检索结果-内蒙古大学图书馆

MRI image segmentation based on fast kernel clustering analysis

Frontiers of Electrical and Electronic Engineering in China 2011年第2期6卷 363-373页

作者： Liang LIAO Yanning ZHANG Shaanxi Provincial Key Laboratory of Speech and Image Information Processing(SAIIP) School of Computer ScienceNorthwestern Polytechnical UniversityXi’an 710129China School of Electric and Information Engineering Zhongyuan University of TechnologyZhengzhou 450007China

Kernel-based clustering is supposed to provide a better analysis tool for pattern classification,which implicitly maps input samples to a highdimensional space for improving pattern *** this implicit space map,the kernel trick is believed to elegantly tackle the problem of“curse of dimensionality”,which has actually been more challenging for kernel-based clustering in terms of computational complexity and classification accuracy,which traditional kernelized algorithms cannot effectively deal *** this paper,we propose a novel kernel clustering algorithm,called KFCM-III,for this problem by replacing the traditional isotropic Gaussian kernel with the anisotropic kernel formulated by Mahalanobis ***,a reduced-set represented kernelized center has been employed for reducing the computational complexity of KFCM-I algorithm and circumventing the model deficiency of KFCM-II *** proposed KFCMIII has been evaluated for segmenting magnetic resonance imaging(MRI)*** this task,an image intensity inhomogeneity correction is employed during image segmentation *** a scheme called preclassification,the proposed intensity correction scheme could further speed up image *** experimental results on public image data show the superiorities of KFCM-III.

关键词： kernel-based clustering dimensionality reduction speeding-up scheme magnetic resonance imaging(MRI)image segmentation intensity inhomogeneity correction

来源：评论

学校读者我要写书评

暂无评论

Combination Method of Rules and Statistics for Abbreviation and Its Full Name Recognition

Combination Method of Rules and Statistics for Abbreviation ...

引用

2011 International Conference on Informatics,Cybernetics,and computer Engineering(ICCE 2011)

作者： Yang Hua Hong Yu Hua Zhenwei Yao Jianmin Zhao Mingming Feng Yanhui Provincial Key Laboratory of Computer Information Processing Technology Soochow University Suzhou Municipal Science and Technology Bureau

This paper proposes a Combination of rules and statistics algorithm. Firstly, this research uses the rule-based approach to identify the abbreviation. Secondly, the full name candidates of the abbreviation are recognized based on n-gram feature. Thirdly, we use the rule and statistic based algorithm to identify the best candidate for the abbreviation. The method of abbreviation recognition has achieved a high accuracy rate, and it is independent, portable and efficient. The method of the full name recognition is superior to the approach introduced in related work on the basis of analyzing and comparing experiment results.

关键词： Biomedical information extraction Abbreviation recognition Abbreviation full name recognition Text mining Combining method of rules and statistics

来源：评论

学校读者我要写书评

暂无评论

Developing software using a novel event-condition-state pattern framework: Taking mobile input method system As A Case Study

Journal of Software

引用

Journal of Software 2011年第8期6卷 1506-1512页

作者： Zhu, Fei Diao, Hongjun Huang, Wei School of Computer Science and Technology Soochow University Suzhou Jiangsu 215006 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou Jiangsu 215006 China

Design patterns add more reliability, flexibility and reusability to a software system. Taking advantage of design patterns is usually beneficial to software design and makes software development relatively easier. The state pattern proposed by GoF is not a determined design and can hardly be transformed into implementation code directly. It is disable to cope with sophisticated response event either. Hereby we propose a novel event-conditionstate pattern framework, an event-based finite state machine. The framework improves GoF state pattern by resegmenting Context into two classes, one for management and the other for operation interface. Essential components for implementation, such as management, state transferring, and event triggering mechanism, are also taken into consideration in the framework. We use pattern framework to develop a thirty party input method system which has a Windows Mobile system version and a Symbian system version separately. We rewrote Context part related with system interfaces in the two different systems, and encapsulated the part related with internal logic of input method by concrete subclasses, thus avoiding redundant developing work in both systems and providing convenience for later synchronous updating and maintenance of two input methods. With the pattern framework, much effort during software development is saved. The development logic seems simpler and clearer. As a result, the whole development process is simplified. © 2011 ACADEMY PUBLISHER.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Chinese zero anaphor detection: Rule-based approach

