检索结果-内蒙古大学图书馆

12th Conference on Computational Natural Language Learning, CoNLL 2008

作者： Wang, Hongling Wang, Honglin Zhou, Guodong Zhu, Qiaoming Jiang Su Provincial Key Lab for Computer Information Processing Technology School of Computer Science and Technology Soochow University Suzhou 215006 China

ISBN: (纸本)1905593481

This paper proposes a dependency tree-based SRL system with proper pruning and extensive feature engineering. Official evaluation on the CoNLL 2008 shared task shows that our system achieves 76.19 in lab.led macro F1 for the overall task, 84.56 in lab.led attachment score for syntactic dependencies, and 67.12 in lab.led F1 for semantic dependencies on combined test set, using the standalone MaltParser. Besides, this paper also presents our unofficial system by 1) applying a new effective pruning algorithm;2) including additional features;and 3) adopting a better dependency parser, MSTParser. Unofficial evaluation on the shared task shows that our system achieves 82.53 in lab.led macro F1, 86.39 in lab.led attachment score, and 78.64 in lab.led F1, using MSTParser on combined test set. This suggests that proper pruning and extensive feature engineering contributes much in dependency tree-based SRL. © 2008.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Approaches to image retrieval using fuzzy set theory

Approaches to image retrieval using fuzzy set theory

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Li, Yang Xuelong, Hu Jun, Pan School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Province Key Lab. for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

This paper mainly presents two approaches for image retrieval. There is some faintness in color locating in quantification boundary when image color is quantized. The membership function in fuzzy set theory can describe the fuzzy transition preferably. In this paper, the membership function in HSI color space is adopted to solve the problem above. At the same time, spatial information is integrated with color feature to describe the image content more truly. Due to the importance of texture feature, gray concurrence matrix is extracted. In the second part of this paper, retrieval scheme combining four image feature descriptors is presented, and then follows Fuzzy Hamming Distance (FHD) which is used as a fuzzy similarity measure. We have performed an experiment on a 1000 images database and our results show higher retrieval accuracy. © 2008 IEEE.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

A novel ant colony based cross-layer QoS routing algorithm for wireless mesh networks

A novel ant colony based cross-layer QoS routing algorithm f...

引用

2008 11th IEEE International Conference on Communication technology, ICCT 2008

作者： Hui, Zhang Yu-Ning, Dong Long-Xiang, Yang Hong-Bo, Zhu Jiangsu Provincial Key Lab. of Wireless Communications College of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003 China Jiangsu Provincial Key Lab. of Image Processing and Image Communication College of Communication and Information Engineering Nanjing University of Posts and Telecommunications Nanjing 210003 China

ISBN: (纸本)9781424422517

According to the heterogeneous characteristics of wireless mesh networks and the QoS requirements of multimedia applications, we design a novel QoS adaptive architecture for WMNs that is cross-domain, cross-layer and cross-node. Furthermore, this architecture is mathematically described by using a bi-level programming model. This model uses the optimization results of subnets as the optimization parameters or optimization constraints of backbone networks, and combines the features of different network domains. Based on this bi-level programming model, we propose an ant colony optimization based routing algorithm. Simulation results show that the bi-level programming model, which fully optimizes various QoS parameters of paths, can effectively adapt to the heterogeneous characteristics of WMNs so as to obtain the optimal path;the proposed routing algorithm, which has both advantages of low complexity and fast convergence speed, can converge to the theoretical optimal solution of bi-level programming model. © 2008 IEEE.

关键词： Routing algorithms

来源：评论

学校读者我要写书评

暂无评论

Video object matching based on sift algorithm

Video object matching based on sift algorithm

引用

2008 IEEE International Conference Neural Networks and Signal processing, ICNNSP

作者： Xuelong, Hu Yingcheng, Tang Zhenghua, Zhang School of Information Engineering Yangzhou University Yangzhou Jiangsu 225009 China Jiangsu Prov. Key Lab for Image Processing and Image Communication Nanjing University of Posts and Communications Nanjing Jiangsu 210003 China Jiangsu Prov. Key Lab. for Computer Information Processing Technology Suzhou University Suzhou Jiangsu 215006 China

