检索结果-内蒙古大学图书馆

2019 IEEE International Conference on Signal, information and Data processing, ICSIDP 2019

作者： Duan, Chenhui Tang, Linbo Li, Chen Wu, Chen Li, Cheng Zhao, Baojun Radar Research Lab School of Information and Electronics Beijing Institute of Technology Beijing100081 China Beijing Key Laboratory of Embedded Real-Time Information Processing Technology Beijing100081 China School of Computer Science North China University of Technology Beijing100144 China

ISBN: (纸本)9781728123455

With the rapid advancement of optical remote sensing (RS) satellites, RS video has replaced RS image as the main way to obtain information in orbit environment. However, the storage and transmission of on-orbit RS video faces enormous challenges: the contradiction between limited power, space and bandwidth and massive video data volume is becoming increasingly acute. To solve this problem, this paper proposes an effective implementation of spaceborne real-time RS video compression based on CPU+GPU heterogeneous framework. First, we propose a new rate control method based on HEVC for on-orbit RS video compression, which allocates less bitrate for low complexity code blocks (CBs) and more bitrate for high complexity CBs, which can improve the accuracy of rate control algorithm while ensuring compression quality. Then this paper makes full use of the CPU + GPU heterogeneous framework to speed up the whole compression processing. The experimental results show that the proposed compression framework realizes 200x real-time compression of 1080p spaceborne RS video with a PSNR greater than 38.7 dB. © 2019 IEEE.

关键词： Orbits

来源：评论

学校读者我要写书评

暂无评论

Multivariate classification of deep web sources based on maximum entropy model

引用

Journal of Computational information Systems 2008年第3期4卷 1093-1100页

作者： Huang, Li Zhao, Pengpeng Cui, Zhiming Wei, Fang Institute of Intelligent Information Processing and Application Soochow University Suzhou 215006 China Jiangsu Key Laboratory of Computer Information Processing Technology Soochow University Suzhou 215006 China

With the fast development of World Wide Web, the quantity of web information is increasing in an unprecedented pace, a great many of which are generated dynamically from background databases, and can't be indexed by traditional search engine, so we call them Deep Web. For the heterogeneous and dynamic features of Deep Web sources, classifying the Deep Web source by domain effectively is a significant precondition of Deep Web sources integration. In this paper, we consider the visible features of Deep Web and Maximum Entropy approach, and then on the basis of binary classification, we propose a new multivariate classification approach based on Maximum Entropy towards Deep Web sources. In addition, we propose a Feedback algorithm to improve the accuracy of classification. An experimental evaluation over real Web data shows that, our approach could provide an effective and general solution to the multivariate classification of Deep Web sources.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Improved MFCC feature extraction combining symmetric ICA algorithm for robust speech recognition

引用

Journal of Multimedia 2012年第1期7卷 74-81页

作者： Zhao, Huan Zhao, Kai Liu, He Yu, Fei School of Information Science and Engineering Hunan University Changsha China Jiangsu Provincial Key Laboratory of Computer Information Processing Technology Suzhou China

Independent component analysis (ICA), instead of the traditional discrete cosine transform (DCT), is often used to project log Mel spectrum in robust speech feature extraction. The paper proposed using symmetric orthogonalization in ICA for projecting log Mel spectrum into a new feature space as a substitute in extracting speech features to solve the problem of cumulative error and unequal weights that deflation orthogonalization brings, so as to improve the robustness of speech recognition systems, and increase the efficiency of estimation at the same time. Furthermore, the paper studied the nonlinearities of the objective function in ICA and their coefficients, tested them in all kinds of environments, finding that they influenced the recognition rate greatly in speech recognition systems, and applied a new coefficient in the proposed method. Experiments based on HMM and Aurora-2 speech corpus suggested that the new method was superior to deflation- based ICA and MFCC. © 2012 ACADEMY PUBLISHER.

关键词： Feature extraction

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

Extracting Protein-Protein Interaction from Biomedical Text Using Additional Shallow Parsing information

Extracting Protein-Protein Interaction from Biomedical Text ...