Chinese zero anaphor detection: Rule-based approach

引用

作者： Qin, Kaiwei Kong, Fang Li, Peifeng Zhu, Qiaoming School of Computer Science and Technology Soochow University Jiangsu 215006 China Key Lab. of Computer Information Processing Technology of Jiangsu Province Suzhou Jiangsu 215006 China

ISBN: (纸本)9783642256608

A rule-based approach for Chinese zero anaphor detection is proposed. Given a parse tree, the smallest IP sub-tree covering the current predicate is captured. Based on this IP sub-tree, some rules are proposed for detecting whether a Chinese zero anaphor exists. This paper also systematically evaluates the rule-based method on OntoNotes corpus. Using golden parse tree, our method achieves 82.45 in F-measure. And the F-measure is 63.84 using automatic parser. The experiment results show that our method is very effective on Chinese zero anaphor detection. © 2011 Springer-Verlag Berlin Heidelberg.

关键词： Forestry

来源：评论

学校读者我要写书评

暂无评论

On the Operational Semantics of a Higher Order Safe Ambients Calculus

On the Operational Semantics of a Higher Order Safe Ambients...

引用

The Second International Conference on Theoretical and Mathematical Foundations of computer Science（ICTMF 2011）

作者： Zining Cao Department of Computer Science and Technology Nanjing University of Aero.& Astro. Provincial Key Laboratory for Computer Information Processing Technology Soochow University

In this paper, we propose a higher order safe ambients calculus. In this setting, we propose an extended labelled transition system and an extended labelled bisimulation for this calculus. We also give the reduction barbed congurence and prove the equivalence of extended labelled bisimulation and reduction barbed congruence for this calculus.

关键词： SAP On the Operational Semantics of a Higher Order Safe Ambients Calculus

来源：评论

学校读者我要写书评

暂无评论

Assigning method for decision power based on linguisitc 2-tuple judgment matrices

Journal of Software

引用

Journal of Software 2011年第3期6卷 508-515页

作者： Zhang, Xixiang Yue, Guangxue Zheng, Xiajie Yu, Fei Business School of Jiaxing University Jiaxing China Mathematics and Information Engineering School of Jiaxing University Jiaxing China Department of Computer Science and Technology Huaihua University Huaihua China Jiangsu Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China

Decision power is very important in group decision making, which effects the final decision making result. When there exists uncertainty in group decision making, it is easy for an expert to express his/her preferences using fuzzy linguistic term such as 'good', 'very good'. The linguistic 2-tuple representation model was selected to represent fuzzy linguistic term for its accuracy in representing fuzzy terms and less loss of information in processing. To obtain the objective decision power in group decision making where the experts express their opinions using linguistic 2-tuple judgment matrices, the paper put forward a new approach to assign decision power based on element consistency level. And the method for calculating the contribution degree of each expert was also provided. The proposed method thought of calculating the different weight to aggregate different element according to the element consistent level. An illustrated example was used to demonstrate the proposed method. And a GDSS based on the method was also developed to simplify the application in ***. The GDSS was applied to building non-financial performance system for listed company in small and medium enterprise board in China, which showed its reasonability. © 2011 ACADEMY PUBLISHER.

关键词： Linguistics

来源：评论

学校读者我要写书评

暂无评论

processing of simulated biosensor data using artificial neural networks

Processing of simulated biosensor data using artificial neur...

引用

2011 IEEE International Symposium on IT in Medicine and Education, ITME 2011

作者： Ling, Gao Institute of Information Science and Engineering ShanDong Normal University Shandong Provincial Key Laboratory for Distributed Computer Software Novel Technology Jinan 250014 China

ISBN: (纸本)9781612847023

Probability artificial neural network (PNN) and back propagation neural network (BPNN) are used in processing of the simulated data of heavy metals biosensors. The probability artificial neural network is used in pattern recognition to determine the kinds of heavy metals in the sample. The back propagation neural network is used in prediction of the heavy metal concentrations. The results shows that these two artificial neural networks work well. © 2011 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Survey of Game Theory in Wireless Sensor Networks Security

