检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yiheng Zhang Dong Liu Zheng-Jun Zha CAS Key Laboratory of Technology in Geo-Spatial Information Processing and Application System University of Science and Technology of China Hefei China

ISBN: (纸本)9781509060689

Vehicle re-identification (re-id) plays an important role in the automatic analysis of the drastically increasing urban surveillance videos. Similar to the other image retrieval problems, vehicle re-id suffers from the difficulties caused by various poses of vehicles, diversified illuminations, and complicated environments. Triplet-wise training of convolutional neural network (CNN) has been studied to address these challenges, where the CNN is adopted to automate the feature extraction from images, and the training adopts triplets of (query, positive example, negative example) to capture the relative similarity between them to learn representative features. The traditional triplet-wise training is weakly constrained and thus fails to achieve satisfactory results. We propose to improve the triplet-wise training at two aspects: first, a stronger constraint namely classification-oriented loss is augmented with the original triplet loss; second, a new triplet sampling method based on pairwise images is designed. Our experimental results demonstrate the effectiveness of the proposed methods that achieve superior performance than the state-of-the-arts on two vehicle re-id datasets, which are derived from real-world urban surveillance videos.

关键词： Training Feature extraction Streaming media Videos Sampling methods Licenses Cameras

来源：评论

学校读者我要写书评

暂无评论

Association rule analysis for tour route recommendation and application to WCTSNOP

Association rule analysis for tour route recommendation and ...

引用

ISPRS Geospatial Week 2017

作者： Fang, Hui Chen, Chongcheng Lin, Jiaxiang Liu, Xianfeng Fang, Dong Laboratory of Spatial Data Mining and Information Sharing of Ministry of Education Spatial Information Research Centre of Fujian Fuzhou University District Xueyuan Road China Dept. of Computer Science Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou University District Xiyuangong Road China College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou China Fuzhou Silviscene Information Technology Co. Ltd. China

The increasing E-tourism systems provide intelligent tour recommendation for tourists. In this sense, recommender system can make personalized suggestions and provide satisfied information associated with their tour cycle. Data mining is a proper tool that extracting potential information from large database for making strategic decisions. In the study, association rule analysis based on FP-growth algorithm is applied to find the association relationship among scenic spots in different cities as tour route recommendation. In order to figure out valuable rules, Kulczynski interestingness measure is adopted and imbalance ratio is computed. The proposed scheme was evaluated on Wangluzhe cultural tourism service network operation platform (WCTSNOP), where it could verify that it is able to quick recommend tour route and to rapidly enhance the recommendation quality. © Authors 2017. CC BY 4.0 License.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Variable-numbered Multi-target Tracking Algorithm Based on Universal Track Initiation Model with Adaptive Threshold 35

Variable-numbered Multi-target Tracking Algorithm Based on U...

引用

第35届中国控制会议

作者： HUANG Dayu WANG Duo WU Shaofeng CAI Yunze Science and Technology on Avionics Integration Laboratory Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information ProcessingMinistry of Education of China

ISBN: (纸本)9781509009107

This paper firstly proposed a universal track initiation method with adaptive *** this method,performance under heavy clutter tracking environment is ***,joint probabilistic data association filter is the common data association method,which only deal with the fixed-numbered multi-target tracking *** the data pre-association process,an improved JPDAF algorithm is proposed to accomplish variable-numbered multi-target tracking,which is validated by simulation results.

关键词： Adaptive Threshold Track Initiation Variable-numbered Multi-targets Joint Probabilistic Data Association Filter

来源：评论

学校读者我要写书评

暂无评论

Randomized consensus based distributed kalman filtering over wireless sensor networks

arXiv

引用

arXiv 2018年

作者： Qin, Jiahu Wang, Jie Shi, Ling Kang, Yu Department of Automation University of Science and Technology of China Hefei230027 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong Department of Automation State Key Laboratory of Fire Science Institute of Advanced Technology University of Science and Technology of China Hefei230027 China Key Laboratory of Technology in Geo-Spatial Information Processing and Application System Chinese Academy of Sciences Beijing100190 China