ISBN: (纸本)9781424423118

SIFT (Scale Invariant Feature Transform) is used to solve visual tracking problem, where the appearances of the tracked object and scene background change during tracking. The implementation of this algorithm has five major stages: scale-space extrema detection;keypoint localization;orientation assignment;keypoint descriptor;keypoint matching. From the beginning frame, object is selected as the template, its SIFT features are computed. Then in the following frames, the SIFT features are computed. Euclidean distance between the object's SIFT features and the frames' SIFT features can be used to compute the accurate position of the matched object. The experimental results on real video sequences demonstrate the effectiveness of this approach and show this algorithm is of higher robustness and real-time performance. It can solve the matching problem with translation, rotation and affine distortion between images. It plays an important role in video object tracking and video object retrieval. © 2008 IEEE.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Exploring Various Features in Semantic Role lab.ling

Exploring Various Features in Semantic Role Labeling

引用

International Conference on Advanced Language processing and Web information technology (ALPIT)

作者： Hongling Wang Guodong Zhou Qiaoming Zhu Peide Qian Jiangsu Provincial Key Lab for Computer Information Processing TechnologySchool of Computer Science and Technology Soochow University Suzhou China 215006

This paper explores the contributions of various features in semantic role lab.ling. Moreover, an optimal set of features is selected using a greedy strategy. Finally, an effective headword-driven pruning algorithm is proposed to filter out irrelavant instances. Evaluation on the CoNLL'2005 SRL benchmark corpus shows that our method achieved comparable performance with the best-reported ones on a single automatic parse tree.

关键词： Training Classification algorithms Accuracy Pediatrics Support vector machines lab.ling System performance

来源：评论

学校读者我要写书评

暂无评论

Ontology-Based Deep Web Synchronous-Annotation

Ontology-Based Deep Web Synchronous-Annotation

引用

ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM

作者： PengYu Hu Wei Fang ZhiMing Cui Jiangsu Provincial Key Laboratory of Computer Information Processing Technology The Institute of Intelligent Information Processing and Application Soochow University Suzhou China

An increasing number of databases have become Web accessible through HTML form-based search interfaces, which is so-called deep Web. For full utilization of deep Web resources and improving Web intelligence, which is essential for many applications such as deep Web data collection and comparison shopping, they need to be extracted out and assigned meaningful lab.ls. In this paper, we present a synchronous-annotation approach that introduce domain ontology as a global schema ordered by Web databases to the annotation process. We combine ontology, interface schema and result schema and adopt the strategy of query ontology instance to implement annotation. In order to verify the effectiveness of the method proposed in this paper, we test on a number of different areas of Web databases. The experimental results indicate that the proposed approach is more effective than existing approaches.

关键词： Ontologies Databases Vocabulary Data mining Books Music Motion pictures

来源：评论

学校读者我要写书评

暂无评论

Tree Kernel-Based Semantic Relation Extraction Using Unified Dynamic Relation Tree

Tree Kernel-Based Semantic Relation Extraction Using Unified...

引用

International Conference on Advanced Language processing and Web information technology (ALPIT)

作者： Longhua Qian Guodong Zhou Fang Kong Qiaomin Zhu Peide Qian Jiangsu Provincial Key Laboratory for Computer Information Processing Technology School of Computer Science and Technology Soochow University Suzhou China

This paper proposes a unified dynamic relation tree (DRT) span for tree kernel-based semantic relation extraction between entity names. The basic idea is to apply a variety of linguistics-driven rules to dynamically prune out noisy information from a syntactic parse tree and include necessary contextual information. In addition, different kinds of entity-related semantic information are unified into the syntactic parse tree. Evaluation on the ACE RDC 2004 corpus shows that the unified DRT span outperforms other widely-used tree spans, and our system achieves comparable performance with the state-of-the-art kernel-based ones. This indicates that our method can not only well model the structured syntactic information but also effectively capture entity-related semantic information.

