检索结果-内蒙古大学图书馆

Robust frequent directions with application in online learning

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Luo, Luo Chen, Cheng Zhang, Zhihua Li, Wu-Jun Zhang, Tong Department of Computer Science and Engineering Shanghai Jiao Tong University 800 Dongchuan Road Shanghai200240 China National Engineering Lab for Big Data Analysis and Applications School of Mathematical Sciences Peking University 5 Yiheyuan Road Beijing100871 China National Key Laboratory for Novel Software Technology Collaborative Innovation Center of Novel Software Technology and Industrialization Department of Computer Science and Technology Nanjing University 163 Xianlin Avenue Nanjing210023 China Computer Science & Mathematics Hong Kong University of Science and Technology Hong Kong

The frequent directions (FD) technique is a deterministic approach for online sketching that has many applications in machine learning. The conventional FD is a heuristic procedure that often outputs rank deficient matrices. To overcome the rank deficiency problem, we propose a new sketching strategy called robust frequent directions (RFD) by introducing a regularization term. RFD can be derived from an optimization problem. It updates the sketch matrix and the regularization term adaptively and jointly. RFD reduces the approximation error of FD without increasing the computational cost. We also apply RFD to online learning and propose an effective hyperparameter-free online Newton algorithm. We derive a regret bound for our online Newton algorithm based on RFD, which guarantees the robustness of the algorithm. The experimental studies demonstrate that the proposed method outperforms state-of-the-art second order online learning algorithms. Copyright © 2017, The Authors. All rights reserved.

关键词： Heuristic methods

Person re-identification by camera correlation aware feature augmentation

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Chen, Ying-Cong Zhu, Xiatian Zheng, Wei-Shi Lai, Jian-Huang School of Data and Computer Science Sun Yat-sen University Guangzhou510275 China Collaborative Innovation Center of High Performance Computing National University of Defense Technology Changsha410073 China Department of Computer Science and Engineering Chinese University of Hong Kong School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom Key Laboratory of Machine Intelligence and Advanced Computing Sun Yatsen University Ministry of Education China Guangdong Province Key Laboratory of Information Security China

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coRrelation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT. We conducted extensively comparative experiments to validate the superiority and advantages of our proposed framework over state-of

关键词： Cameras

Use of information technologies to explore correlations between climatic factors and spontaneous intracerebral hemorrhage in different age groups

学校读者我要写书评

暂无评论

Journal of Computing science and engineering 2017年第4期11卷 142-151页

作者： Ting, Hsien-Wei Chan, Chien-Lung Pan, Ren-Hao Lai, Robert K. Chien, Ting-Ying Department of Neurosurgery Taipei Hospital Ministry of Health and Welfare New Taipei City Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Department of Information Management Yuan Ze University Taoyuan City Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan Department of Information Management Tunghai University Taichung City Taiwan

Spontaneous intracerebral hemorrhage (sICH) has a high mortality rate. Research has demonstrated that sICH occurrence is related to weather conditions;therefore, this study used the decision tree method to explore the impact of climatic risk factors on sICH at different ages. The Taiwan National Health Insurance Research database (NHIRD) and other open-access data were used in this study. The inclusion criterion was a first-attack sICH. The decision tree algorithm and random forest were implemented in R programming language. We defined a high risk of sICH as more than the average number of cases daily, and the younger, middle-aged and older groups were calculated as having 0.77, 2.26 and 2.60 cases per day, respectively. In total, 22,684 sICH cases were included in this study;3,102 patients were younger ( 65 years, older group). The risk of sICH in the younger group was not correlated with temperature, wind speed or humidity. Themiddle group had two decision nodes: a higher risk if the maximum temperature was > 19°C (probability = 63.7%), and if the maximum temperature was 23.933°C (probability = 60.7%). This study demonstrated that the sICH incidence in the younger patients was not significantly correlated with weather factors;that in the middle-aged sICH patients was highly-correlated with the apparent temperature;and that in the older sICH patients was highly-correlated with the mean ambient temperature. "Warm" cold ambient temperatures resulted in a higher risk of sICH, especially in the older patients. © 2017. The Korean Institute of Information Scientists and Engineers.