This paper is concerned with developing a novel distributed Kalman filtering algorithm over wireless sensor networks based on randomized consensus strategy. Compared with centralized algorithm, distributed filtering techniques require less computation per sensor and lead to more robust estimation since they simply use the information from the neighboring nodes in the network. However, poor local sensor estimation caused by limited observability and network topology changes which interfere the global consensus are challenging issues. Motivated by this observation, we propose a novel randomized gossip based distributed Kalman filtering algorithm. information exchange and computation in the proposed algorithm can be carried out in an arbitrarily connected network of nodes. In addition, the computational burden can be distributed for a sensor which communicates with a stochastically selected neighbor at each clock step under schemes of gossip algorithm. In this case, the error covariance matrix changes stochastically at every clock step, thus the convergence is considered in a probabilistic sense. We provide the mean square convergence analysis of the proposed algorithm. Under a sufficient condition, we show that the proposed algorithm is quite appealing as it achieves better mean square error performance theoretically than the noncooperative decentralized Kalman filtering algorithm. Besides, considering the limited computation, communication and energy resources in the wireless sensor networks, we propose an optimization problem which minimizes the average expected state estimation error based on the proposed algorithm. To solve the proposed problem efficiently, we transform it into a convex optimization problem. And a sub-optimal solution is attained. Examples and simulations are provided to illustrate the theoretical results. Copyright © 2018, The Authors. All rights reserved.

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Weak value amplification via second-order correlated technique

引用

Chinese Physics B 2016年第2期25卷 58-61页

作者：崔挺黄靖正刘翔曾贵华 State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Key Laboratory on Navigation and Location-based Serviceand Center of Quantum Information Sensing and Processing Shanghai Jiao Tong University Shanghai Key Laboratory of Aerospace Intelligent Control Technology Shanghai Institute of Spaceflight Control Technology College of Information Science and Technology Northwest University

We propose a new framework combining weak measurement and second-order correlated technique. The theoretical analysis shows that weak value amplification （WVA） experiment can also be implemented by a second-order correlated system. We then build two-dimensional second-order correlated function patterns for achieving higher amplification factor and discuss the signal-to-noise ratio influence. Several advantages can be obtained by our proposal. For instance, detectors with high resolution are not necessary. Moreover, detectors with low saturation intensity are available in WVA setup. Finally, type-one technical noise can be effectively suppressed.

关键词： weak measurement two-dimensional second-order correlated function

来源：评论

学校读者我要写书评

暂无评论

Predicting essential proteins based on gene expression data, subcellular localization and PPI data 1

引用

12th International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2017

作者： Lei, Xiujuan Wang, Siguo Pan, Linqiang School of Computer Science Shaanxi Normal University Xi’anShaanxi710119 China Key Laboratory of Image Information Processing and Intelligent Control School of Automation Huazhong University of Science and Technology WuhanHubei430074 China School of Electric and Information Engineering Zhengzhou University of Light Industry ZhengzhouHenan450002 China

ISBN: (数字)9789811071799

ISBN: (纸本)9789811071782

Predicting essential proteins is indispensable for understanding the minimal requirements of cellular survival and development. In recent years, many methods combined with the topological features of PPI networks have been proposed. However, most of these approaches ignored the intrinsic characteristics of biological attributes. This paper integrates Gene expression data, Subcellular localization and PPI networks to identify essential proteins, named GSP. We use local average connectivity and edge clustering coefficient unite with gene expression data to measure centralities of nodes. Compared with non-essential proteins, essential proteins appear more frequently in some subcellular localizations such as Nucleus and considering that different compartments play different roles, thus we integrate subcellular localization information to identify essential proteins. The computational experiment results on the yeast PPI networks show that the proposed method GSP outperforms other state-of-art methods including DC, EC, IC, SC, NC, LAC, PeC, WDC and UDoNC. © Springer Nature Singapore Pte Ltd 2017.

关键词： Proteins

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Comprehensive Evaluation of Economic Performance on Thermal Power Plant Using Modified Grey Clustering 35

Fuzzy Comprehensive Evaluation of Economic Performance on Th...

引用

第35届中国控制会议

作者： HUANG Xiao Ying WANG Jing Cheng XIA Qi WANG Bo Hui Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System control and Information ProcessingMinistry of Education of China Department of Processing Business Shanghai Institute of Laser Technology

ISBN: (纸本)9781509009107

Real-time comprehensive evaluation of economic performance on thermal power plant unit is helpful to improve benefits of power *** to the complexity of power plant,this paper proposes a three-layer evaluation framework to solve the real-time economic evaluation *** top layer only has a comprehensive evaluation *** second layer is block layer with four economic blocks,in which each block is achieved by their corresponding indexes of the third *** index selection of the evaluation framework is completed with ***,this paper proposes a combined weight strategy which is based on AHP and entropy method to determine element weight of each *** for evaluation strategy,this paper proposes a modified grey clustering for block *** on grey clustering results and combined weight,an improved fuzzy comprehensive evaluation method is used to complete economic comprehensive *** real data from a1000 MW power plant is used to train and test the evaluation *** results are basically accord with real condition,which proves the effectiveness of the evaluation method.

