检索结果-内蒙古大学图书馆

International Joint Conference on Neural Networks

作者： Nengwen Zhao Lefei Zhang Bo Du Liangpei Zhang Dacheng Tao Jane You State Key Laboratory of Software Engineering School of Computer Wuhan University Department of Computing The Hong Kong Polytechnic University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Centre for Quantum Computation & Intelligent Systems and the Faculty of Engineering and Information Technology University of Technology

ISBN: (纸本)9781509006212

Gait recognition is a rising biometric technology which aims to distinguish people purely through the analysis of the way they walk, while the problem is that the dimensionality of the gait data is too high, so it is necessary to carry on dimensionality reduction task. Up to date, in the area of computer vision and pattern recognition, various dimensionality reduction algorithms have been employed for gait data, including the conventional vector representation based methods principal components analysis (PCA) and, locality preserving projection (LPP), and the recently proposed multi-linear subspace learning based approaches such as multilinear principal component analysis (MPCA). In this paper, inspired by the advantages of the tensor representation and manifold learning, we propose a novel sparse tensor discriminative locality alignment for human gait feature representation and dimensionality reduction algorithm, and sub-sequently apply the refined feature for gait recognition by a lazy classifier of the KNN. The proposed method adopts sparse multi-way projection based on the high-order version of discriminative locality alignment, by which the class separability is enhanced and the potential model overfitting is simultaneously avoided. Extensive experiments on the University of South Florida (USF) HumanID Gait Database show that the proposed method achieves better recognition rate compared with some existing classical dimensionality reduction algorithms.

关键词： Gait recognition dimensionality reduction images computer vision Tensor Locomotion Gait principal components analysis vector representation Alignment

来源：评论

学校读者我要写书评

暂无评论

Editorial A Broader Coverage of the IEEE Education Society IEEE-RITA Electronic Journal: Latin American and Caribbean Consortium of engineering Institutions (LACCEI) Collaboration

引用

Revista Iberoamericana de Tecnologias del Aprendizaje 2015年第3期10卷 100-101页

作者： Castro, Manuel Tovar, Edmundo Esparragorza, Ivan E. Petrie, Maria M. Larrondo Department of Electrical and Computer Engineering Spanish University for Distance Education Madrid Spain Department of Languages and Computer Systems and Software Engineering Technical University of Madrid Madrid Spain Penn State University MediaPA United States Department of Computer Engineering Florida Atlantic University Boca RatonFL United States

This editorial introduces the first selection of papers in IEEE-RITA from the LACCEI annual conference held in 2014. It publishes a view of the LACCEI coverage of issues and topics inside their engineering coverage of... 详细信息

关键词： Special issues and sections Meetings IEEE Education Society engineering education

来源：评论

学校读者我要写书评

暂无评论

Using decision rules for solving conflicts in extended feature models 8

Using decision rules for solving conflicts in extended featu...

引用

8th ACM SIGPLAN International Conference on software Language engineering, SLE 2015

作者： Ochoa, Lina González-Rojas, Oscar Thüm, Thomas Systems and Computing Engineering Department School of Engineering Universidad de Los Andes Bogotá Colombia Institute of Software Engineering and Automotive Informatics Technische Universität Braunschweig Brunswick Germany

ISBN: (纸本)9781450336864

software Product Line engineering has introduced feature modeling as a domain analysis technique used to represent the variability of software products and decision-making scenarios. We present a model-based transformation approach to solve conflicts among configurations performed by different stakeholders on feature models. We propose the usage of a domain-specific language named CoCo to specify attributes as non-functional properties of features, and to describe busineb-related decision rules in terms of costs, time, and human resources. These specifications along with the stakeholders' configurations and the feature model are transformed into a constraint programming problem, on which decision rules are executed to find a non-conflicting set of solution configurations that are aligned to busineb objectives. We evaluate CoCo's compositionality and model complexity simplification while using a set of motivating decision scenarios. © 2015 ACM.

关键词： Constraint satisfaction problems

来源：评论

学校读者我要写书评

暂无评论

Mobile application testing in industrial contexts: An exploratory multiple case-study 1

引用

14th International Conference on New Trends in Intelligent software Methodology, Tools, and Techniques, SoMeT 2015

作者： Zein, Samer Salleh, Norsaremah Grundy, John Department of Computer Science International Islamic University Kuala Lumpur Malaysia Centre for Computing and Engineering Software Systems Swinburne University of Technology Melbourne Australia

ISBN: (数字)9783319226897

ISBN: (纸本)9783319226880

Recent empirical studies in the area of mobile application testing indicate the need for specific testing techniques and methods for mobile applications. This is due to mobile applications being significantly different than traditional web and desktop applications, particularly in terms of the physical constraints of mobile devices and the very different features of their operating systems. In this paper, we presented a multiple case-study involving four software development companies in the area of mobile and smartphones application. We aimed to identify testing techniques currently being applied by developers and challenges that they are facing. Our principle results are that many industrial teams seem to lack sufficient knowledge on how to test mobile applications, particularly in the areas of mobile application life-cycle conformance, context-awareness, and integration testing. We also found that there is no formal testing approach or methodology that can facilitate a development team to systematically test a critical mobile application. © Springer International Publishing Switzerland 2015.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