关键词： Decision trees

Building Chinese affective resources in valence-arousal dimensions 15

学校读者我要写书评

暂无评论

Building Chinese affective resources in valence-arousal dime...

15th Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2016

作者： Yu, Liang-Chih Lee, Lung-Hao Hao, Shuai Wang, Jin He, Yunchao Hu, Jun Lai, K. Robert Zhang, Xuejie Department of Information Management Yuan Ze University Taiwan Department of Computer Science and Engineering Yuan Ze University Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taiwan Information Technology Center National Taiwan Normal University Taiwan School of Software Nanchang University Jiangxi China School of Information Science and Engineering Yunnan University Yunnan China

ISBN: (纸本)9781941643914

An increasing amount of research has recently focused on representing affective states as continuous numerical values on multiple dimensions, such as the valence-arousal (VA) space. Compared to the categorical approach that represents affective states as several classes (e.g., positive and negative), the dimensional approach can provide more fine-grained sentiment analysis. However, affective resources with valence-arousal ratings are still very rare, especially for the Chinese language. Therefore, this study builds 1) an affective lexicon called Chinese valence-arousal words (CVAW) containing 1,653 words, and 2) an affective corpus called Chinese valence-arousal text (CVAT) containing 2,009 sentences extracted from web texts. To improve the annotation quality, a corpus cleanup procedure is used to remove outlier ratings and improper texts. Experiments using CVAW words to predict the VA ratings of the CVAT corpus show results comparable to those obtained using English affective resources. ©2016 Association for Computational Linguistics.

关键词： Sentiment analysis

Optimal Estimation of Sensor Biases for Asynchronous Multi-Sensor data Fusion

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Pu, Wenqiang Liu, Ya-Feng Yan, Junkun Liu, Hongwei Luo, Zhi-Quan National Laboratory of Radar Signal Processing Collaborative Innovation Center of Information Sensing and Understanding Xidian University Xi'an710071 China State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China Shenzhen Research Institute of Big Data Chinese University of Hong Kong Shenzhen518100 China

An important step in a multi-sensor surveillance system is to estimate sensor biases from their noisy asynchronous measurements. This estimation problem is computationally challenging due to the highly nonlinear transformation between the global and local coordinate systems as well as the measurement asynchrony from different sensors. In this paper, we propose a novel nonlinear least squares (LS) formulation for the problem by assuming the existence of a reference target moving with an (unknown) constant velocity. We also propose an efficient block coordinate decent (BCD) optimization algorithm, with a judicious initialization, to solve the problem. The proposed BCD algorithm alternately updates the range and azimuth bias estimates by solving linear least squares problems and semidefinite programs (SDPs). In the absence of measurement noise, the proposed algorithm is guaranteed to find the global solution of the problem and the true biases. Simulation results show that the proposed algorithm significantly outperforms the existing approaches in terms of the root mean square error (RMSE). Copyright © 2017, The Authors. All rights reserved.

关键词： Mean square error

Opinion diversity and community formation in adaptive networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Yu, Yi Xiao, Gaoxi Li, Guoqi Tay, Wee Peng Teoh, Hao Fatt Data Science Innovation Hub Merck Sharp & Dohme 1 Fusionopolis Way 138632 Singapore School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore Complexity Institute Nanyang Technological University 50 Nanyang Avenue Singapore Center for Brain Inspired Computing Research Department of Precision Instrument Tsinghua University Beijing China

It is interesting and of significant importance to investigate how network structures co-evolve with opinions. The existing models of such co-evolution typically predict that network nodes either reach a global consensus or break into separated communities, each of which has its own community consensus. Such results, however, cannot explain the richness of real-life opinions, which are typically diversified with no global or even community consensus. In addition, people seldom, if not never, totally cut themselves off from dissenters. In this article, we show that, a simple model integrating consensus formation, link rewiring and opinion change allows complex system dynamics to emerge, driving the system into a dynamic equilibrium with co-existence of diversified opinions. Specifically, similar opinion holders may form into communities yet with no strict community consensus;and rather than being separated into disconnected communities, different communities are connected by a non-trivial proportion of inter-community links. More importantly, we show that the complex dynamics may lead to different numbers of communities at steady state with a given tolerance between different opinion holders. We construct a framework for theoretically analyzing the co-evolution process. Theoretical analysis and extensive simulation results reveal some useful insights into the complex co-evolution process, including the formation of dynamic equilibrium, the phase transition between different steady states with different numbers of communities, and the dynamics between opinion distribution and network modularity. Copyright © 2017, The Authors. All rights reserved.