引用

International Conference on BioMedical Engineering and Informatics (BMEI)

作者： Huanhuan Yu Longhua Qian Guodong Zhou Qiaoming Zhu Jiangsu Provincial Key Laboratory of Computer Information Processing Technology School of Computer Science and Technology Soochow University Suzhou China

This paper explores protein-protein interaction extraction from biomedical literature using support vector machines (SVM). Besides common lexical features, various overlap features and base phrase chunking information are used to improve the performance. Evaluation on the AIMed corpus shows that our feature-based method achieves very encouraging performances of 68.6 and 51.0 in F-measure with 10-fold pair-wise cross-validation and 10-fold document-wise cross-validation respectively, which are comparable with other state-of-the-art feature-based methods.

关键词： Data mining Proteins Kernel Support vector machines Biomedical computing Feature extraction Paper technology Birth disorders information processing computer science

来源：评论

学校读者我要写书评

暂无评论

Towards Termination Criteria of Ant Colony Optimization

Towards Termination Criteria of Ant Colony Optimization

引用

International Conference on Natural Computation (ICNC)

作者： Qiang Lv Xiaoyan Xia School of Computer Science and Technology Suzhou University Suzhou Jiangsu China Provincial Key Laboratory Computer Information Processing Technology Suzhou Jiangsu China

Ant colony optimization (ACO for short) has been proved a successful meta-heuristic by a huge of empirical studies. This paper discusses the termination criteria of ACO and therefore provides research ideas to other meta-heuristics. A general discussion about four types of termination criteria has been firstly discussed in this article. Then some measures of convergence based on pheromone have been introduced. And a new termination criterion based on Bayesian approach is presented. Finally a new convergence proof for a class of ACO algorithms is presented.

关键词： Ant colony optimization Convergence Space exploration Algorithm design and analysis Upper bound Bayesian methods computer science information processing Stochastic processes Physics computing

来源：评论

学校读者我要写书评

暂无评论

Topic-Driven Multi-document Summarization

Topic-Driven Multi-document Summarization

引用

International Conference on Asian Language processing (IALP)

作者： Hongling Wang Guodong Zhou Jiangsu Provincial Key Laboratory of Computer Information Processing Technology School of Computer Science and Technology Soochow University Suzhou China

This paper presents a topic-driven framework for generating a generic summary from multi-documents. Our approach is based on the intuition that, from the statistical point of view, the summary's probability distribution over the topics should be consistent with the multi-documents' probability distribution over the inherent topics. Here, the topics are defined as weighted “bag-of-words” and derived by Latent Dirichlet Allocation from a collection of documents, either the given multi-documents or a related large-scale corpus. In this sense, we could represent various kinds of text units, such as word, sentence, summary, document and multi-documents, using a single vector space model via their corresponding probability distributions over the derived topics. Therefore, we are able to extract a sentence or summary by calculating the similarity between a sentence/summary and the given multi-documents via their topic probability distributions. In particular, we propose two methods in similarity measurement: the static method and the dynamic method. While the former is employed to detect the salience of information in a static way, the later further controls redundancy in a dynamic way. In addition, we integrate various popular features to improve the performance. Evaluation on the TAC 2008 update summarization task shows encouraging results.

关键词： Probability distribution Redundancy Semantics Strontium Resource management Mathematical model

来源：评论

学校读者我要写书评

暂无评论

Research on remote heterogeneous disaster recovery technology in grid computing security

Research on remote heterogeneous disaster recovery technolog...

引用

2006 2nd International Conference on Semantics Knowledge and Grid, SKG

作者： Wu, Ronghui Li, Renfa Yu, Fei Yue, Guangxue Wen, Jigang School of Computer and Communication Hunan University Changsha 410082 China State Key Laboratory for Novel Software Technology Nanjing University Nanjing 210093 China Provincial Key Laboratory of Computer Information Processing Technology Jiangsu Province Suzhou University Suzhou 150063 China College of Informationg Engineering JiaXing University JiaXing 314000 China

ISBN: (纸本)0769532055

The tradition standby mechanism can't carry out the dynamic Disaster Recovery of database between distributed isomeric storage systems, accordingly, research the method of allopatric isomeric backup based on grid calculation is an important research subject. In this paper, some technique and strategy of allopatric isomeric backup in grid calculation environment are researched by comparing and analyzing the existing technique of database allopatric backup, a remote-data copy method is presented, a remote-data disaster dump system and a allopatric isomeric data Disaster Recovery tool are designed and implemented based on interlaver. © 2006 IEEE.