Quantum state and process tomography via adaptive measurements

引用

Science China(Physics,Mechanics & Astronomy) 2016年第10期59卷 25-32页

作者： HengYan Wang WenQiang Zheng NengKun Yu KeRen Li DaWei Lu Tao Xin Carson Li ZhengFeng Ji David Kribs Bei Zeng XinHua Peng JiangFeng Du Hefei National Laboratory for Physical Sciences at Microscale and Department of Modern Physics University of Science and Technology of ChinaHefei 230026China Department of Applied Physics Zhejiang University of TechnologyHangzhou 310023China Institute for Quantum Computing University of WaterlooWaterloo N2L 3G1Canada 4Department of Mathematics&Statistics University of GuelphGuelph N1G 2W1Canada Centre for Quantum Computation&Intelligent Systems Faculty of Engineering and Information TechnologyUniversity of Technology SydneySydney NSW 2007Australia State Key Laboratory of Low-Dimensional Quantum Physics and Department of Physics Tsinghua UniversityBeijing 100084China Department of Physics University of GuelphGuelph N1G 2W1Canada State Key Laboratory of Computer Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China Canadian Institute for Advanced Research Toronto M5G 1Z8Canada

We investigate quantum state tomography(QST) for pure states and quantum process tomography(QPT) for unitary channels via adaptive measurements. For a quantum system with a d-dimensional Hilbert space, we first propose an adaptive protocol where only 2d. 1 measurement outcomes are used to accomplish the QST for all pure states. This idea is then extended to study QPT for unitary channels, where an adaptive unitary process tomography(AUPT) protocol of d2+d.1measurement outcomes is constructed for any unitary channel. We experimentally implement the AUPT protocol in a 2-qubit nuclear magnetic resonance system. We examine the performance of the AUPT protocol when applied to Hadamard gate, T gate(/8 phase gate), and controlled-NOT gate,respectively, as these gates form the universal gate set for quantum information processing purpose. As a comparison, standard QPT is also implemented for each gate. Our experimental results show that the AUPT protocol that reconstructing unitary channels via adaptive measurements significantly reduce the number of experiments required by standard QPT without considerable loss of fidelity.

关键词： quantum tomography state reconstruction nuclear magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Regularizing Deep Convolutional Neural Networks with a Structured Decorrelation Constraint

Regularizing Deep Convolutional Neural Networks with a Struc...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Wei Xiong Bo Du Lefei Zhang Ruimin Hu Dacheng Tao Computer School of Wuhan University National Engineering Research Center for Multimedia Software Wuhan China Collaborative Innovation Center of Geospatial Technology China Department of Computing The Hong Kong Polytechnic University Hong Kong China National Engineering Research Center for Multimedia Software Computer School of Wuhan University China Centre for Quantum Computation & Intelligent Systems University of Technology Sydney NSW Australia

ISBN: (纸本)9781509054749

Deep convolutional networks have achieved successful performance in data mining field. However, training large networks still remains a challenge, as the training data may be insufficient and the model can easily get overfitted. Hence the training process is usually combined with a model regularization. Typical regularizers include weight decay, Dropout, etc. In this paper, we propose a novel regularizer, named Structured Decorrelation Constraint (SDC), which is applied to the activations of the hidden layers to prevent overfitting and achieve better generalization. SDC impels the network to learn structured representations by grouping the hidden units and encouraging the units within the same group to have strong connections during the training procedure. Meanwhile, it forces the units in different groups to learn non-redundant representations by minimizing the cross-covariance between them. Compared with Dropout, SDC reduces the co-adaptions between the hidden units in an explicit way. Besides, we propose a novel approach called Reg-Conv that can help SDC to regularize the complex convolutional layers. Experiments on extensive datasets show that SDC significantly reduces overfitting and yields very meaningful improvements on classification performance (on CIFAR-10 6.22% accuracy promotion and on CIFAR-100 9.63% promotion).