关键词： Complex networks

SciPy 1.0—Fundamental algorithms for scientific computing in python

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Virtanen, Pauli Gommers, Ralf Oliphant, Travis E. Haberland, Matt Reddy, Tyler Cournapeau, David Burovski, Evgeni Peterson, Pearu Weckesser, Warren Bright, Jonathan van der Walt, Stéfan J. Brett, Matthew Wilson, Joshua Millman, K. Jarrod Mayorov, Nikolay Nelson, Andrew R.J. Jones, Eric Kern, Robert Larson, Eric Carey, C.J. Polat, Ilhan Feng, Yu Moore, Eric W. VanderPlas, Jake Laxalde, Denis Perktold, Josef Cimrman, Robert Henriksen, Ian Quintero, E.A. Harris, Charles R. Archibald, Anne M. Ribeiro, Antônio H. Pedregosa, Fabian van Mulbregt, Paul University of Jyväskylä University of Jyväskylä FI-40014 Finland Quansight LLC AustinTX United States Ultrasound Imaging Mayo Clinic RochesterMN55902 United States Electrical Engineering Brigham Young University ProvoUT84604 United States Enthought Inc. AustinTX78701 United States Anaconda Inc AustinTX78701 United States BioResource and Agricultural Engineering Department California Polytechnic State University San Luis ObispoCA93407 United States Department of Mathematics University of California Los AngelesCA90025 United States Los Alamos National Laboratory Los AlamosNM87544 United States Independent Researcher Higher School of Economics Myasnitskaya 20 Moscow101000 Russia Independent Researcher Saue Estonia Department of Mechanics and Applied Mathematics Institute of Cybernetics Tallinn Technical University Akadeemia Rd 21 Tallinn Estonia Independent Researcher NY United States Berkeley Institute for Data Science University of California BerkeleyCA94720 United States School of Psychology University of Birmingham Edgbaston BirmighamB15 2TT United Kingdom Division of Biostatistics University of California BerkeleyCA94720 United States WayRay LLC Skolkovo Innovation Center Moscow143026 Russia Australian Nuclear Science and Technology Organisation Locked Bag 2001 Kirrawee DCNSW2232 Australia Institute for Learning and Brain Sciences University of Washington SeattleWA98195 United States College of Information and Computing Sciences University of Massachusetts Amherst AmherstMA01002 United States Berkeley Center for Cosmological Physics University of California BerkeleyCA94720 United States Bruker Biospin Corp. 15 Fortune Drive BillericaMA01821 United States University of Washington SeattleWA98195 United States New Technologies - Research Centre University of West Bohemia Univerzitní 8 Plzeň306 14 Czech Republic Oden Institute for Computational Engineering and Sciences University of Texas at Austin AustinTX7

SciPy is an open source scientific computing library for the Python programming language. SciPy 1.0 was released in late 2017, about 16 years after the original version 0.1 release. SciPy has become a de facto standard for leveraging scientific algorithms in the Python programming language, with more than 600 unique code contributors, thousands of dependent packages, over 100,000 dependent repositories, and millions of downloads per year. This includes usage of SciPy in almost half of all machine learning projects on GitHub, and usage by high profile projects including LIGO gravitational wave analysis and creation of the first-ever image of a black hole (M87). The library includes functionality spanning clustering, Fourier transforms, integration, interpolation, file I/O, linear algebra, image processing, orthogonal distance regression, minimization algorithms, signal processing, sparse matrix handling, computational geometry, and statistics. In this work, we provide an overview of the capabilities and development practices of the SciPy library and highlight some recent technical developments. Copyright © 2019, The Authors. All rights reserved.

