检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Wei Xiong Bo Du Lefei Zhang Liangpei Zhang Dacheng Tao State Key Laboratory of Software Engineering School of Computer Science Wuhan University China Department of Computing The Hong Kong Polytechnic University Kowloon Hong Kong State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University China Centre for Quantum Computation & Intelligent Systems University of Technology Sydney NSW 2007 Australia

ISBN: (纸本)9781509006212

Deep networks like the convolutional neural network and its variants usually learn hierarchical features from labeled images, which is very expensive to obtain. How can we find an unsupervised way to effectively extract deep and abstract features from images without annotations? Even from large qualities of images with noise? In this paper, we propose a robust deep neural network, named as stacked convolutional denoising auto-encoders (SCDAE), which can map raw images to hierarchical representations in an unsupervised manner. Our network is elaborately designed to fit for the visual recognition tasks. It is established by stacking the denoising auto-encoders. Unlike the prior works, in the training phase, the auto-encoders are trained patch-wisely so that the latent features can be applied to powerful regularizers for better representation;in the inference phase, the denoising auto-encoders are stacked convolutionally, hence the generated feature maps in the higher layers can preserve the coherent structures within the features in the lower layers. To achieve better performance, we apply whitening to each layer to sphere the input features. Our network is evaluated on the challenging image datasets MNIST, CIFAR-10 and STL-10 and demonstrates superior performance to the state-of-the-art unsupervised networks.

关键词： Noise reduction Convolutional codes Training Feature extraction Kernel Optimized production technology Robustness

来源：评论

学校读者我要写书评

暂无评论

Parameter identification of plant growth models with stochastic development

Parameter identification of plant growth models with stochas...

引用

International Conference on Functional-Structural Plant Growth Modeling, Simulation, Visualization and Applications (FSPMA)

作者： Mengzhen Kang Jing Hua Philippe de Reffye Marc Jaeger Qingdao Academy of Intelligent Sciences Qingdao China State Key Laboratory of Management and Control for Complex Systems CASIA Beijing China AMAP Unit CIRAD Montpellier Languedoc-Roussillon FR AMAP Unit CIRAD Montpellier Languedoc-Roussillon France LIRMM ICAR University of Montpellier France

ISBN: (纸本)9781509016600

Plant architectures generally display structural variations among individuals. Stochastic FSPMs have been developed to capture such feature, but calibrating such models is a challenging issue. For GreenLab model, parameter identification has been achieved on several crops and trees, but the estimation of functional parameters is mostly limited to plants with deterministic development. In this work, we propose a methodological framework allowing the efficient FSPM parameter estimation for stochastic ramified plants. We focus on the randomness in three kinds of meristem activities in plant development: growth, death and branching. Concepts of organic series and potential structure are introduced to build the fitting target as well as corresponding model output. We show that, with a limited set of sampled plants (here from simulation), using a few organic series, the inverse method retrieves well the parameter values (the original parameter set being known here). Requiring the concept of physiological age and the assumption of common biomass pool, the proposed approach provides a solution of solving source-sink functions of complex plant architectures, with a novel simplified way of plant sampling. The proposed parameter estimation frame is promising, since this in silico process mimics the procedure of calibrating model for real plants in a stand. Estimating parameters on stochastic plant architectures opens a new range of coming applications.

关键词： Stochastic processes Biological systems Physiology Biological system modeling Computational modeling Vegetation Biomass

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Road detection algorithm for Autonomous Navigation systems based on dark channel prior and vanishing point in complex road scenes” [Robot. Auton. Syst. 85 (2016) 1–11]

引用

Robotics and Autonomous systems 2017年 88卷 202-202页

作者： Yong Li Weili Ding Xuguang Zhang Zhaojie Ju Laboratory of Pattern Recognition and Intelligent Systems Key Laboratory of Industrial Computer Control Engineering of Hebei Province Department of Automation Institute of Electrical Engineering Yanshan University Qinghuangdao Hebei 066004 China College of Information Science and Engineering Northeastern University Shenyang Liaoning 110004 China School of Computing University of Portsmouth PO1 3HE UK

来源：评论

学校读者我要写书评

暂无评论

Distributed formation stabilization for mobile agents using virtual tensegrity structures

Distributed formation stabilization for mobile agents using ...

引用

第三十四届中国控制会议

作者： YANG Qingkai CAO Ming FANG Hao CHEN Jie HUANG Jie School of Automation Beijing Institute of Technology Key Laboratory of Intelligent Control and Decision of Complex Systems Faculty of Mathematics and Natural Sciences ITM University of Groningen

ISBN: (纸本)9789881563897

This paper investigates the distributed formation control problem for a group of mobile Euler-Lagrange agents to achieve global stabilization by using virtual tensegrity structures. Firstly, a systematic approach to design tensegrity frameworks is elaborately explained to confine the interaction relationships between agents, which allows us to obtain globally rigid frameworks. Then, based on virtual tensegrity frameworks, distributed control strategies are developed such that the mobile agents converge to the desired formation globally. The theoretical analysis is further validated through simulations.