关键词： Neurons Correlation Decorrelation Training Data models Electronic mail Biological neural networks

来源：评论

学校读者我要写书评

暂无评论

Omnidirectional chargability with directional antennas

Omnidirectional chargability with directional antennas

引用

International Conference on Network Protocols

作者： Haipeng Dai Xiaoyu Wang Alex X. Liu Fengmin Zhang Yang Zhao Guihai Chen State Key Laboratory for Novel Software Technology Nanjing University Nanjing Jiangsu CHINA Department of Computer Science and Engineering Michigan State University East Lansing MI USA Shanghai key Laboratory of Scalable Computing and Systems Shanghai Jiao Tong University Shanghai CHINA

ISBN: (纸本)9781509032822

Wireless Power Transfer (WPT) has received more and more attentions because of its convenience and reliability. In this paper, we first propose the notion of omnidirectional charging by which an area is omnidirectionally charged if a device with directional antennas at any position in the area with any orientation can be charged by directional chargers with power being no smaller than a given threshold. We present our empirical charging model based on field experimental results using off-the-shelf WPT products. Next, we consider the problem of detecting whether the target area achieves omnidirectional charging given a deterministic deployment of chargers. We develop piecewise constant approximation and area discretization techniques to partition the target area into subareas and approximate powers from chargers as constants. Then we propose the Minimum Coverage Set extraction technique which reduces the continuous search space to a discrete one and thereby allows a fast detection algorithm. Moreover, we consider the problem of determining the probability that the target area achieves omnidirectional charging given a random deployment of chargers. We first replace the target area by grid points on triangular lattices to reduce the search space from infinite to finite, then approximate chargers' power with reasonable relaxation, and derive an upper bound of the omnidirectional charging probability. Finally, we conduct both simulation and field experiments, and the results show that our algorithm outperforms comparison algorithms by at least 120%, and the consistency degree of our theoretical results and field experimental results is larger than 93.6%.

关键词： Wireless sensor networks Wireless communication Directional antennas Adaptation models Joining processes Conferences Protocols

来源：评论

学校读者我要写书评

暂无评论

A separability-entanglement classifier via machine learning

arXiv

引用

arXiv 2017年

作者： Lu, Sirui Huang, Shilin Li, Keren Li, Jun Chen, Jianxin Lu, Dawei Ji, Zhengfeng Shen, Yi Zhou, Duanlu Zeng, Bei Department of Physics Tsinghua University Beijing100084 China Institute for Quantum Computing University of Waterloo WaterlooONN2L 3G1 Canada Institute for Interdisciplinary Information Sciences Tsinghua University Beijing100084 China Beijing Computational Science Research Center Beijing100193 China Department of Mathematics & Statistics University of Guelph GuelphONN1G 2W1 Canada Joint Center for Quantum Information and Computer Science University of Maryland College ParkMD United States Department of Physics Southern University of Science and Technology Shenzhen518055 China Centre for Quantum Computation & Intelligent Systems School of Software Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China Department of Statistics and Actuarial Science University of Waterloo WaterlooONN2L 3G1 Canada Institute of Physics Chinese Academy of Sciences Beijing100190 China

The problem of determining whether a given quantum state is entangled lies at the heart of quantum information processing, which is known to be an NP-hard problem in general. Despite the proposed many methods such as the positive partial transpose (PPT) criterion and the k-symmetric extendibility criterion to tackle this problem in practice, none of them enables a general, effective solution to the problem even for small dimensions. Explicitly, separable states form a high-dimensional convex set, which exhibits a vastly complicated structure. In this work, we build a new separability-entanglement classifier underpinned by machine learning techniques. Our method outperforms the existing methods in generic cases in terms of both speed and accuracy, opening up the avenues to explore quantum entanglement via the machine learning approach. Copyright © 2017, The Authors. All rights reserved.

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

An assessment of search-based techniques for reverse engineering feature models

An assessment of search-based techniques for reverse enginee...

引用

作者： Lopez-Herrejon, Roberto E. Linsbauer, Lukas Galindo, José A. Parejo, José A. Benavides, David Segura, Sergio Egyed, Alexander Institute for Software Systems Engineering Johannes Kepler University Linz Altenbergerstr. 69 Linz4040 Austria Department of Computer Languages and Systems University of Seville Av Reina Mercedes S/N Seville41012 Spain

Successful software evolves from a single system by adding and changing functionality to keep up with users' demands and to cater to their similar and different requirements. Nowadays it is a common practice to offer a system in many variants such as community, professional, or academic editions. Each variant provides different functionality described in terms of features. software Product Line engineering (SPLE) is an effective software development paradigm for this scenario. At the core of SPLE is variability modelling whose goal is to represent the combinations of features that distinguish the system variants using feature models, the de facto standard for such task. As SPLE practices are becoming more pervasive, reverse engineering feature models from the feature descriptions of each individual variant has become an active research subject. In this paper we evaluated, for this reverse engineering task, three standard search based techniques (evolutionary algorithms, hill climbing, and random search) with two objective functions on 74 SPLs. We compared their performance using precision and recall, and found a clear trade-off between these two metrics which we further reified into a third objective function based on Fβ, an information retrieval measure, that showed a clear performance improvement. We believe that this work sheds light on the great potential of search-based techniques for SPLE tasks. © 2014 Elsevier Inc. All rights reserved.

关键词： Reverse engineering

来源：评论

学校读者我要写书评

暂无评论

Denoising Auto-Encoders toward Robust Unsupervised Feature Representation

Denoising Auto-Encoders toward Robust Unsupervised Feature R...

引用

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

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：