关键词： Artificial neural networks Data mining Feature extraction Kernel Cities and towns Noise measurement Joining processes

来源：评论

学校读者我要写书评

暂无评论

Implementation of data-exchanging system based on message oriented middleware in agricultural website

引用

WSEAS Transactions on computers 2008年第6期7卷 620-629页

作者： Zhang, Xiaoshuan Wu, Qinghua Tian, Dong Zhao, Ming Xiaoshuan, Zhang College of Information and Electrical Engineering China Agricultural University Beijing 100083 China Jiangsu Provincial Key Laboratory Computer Information Processing Technology Suzhou China

With the startup of the Golden Agriculture Project, the step of being-information of agriculture is becoming rapid. And the transformation and share of data is indispensable to the being-information of agriculture. How to implement data combination, data transformation and data receiving applications are the important means to complete the information share safely and enhance the efficiency. The paper starts with searching of methods to implement data interchange, and introduce some of the methods, points of the techniques, etc. Basing on this, the paper also introduces the detail requirement analyses, system design and detail implementation of the system. According to the requirement and trait of the project, a data interchange system is researched and completed. And a data interchange model based on message-oriented middleware (MOM) is presented in this paper, which builds a middleware between the province and the ministry taking part in data interchange. The system has traits as follows: 1. keeping the data safe and credible while it is transformed. 2. having excellent transplantable and applied capability. 3. doesn't need intervention of workman in the process of data interchange. 4. applying the data interchange between databases of different structure. 5. being simple to be developed and applied. MOM TongLink/Q offers interfaces for application development, and it completes the data transformation through the internet. The integration adapters developed do the data management, which are developed based on the Frame for Applications Integration TongIntegrator. This method offers a new approach to resolve the question of data interchange. Now the system has been successfully applied in the data interchange project of Ministry of Agriculture.

关键词： Electronic data interchange

来源：评论

学校读者我要写书评

暂无评论

Adaptive Shadows Detection Algorithm Based on Gaussian Mixture Model

Adaptive Shadows Detection Algorithm Based on Gaussian Mixtu...

引用

International Symposium on information Science and Engineering, ISISE

作者： Yu-jiao XiaHou Sheng-rong Gong Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China Soochow University Suzhou Jiangsu CN

This paper proposed an adaptive shadows detection algorithm based on Gaussian Mixture Model to improve the performance of video object segmentation. This method takes advantage of luminance weight to model the background of the image and obtains a primary segmentation in CIE Luv color space. In this way, it improves the real-time ability of detection. It also becomes more efficient, comparing with the existing shadow detection algorithms which often need to set the threshold manually or get them through a training process. By using the Gaussian distribution, it is able to realize an adaptive shadow detection. At same time, the authors deal with the noise or the aim points uneven distribution by using horizontal filling and vertical filling. It improves the accuracy of segmentation. The experimental results have shown that this method achieves adaptive shadows detection and has strong robustness, high segmentation accuracy.

关键词： Detection algorithms Clustering algorithms Layout Gaussian distribution Pixel Object segmentation Filling Object detection Streaming media information science

来源：评论

学校读者我要写书评

暂无评论

Data expression method in enterprise application using J2EE architecture

引用

WSEAS Transactions on Communications 2008年第6期7卷 541-550页

作者： Zhang, Xiaoshuan Chen, Peijun Zhao, Ming College of Information and Electrical Engineering China Agricultural University Qinghua Donglu 17 Haidian Beijing 100083 China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology Suzhou University Shixinjie 1 Suzhou Jiangsu 215006 China

With use of the Internet, web browser-enabled software applications are developed rapidly. Nowadays enterprises are paying more attention than ever on developing their business on the Web. The demand for rapidly delivering high quality web enabled software applications to the end users is high. The enterprise software developers are making efforts to develop the enterprise software applications that not only satisfy the business needs but also achieve the high quality within a short development process. However, the enterprise software development is normally complicated. For example, factors like the different enterprise environment, the critical business demand, the lack of knowledge and experience from the developers and so on can make the enterprise software development become rather hard work. Under such circumstances, something is needed to simplify the enterprise software development and also enable the sharing of the knowledge and experiences among the different developers. J2EE architecture is becoming the mainstream framework to develop the more complex enterprise application. The important problem arises, which is how to manage to each layer in J2EE and control the interior business data and the customer data, given that J2EE architecture has many complicated layers. There is respective data presentation in relevant layer of J2EE, with strictly rules to access and transform data objects between these layers. This paper adopts the case study method to discuss the data expression of J2EE and the detailed data expressing methods in corresponding layer with some instances. According to the Facade pattern of J2EE, it should control the access to data persistence layer seriously to protect important enterprise data and avoid showing database pattern to client directly. The data persistence layer hides behind the business logic layer and provide business interfaces via the business logic layer to communicate with the presentation layer to package the data persis

关键词： Enterprise software

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：