongbo Zhou, You College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun 130012 China College of Chemistry Jilin University Changchun 130012 China

With the development of high-throughput microarray technology, a large number of microarray data has been obtained by tens of thousands of simulation experiments on gene expression. However, due to the high cost, gene expression data of each experiment has a small number of samples for tens of thousands of genes. Furthermore, most of the genes, such as the features, are unrelated to classification. Therefore, developing an effective and robust method to extract informative genes subset from high dimensional microarray data is a challenging and important issue for microarray data analysis. In this article, we propose an improved feature selection method by samples localization. We only use localized samples to select genes subset, in order to effectively overcome the influence on the results of feature selection by outlier samples and the distribution of samples. Experimental results obtained by SVM classifiers on Leukemia dataset, Prostate dataset, Colon dataset, Breast dataset, DLBCL dataset and Lung dataset demonstrate that the proposed method is superior to those original filter feature selection methods both in best and average accuracies. Copyright © 2013 American Scientific Publishers. Website © 2013 Publishing Technology.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Semi-automatic hardware design using ontologies

Semi-automatic hardware design using ontologies

引用

8th International Conference on Control, Automation, Robotics and Vision (ICARCV)

作者： Hu, He Liu, Da-You Du, Xiao-Yong School of Information Renmin University of China Beijin 100872 China Open Symbol Computation and Knowledge Engineering Laboratory College of Computer Science and Technology Jilin University Changchun 130012 China

ISBN: (纸本)0780386531

Hardware description language (HDL) is widely used to model the structure and behavior of digital systems ranging from simple hardware building blocks to complete systems in today's hardware design. To tackle with ever-increasing complexity of process models, higher level of abstraction needs to be exploited. We propose an ontology-based architecture in the process of hardware design using HDLs. The architecture combines the traditional HDL design processes with ontology models and offers a semi-automatic process utilizing the ontology reasoning abilities of OWL (Web Ontology Language) Based on such ontology assistant architecture, more flexible and automatic processes can be devised, which are of crucial importance to meet current market demands. © 2004 IEEE.

关键词： Computer hardware description languages

来源：评论

学校读者我要写书评

暂无评论

Noise suppression of fluorescein angiogram sequences using bilateral filter

Noise suppression of fluorescein angiogram sequences using b...

引用

International Conference on Machine Learning and Cybernetics, ICMLC 2005

作者： Guo, Xiao-Xin Lu, Yi-Nan Xu, Zhi-Wen Liu, Zhan-Hui Wang, Yun-Xiao Pang, Yun-Jie Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Qianjin Street 2699 Changchun 130012 China

ISBN: (纸本)078039092X

In this paper, a relatively flexible filter called extended bilateral filter is proposed, by which some particular filters can be designed via selecting an appropriate pixel of interest (POI) and defining a kernel for the filter according to some specified requirements. Based on the filter, a fluorescein-angiogram-oriented filter, high-intensity preserving (HIP) filter is introduced to solve the problems of high-intensity preservation when denoising. The results of the experiments show that the HIP filter has the ability of noise suppression, and the ability of high-intensity preservation, which can keep the intensities of bright pixels from degrading via distributing the weights adaptively according to the location and the intensity of each pixel. © 2005 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

Automatic localization of macular area based on structure label transfer

引用

International Journal of Ophthalmology(English edition) 2018年第3期11卷 422-428页

作者： Xiao-Xin Guo Qun Li Chao Sun Yi-Nan LU Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun130012 Jilin Province China College of Computer Science and Technology Jilin University Changchun 130012 Jilin Province China

AIM： To explore feasibility and practicability of macula localization independent of macular morphological features. METHODS： A novel method was proposed to identify macula in fundus images by using structure label transfer. Its main idea was to match a processed image with the candidate images with known structures, and then transfer the structure label representing the macular to the processed image as a result of macula localization. In this way, macula localization couldn＇t be influenced by lesion or other interference any more. RESULTS： The average success rate in four datasets was 98.18%. For accuracy, the average error distance in four datasets was 0.151 optic disc diameter （ODD）. Even for severe lesion images, the proposed method can still maintain high success rate and high accuracy, e.g., 95.65% and 0.124 ODD in the case of STARE dataset, respectively, which indicated that the proposed method was highly robust and stable in the complicated situations. CONCLUSION： The proposed method can avoid the interference of lesion to macular morphological features in macula localization, and can locate macula with high accuracy and robustness, verifying its feasibility.

关键词： fundus image optic disc macula structurelabel transfer

来源：评论

学校读者我要写书评

暂无评论

An approach for calculating semantic similarity between words using WordNet

An approach for calculating semantic similarity between word...

引用

2011 2nd International Conference on Digital Manufacturing and Automation, ICDMA 2011

作者： Hao, Dou Zuo, Wanli Peng, Tao He, Fengling College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun China

ISBN: (纸本)9780769544557

This paper presents a new edge-counting based method using Word Net to compute the similarity. The method achieves a similarity that perfectly fits with human rating and effectively simulate the human tHought process that is people prefer to consider more differences when the semantic distance between two word is closer, and vice versa. At last, we weigh up our model against a benchmark set by human similarity judgment, and obtain a much improved result compared with other methods. © 2011 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An application of Fourier-Mellin transform in image registration

An application of Fourier-Mellin transform in image registra...

引用

Fifth International Conference on Computer and Information Technology, CIT 2005

作者： Guo, Xiaoxin Xu, Zhiwen Lu, Yinan Pang, Yunjie Key Laboratory of Symbol Computation and Knowledge Engineering Jilin University Ministry of Education Qianjin Street 2699 Changchun 130012 China

Fourier-Mellin transform (FMT) is frequently used in content-based image retrieval and digital image watermarking. This paper extends the application of FMT into image registration and proposes an improved registration algorithm based on FMT for the alignment of images differing in translation, rotation angle, and uniform scale factor. The proposed algorithm can eliminate the conversion from Cartesian to log-polar coordinates, avoid the process of interpolation required in the conversion, and obtain a more significant improvement than the conventional method using cross-correlation. Experiments show that the algorithm is accurate and robust regardless of white noise. © 2005 IEEE.

关键词： Fourier transforms

来源：评论

学校读者我要写书评

暂无评论

A study on improved hidden Markov models and applications to speech recognition

A study on improved hidden Markov models and applications to...

引用

2011 International Conference on Computer Science and Service System, CSSS 2011

作者： Zhang, Zeliang Li, Xiongfei Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Changchun China Beihua University Jilin China

ISBN: (纸本)9781424497638

Visual voice lip-reading, so the computer can understand what the speakers want to express direction by looking at their lips. Lip reading is the easiest way to compare the early characters and templates from the frozen image is stored. It ignores the very nature and time changes. This method is very simple, but it's just simple elements can be classified, then it may not show significant speech recognition services. Behavior was characterized by more and more common. Because of the hidden Markov model is superior (HMM), which can be widely used in speech recognition. In recent years, is also used to lip reading identification. Classical HMM model, so that the two assumptions: hidden assumptions collected: in t+1 the state can only be in this country is not in the state before t;from the hidden visible state hypothesis: only by regulating the t hide the visible state, rather than the previous state. This hypothesis is not very useful in some applications (such as lip reading) is reasonable. Under certain conditions, in the t state not only limits the t1, but also t2. Therefore, this study modified the assumptions of the classical HMM to derive a new HMM model and algorithms, and applied to the lip-reading recognition is increasing discrimination. © 2011 IEEE.

关键词： Hidden Markov models

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：