关键词： economic evaluation grey clustering combined weight PCA fuzzy comprehensive evaluation

来源：评论

学校读者我要写书评

暂无评论

Comparison of Several Color Histogram Based Retrieval Algorithms

Comparison of Several Color Histogram Based Retrieval Algori...

引用

2016 IEEE Advanced information Management,Communicates,Electronic and Automation control Conference(IMCEC 2016)

作者： Qiuxiang Liao Wuzhou University Guangxi Colleges and University Key Laboratory of Image Processing and Intelligent Information System

ISBN: (纸本)9781509001668

As an important visual characteristic,color has been widely applied in content based image *** paper adopted the RGB color model,wherein intersection distance method,Euclidean distance method and correlation distance method based on color histogram characteristics were applied respectively in the experiments of the same sample image and the same image *** results show that the three algorithms could retrieve the sample image accurately,wherein the histogram intersection algorithm completed the retrieval most quickly;the Euclidean distance method based on simple theories can be understood easily;and the correlation distance method had the lowest recall *** experimental results have certain guidance and reference values for selecting and optimizing the content based image retrieval algorithm.

关键词： accumulative histogram histogram intersection distance euclidean distance correlation distance

来源：评论

学校读者我要写书评

暂无评论

Burden Distribution control and Optimization of Bell-less Top Blast Furnace

Burden Distribution Control and Optimization of Bell-less To...

引用

第28届中国过程控制会议（CPCC 2017）暨纪念中国过程控制会议30周年

作者： Lanzhen Li Genke Yang Changchun PAN Qingsong Gong Hongwu Wang Department of Automation and Key Laboratory of System Control and Information Processing Ministry of Education of ChinaShanghai Jiao Tong University Collaborative Innovation Center for Advanced Ship and Deep-Sea Exploration(CISSE)

Burden distribution plays an important role in ensuring the stability of blast furnace,improving the distribution of gas flow and the utilization ratio of blast furnace gas and reducing the emission of *** shape of burden surface approximately reflects the distribution of gas *** order to obtain the desired sharp charge level,we built the optimization model under two different cases that the charging angle is fixed and variable respectively,and separately use the pattern search method and genetic algorithm to solve the above optimization *** based on the research mentioned above,a burden distribution simulation software is developed to give the reliable burden distribution matrix associated with a new burden surface,which very important to the blast furnace operator.

关键词： Blast Furnace Burden Distribution Burden Surface Shape control Burden distribution matrix

来源：评论

学校读者我要写书评

暂无评论

The Topologies Research of a Soft Switching Bidirectional DC/DC Converter

The Topologies Research of a Soft Switching Bidirectional DC...

引用

Annual Conference of the IEEE Industrial Electronics Society

作者： Qi Zhang Yongping Zhang Xiangdong Sun Dong Liu Fujin Deng Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi'an China Department of Electrical Enginnering Department of Energy Technology Aalborg University Aalborg Denmark

A soft-switching solution implemented to the traditional bidirectional DC/DC converter is developed. The soft-switching cell, which composed of three auxiliary switches, one resonant capacitor and one resonant inductor, is equipped in the traditional bidirectional DC/DC converter to realize circuit ZCT or ZVT operations in both energy transmission directions. Two driving methods are presented to charging energy for different storage applications according to the storage materials' electrical characteristics. There are two methods in buck mode. The first method with low conduction losses suffers from a hard turning off process in one of the auxiliary switches, while the others experience the soft operation. As for the other method, the zero voltage or zero current transmissions in all switches are realized, however, the relative higher but fixed conduction losses are introduced by the resonant circle. And the proposed topology of bidirectional soft-switching dc-dc converter (TASBC) performs ideal soft switching at boost operations. The characteristics of the proposed converter has been verified by MATLAB simulations and experimental results.

关键词： Turning Capacitors Equivalent circuits Mathematical model Topology Soft switching Inductors

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：