关键词： Formation stabilization,Tensegrity structure,Global convergence,Euler-Lagrange dynamics

来源：评论

学校读者我要写书评

暂无评论

Cloud computing Platform and Big Data Service for Incubator Cluster

Cloud Computing Platform and Big Data Service for Incubator ...

引用

2016年IEEE/INFORMS服务运筹、物流与信息化国际会议

作者： Gang Xiong Chi Zhang Tongkai Ji Banji Guan Aobing Sun Yuexiang Hu Timo R.Nyberg Dongguan Research Institute of CASIA Cloud Computing CenterChinese Academy of Sciences The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences School of Economic and Management Beijing University of Chemical Technology Department of Industrial Engineering and Management School of Sciences Aalto University

Hundreds of incubators get birthed worldwide every day, and many new ICT technologies developed continuously, like cloud computing and big data. Therefore, it's possible and necessary to develop a cloud computing platform that gathering a variety of data and resources information needed by thousands of incubators and millions of incubated enterprises. In this paper, after comparing three different countries incubator's management procedure, we mainly talk about the way to design a cloud-based incubator platform including its architecture, main functions, and the interface. We assume that the platform can gather and share a variety of information and resource, like money, human resource, equipment, office place and so on. So the platform is beneficial for the incubated enterprises, incubators, and the government. For example, the platform can provide individual services through big data technology. The platform can analysis the situation of incubators and warn the companies in dangerous condition with the history big data. Finally, this paper describes the use case of cloud-based incubator platform for Guangdong Province.

关键词： business incubator cluster open innovation cloud computing platform crowdsourcing big data service

来源：评论

学校读者我要写书评

暂无评论

Catch the black sheep: Unified framework for shilling attack detection based on fraudulent action propagation 24

Catch the black sheep: Unified framework for shilling attack...

引用

24th International Joint Conference on Artificial Intelligence, IJCAI 2015

作者： Zhang, Yongfeng Tan, Yunzhi Zhang, Min Liu, Yiqun Chua, Tat-Seng Ma, Shaoping State Key Laboratory of Intelligent Technology and Systems Department of Computer Science Tsinghua University Beijing100084 China School of Computing National University of Singapore Singapore117417 Singapore

ISBN: (纸本)9781577357384

Many e-commerce systems allow users to express their opinions towards products through user reviews systems. The user generated reviews not only help other users to gain a more insightful view of the products, but also help online businesses to make targeted improvements on the products or services. Besides, they compose the key component of various personalized recommender systems. However, the existence of spam user accounts in the review systems introduce unfavourable disturbances into personalized recommendation by promoting or degrading targeted items intentionally through fraudulent reviews. Previous shilling attack detection algorithms usually deal with a specific kind of attacking strategy, and are exhausted to handle with the continuously emerging new cheating methods. In this work, we propose to conduct shilling attack detection for more informed recommendation by fraudulent action propagation on the reviews themselves, without caring about the specific underlying cheating strategy, which allows us a unified and flexible framework to detect the spam users.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

BJUT at TREC 2015 Temporal Summarization Track 24

BJUT at TREC 2015 Temporal Summarization Track

引用

24th Text REtrieval Conference, TREC 2015

作者： Yao, Yingzhe Yang, Zhen Fan, Kefeng College of Computer Science Beijing University of Technology Beijing100124 China Beijing Key Laboratory of Trusted Computing Beijing100124 China National Engineering Laboratory for CTISCP Beijing100124 China Guangxi Colleges Universities Key Laboratory of cloud computing and complex systems Guilin University of Electronic Technology Guilin541004 China

In this paper, we describe our efforts for TREC Temporal Summarization Track 2015. Since this is the third time we participate in this track,we adopt a different novel method NMFR to solve the newly emerging temporal summarization problem. Our goal of this year is to evaluate the effectiveness of: (1) Considering the semantic structure of document and the manifold structure of document could be as possible to preserve the essential characteristic of the original high-dimensional space of documents during the process of feature reduction.(2)Using the non-negative matrix factorization with our semantic and manifold regularization for summarization is effective and comparable to Affinity Propagation. Finally, we conduct experiments to verify the proposed framework NMFR on TREC Temporal Summarization Track Corpus, and, as would be expected, the results demonstrate its generality and superior performance. © 2015 24th Text REtrieval Conference, TREC 2015 - Proceedings. All Rights Reserved.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Quantum State Tomography via Reduced Density Matrices