引用

Journal of Networks 2011年第3期6卷 521-532页

作者： Shen, Shigen Yue, Guangxue Cao, Qiying Yu, Fei College of Information Science and Technology Donghua University Shanghai China College of Mathematics and Information Engineering Jiaxing University Jiaxing China College of Computer and Communication Hunan University Changsha China Department of Computer Science and Technology Huaihua University Huaihua China Jiangsu Provincial Key Laboratory for Computer Information Processing Technology Soochow University Soochow China

Wireless Sensor Networks (WSNs) are becoming an integral part of our lives. There are not widespread applications of WSNs without ensuring WSNs security. Due to the limited capabilities of sensor nodes in terms of computation, communication, and energy, providing security to WSNs is challenging. In fact, the process of implementing WSNs security is adaptive and dynamic, which evolves continually. The essence of attack-defend in WSNs security can be expressed by mutual strategies of interdependence while game theory can be used for the purpose of accounting for interactions among strategies of rational decision makers. Therefore, studying WSNs security with game theory has higher scientificity and rationality. This paper presents a survey of security approaches based on game theory in WSNs. According to different applications, a taxonomy is proposed, which divides current existing typical game-theoretic approaches for WSNs security into four categories: preventing Denial of Services (DoS) attacks, intrusion detection, strengthening security, and coexistence with malicious sensor nodes. The main ideas of each approach are overviewed while advantages and disadvantages of various approaches are discussed. Then, this paper overviews related work and highlights the difference from other surveys, and points out some future research areas for ensuring WSNs security based on game theory, including Base Station (BS) credibility, Intrusion Detection System (IDS) efficiency, WSNs mobility, WSNs Quality of Service (QoS), real-world applicability, energy consumption, sensor nodes learning, and expanding game theory applications and different games. Thus, a global view of WSNs security approaches based on game theory is provided. To our best knowledge of knowing, it is the first paper centrally focusing on game theory in WSNs security. It will make the researchers a better understanding of game-theoretic solutions to WSNs security and further research directions. © 2011 ACADEMY PU

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Extracting Image Semantic Object Based on Artificial Bee Colony Algorithm

Extracting Image Semantic Object Based on Artificial Bee Col...

引用

The second International Conference of Electrical and Electronics Engineering(ICEEE 2011)

作者： Xiao Yong-hao Chen Yong-chang Yu Wei-yu Tian Jing School of Electronic and Information Engineering South China University of Technology Provincial Key Laboratory for Computer Information Processing Technology Soochow University School of Electrical and Electronic Engineering Nanyang Technological University

In this paper, an efficient approach for extracting semantic object using artificial bee colony algorithm(ABCA) has been proposed. First, we reduce speckle noise in the image. Then fitness function of ABC algorithm is constructed, and image pixels are classified into different regions. Further semantic objects are extracted in terms of color information. The simulation results show that the color clustering via bee colony algorithm gives superior results in enhancing cluster compactness.

关键词： artificial bee colony algorithm,image semantic,image segmentation

来源：评论

学校读者我要写书评

暂无评论

HCM-EPR: A new heuristic cooperative mining model for incomplete electronic patient records

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2011年第2期5卷 257-266页

作者： Ding, Weiping Wang, Jiandong Dong, Jiancheng Zhu, Hao Guan, Zhijing School of Computer Science and Technology Nantong University Nantong 226019 China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou 215006 China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing 210016 China

In recent years, more and more techniques have been applied into electronic patient record mining in order to learn a good hypothesis to extract useful medical knowledge and assist medical experts in making the relational diagnosis. In this paper, a new heuristic cooperative mining model named HCM - EPR based on features of electronic patient record is proposed, combined with theories of particle swarm optimization and extended rough formal concept. Firstly, according to the superconcept - subconcept rough relations thresholding implied in the formal context, a new adjustable extended rough concept lattice hypothesis is constructed. Subsequently, a cooperative searching strategy of PSO is involved into the model to accelerating the searching the optimization and final ensemble hypothesis is produced. Finally, due to the values characteristics in the electronic patient record databases, the intelligent computer-aided diagnosis system of electronic patient record is designed. Some successful experiments and applications to the system show the proposed HCM - EPR model is better improvement in both accuracy and robustness for the medical knowledge mining in the electronic patient records.

关键词： Particle swarm optimization (PSO)

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：