关键词： Open source software

Global contrast based salient region boundary sampling for action recognition 22nd

学校读者我要写书评

暂无评论

Global contrast based salient region boundary sampling for a...

22nd International Conference on MultiMedia Modeling, MMM 2016

作者： Xu, Zengmin Hu, Ruimin Chen, Jun Chen, Huafeng Li, Hongyang National Engineering Research Center for Multimedia Software School of Computer Wuhan University Wuhan China Collaborative Innovation Center of Geospatial Technology Wuhan China School of Mathematics and Computing Science Guangxi Colleges and Universities Key Laboratory of Data Analysis and Computation Guilin University of Electronic Technology Guilin China

ISBN: (纸本)9783319276700

Although the excellent representation ability of improved Dense Trajectory (iDT) based features for action video had been proved on several action datasets, the performance of action recognition still suffers from large camera motion of videos. In this paper, we improve the iDT method by advancing a novel salient region boundary based dense sampling strategy, which reduces the number of trajectories while preserves the discriminative power. We first implement the iDT sampling based on motion boundary image, then introduce a global contrast based salient object segmentation method in interest points sampling step of action recognition. To overcome the flaws of global color contrast-based salient region sampling, we apply morphological gradient to generate a more robust mask for sampling dense points, as motion boundaries are much clearer. To evaluate the proposed method, we conduct extensive experiments on two benchmarks including HMDB51 and UCF 50. The results show that our sampling strategy can improve the performance of action recognition with minor computational cost of mask production. In particular, on the HMDB51 dataset, the improvement over the original iDT result is 3%. Meanwhile, any other dense features of action recognition can achieve more competitive performance by utilizing our sampling strategy and Fisher vector encoding method simply. © Springer International Publishing Switzerland 2016.

关键词： Trajectories

Who will pass? Analyzing learner behaviors in MOOCs

学校读者我要写书评

暂无评论

Research and Practice in Technology Enhanced Learning 2016年第1期11卷 1-11页

作者： Tseng, Shu-Fen Tsao, Yen-Wei Yu, Liang-Chih Chan, Chien-Lung Lai, K. Robert Department of Information Management and Innovation Center for Big Data and Digital Convergence Yuan Ze University 135 Yuan-Tong Road Tao-Yuan City Chung-Li District Taiwan Department of Information Management Yuan Ze University 135 Yuan-Tong Road Tao-Yuan City Chung-Li District Taiwan Department of Computer Science and Engineering and Innovation Center for Big Data and Digital Convergence Yuan Ze University 135 Yuan-Tong Road Tao-Yuan City Chung-Li District Taiwan

Massive open online courses (MOOCs) have recently gained worldwide attention from educational institutes. MOOCs provide a new option for learning, yet measurable learning benefits of MOOCs still need to be investigated. Collecting data of three MOOCs at Yuan Ze University (YZU), this paper intended to classify learning behaviors among 1489 students on the MOOC platform at YZU. This study further examined learning outcomes in MOOCs by different types of learners. The Ward’s hierarchical and k-means non-hierarchical clustering methods were employed to classify types of learners’ behavior while they engaged in learning activities on the MOOC platform. Three types of MOOC learners were classified—active learner, passive learner, and bystander. Active learners who submitted assignments on time and frequently watched lecture videos showed a higher completion rate and a better grade in the course. MOOC learners who participated in online discussion forum reported a higher rate of passing the course and a better score than those inactive classmates. The finding of this study suggested that the first 2 weeks was a critical point of time to retain students in MOOCs. MOOC instructors need to carefully design course and detect risk behaviors of students in early of the classes to prevent students from dropping out of the course. The feature design of discussion forum is to provide peer interaction and facilitate online learning. Our results suggested that timely feedback by instructors or facilitators on discussion forum could enhance students’ engagement in MOOCs. © 2016, The Author(s).

关键词： Learning analytics Learning behavior Learning engagement MOOCs