关键词： Middleware

来源：评论

学校读者我要写书评

暂无评论

DUSA-UNet: Dual Sparse Attentive U-Net for Multiscale Road Network Extraction

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Song, Jie Sun, Yue Cai, Ziyun Xiao, Liang Huang, Yawen Zheng, Yefeng Nanjing University of Posts and Telecommunications College of Automation College of Artificial Intelligence Nanjing210023 China Nanjing University of Science and Technology School of Computer Science and Engineering Nanjing210094 China Nanjing University of Science and Technology Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing210094 China Nanjing University of Science and Technology Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense Nanjing210094 China Tencent YouTu Lab Jarvis Research Center Shenzhen518057 China

The challenges of road network segmentation demand an algorithm capable of adapting to the sparse and irregular shapes, as well as the diverse context, which often leads traditional encoding-decoding methods and simple Transformer embeddings to failure. We introduce a computationally efficient and powerful framework for elegant road-aware segmentation. Our method, called DUSA-UNet, effectively encodes fine-grained local road connectivity and holistic global topological semantics while decoding multiscale road network information. DUSA-UNet offers a novel alternative to the U-Net architecture by integrating connectivity attention, which can exploit intra-road interactions across multi-level sampling features with reduced computational complexity. This local interaction serves as valuable prior information for learning global interactions between road networks and the background through another integrality attention mechanism. The two forms of sparse attention are arranged alternatively and complementarily, and trained jointly, resulting in performance improvements without significant increases in computational complexity. Extensive experiments on various datasets with different resolutions, including Massachusetts, DeepGlobe, SpaceNet, and Large-Scale remote sensing images, demonstrate that DUSA-UNet outperforms state-of-the-art techniques. Our approach represents a significant advancement in the field of road network extraction, providing a computationally feasible solution that achieves high-quality segmentation results. © 1980-2012 IEEE.

关键词： NP-hard

来源：评论

学校读者我要写书评

暂无评论

MMLUP: Multi-Source & Multi-Task Learning for User Profiles in Social Network

引用

computers, Materials & Continua 2019年第9期61卷 1105-1115页

作者： Dongjie Zhu Yuhua Wang Chuiju You Jinming Qiu Ning Cao Chenjing Gong Guohua Yang Helen Min Zhou School of Computer Science and Technology Harbin Institute of TechnologyWeihai264209China College of Information Engineering Sanming University365004SanmingChina Fujian Province University Key Lab for Industry Big Data Analysis and Application FujianChina College of Information Engineering Qingdao Binhai UniversityQingdaoChina Jiangsu Province Wireless Sensing System Application Engneering Technology Research and Development Centre China School of Engineering Manukau Institute of TechnologyAuckland2241New Zealand

With the rapid development of the mobile Internet,users generate massive data in different forms in social network every day,and different characteristics of users are reflected by these social media *** to integrate multiple heterogeneous information and establish user profiles from multiple perspectives plays an important role in providing personalized services,marketing,and recommendation *** this paper,we propose Multi-source&Multi-task Learning for User Profiles in Social Network which integrates multiple social data sources and contains a multi-task learning framework to simultaneously predict various attributes of a ***,we design their own feature extraction models for multiple heterogeneous data ***,we design a shared layer to fuse multiple heterogeneous data sources as general shared representation for multi-task ***,we design each task’s own unique presentation layer for discriminant output of ***,we design a weighted loss function to improve the learning efficiency and prediction accuracy of each *** experimental results on more than 5000 Sina Weibo users demonstrate that our approach outperforms state-of-the-art baselines for inferring gender,age and region of social media users.

关键词： User profiles multi-source multi-task learning social network

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：