引用

Physical Review Letters 2017年第2期118卷 020401-020401页

作者： Tao Xin Dawei Lu Joel Klassen Nengkun Yu Zhengfeng Ji Jianxin Chen Xian Ma Guilu Long Bei Zeng Raymond Laflamme State Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics Tsinghua University Beijing 100084 China Institute for Quantum Computing University of Waterloo Waterloo Ontario N2L 3G1 Canada Department of Physics University of Guelph Guelph N1G 2W1 Ontario Canada Centre for Quantum Computation and Intelligent Systems Faculty of Engineering and Information Technology University of Technology Sydney New South Wales 2007 Australia Department of Mathematics and Statistics University of Guelph Guelph N1G 2W1 Ontario Canada State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences 100190 Beijing China Joint Center for Quantum Information and Computer Science University of Maryland College Park Maryland USA Department of Physics and Astronomy University of Waterloo Waterloo Ontario N2L 3G1 Canada Canadian Institute for Advanced Research Toronto M5G 1Z8 Ontario Canada Perimeter Institute for Theoretical Physics Waterloo Ontario N2L 2Y5 Canada

Quantum state tomography via local measurements is an efficient tool for characterizing quantum states. However, it requires that the original global state be uniquely determined (UD) by its local reduced density matrices (RDMs). In this work, we demonstrate for the first time a class of states that are UD by their RDMs under the assumption that the global state is pure, but fail to be UD in the absence of that assumption. This discovery allows us to classify quantum states according to their UD properties, with the requirement that each class be treated distinctly in the practice of simplifying quantum state tomography. Additionally, we experimentally test the feasibility and stability of performing quantum state tomography via the measurement of local RDMs for each class. These theoretical and experimental results demonstrate the advantages and possible pitfalls of quantum state tomography with local measurements.

关键词： Quantum entanglement Quantum information processing Quantum tomography Random matrix theory

来源：评论

学校读者我要写书评

暂无评论

Gesture recognition based on sparse representation

引用

International Journal of Wireless and Mobile computing 2016年第4期11卷 348-356页

作者： Miao, Wei Li, Gongfa Sun, Ying Jiang, Guozhang Kong, Jianyi Liu, Honghai College of Machinery and Automation Wuhan University of Science and Technology Wuhan430081 China State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China Intelligent Systems and Biomedical Robotics Group School of Computing University of Portsmouth PortsmouthPO1 3HE United Kingdom

Aiming at the problem that the robustness of gesture recognition is difficult to guarantee, this paper presents a method based on multi-features and sparse representation. Hu invariant moments and HOG features of training samples are extracted in training phase. The K-SVD algorithm is used to train the initial value of dictionary formed by two features so as to obtain two sub-dictionaries. In recognition phase, sparse coefficients of corresponding training dictionary are derived by solving minimum l1-norm. Finally, the overall reconstruction error is calculated to judge the categories of test samples. In experimental simulation, five kinds of grasp gesture are collected to create gesture sample library. After selecting optimal HOG parameters and the weight of two features, the recognition effect of the method is analysed. Compared with the commonly used classification, the results show that the method has better recognition rate and robustness. Copyright © 2016 Inderscience Enterprises Ltd.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

A co-evolutionary particle swarm optimization with dynamic topology for solving multi-objective optimization problems

Advances in Modelling and Analysis A

引用

Advances in Modelling and Analysis A 2016年第1期53卷 145-159页

作者： Wu, Daqing Tang, Lixiang Li, Haiyan Ouyang, LiJun Computer Science and Technology Institute University of South China HangyangHunan China Antai College of Economics and Management Shanghai Jiao Tong University Shanghai200240 China Zigong643000 China Key Laboratory of Guangxi High Schools for Complex System and Computational Intelligence Guangxi University for Nationalities Nanning530006 China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University HefeiAnhui Province230039 China Department of Business Administration Hunan University of Finance and Economics Hunan410205 China

This paper proposes a multi-objective with dynamic topology particle swarm optimization (PSO) algorithm for solving multi-objective problems, named DTPSO. One of the main drawbacks of classical multi-objective particle swarm optimization algorithm is low diversity. To overcome this disadvantage, DTPSO uses two dynamic local best particles to lead the search particles with multiple populations to deal with multiple objectives, and maintains diversity of new found non-dominated solutions via partitioned the searching space into fixed number of cells. The proposed DTPSO is validated through comparisons with other two multi-objective algorithms using established benchmarks and metrics. Simulation results demonstrated that DTPSO shows competitive, if not better, performance as compared to the other algorithms. © 2016, AMSE Press. All rights reserved.

关键词： Multiobjective optimization

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：