检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Cui, Jiaxu Yang, Bo Key Laboratory of Symbolic Computation and Knowledge Engineer Ministry of Education School of Computer Science and Technology Jilin University China

Network structure optimization is a fundamental task in complex network analysis. However, almost all the research on Bayesian optimization is aimed at optimizing the objective functions with vectorial inputs. In this work, we first present a flexible framework, denoted graph Bayesian optimization, to handle arbitrary graphs in the Bayesian optimization community. By combining the proposed framework with graph kernels, it can take full advantage of implicit graph structural features to supplement explicit features guessed according to the experience, such as tags of nodes and any attributes of graphs. The proposed framework can identify which features are more important during the optimization process. We apply the framework to solve four problems including two evaluations and two applications to demonstrate its efficacy and potential applications. Copyright © 2018, The Authors. All rights reserved.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

An effective dimensionality reduction method for text classification based on TFP-tree

An effective dimensionality reduction method for text classi...

引用

作者： Liu, Lu College of Software Jilin University Changchun China Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Changchun China College of Computer Science and Technology Jilin University Changchun China

Obtaining interesting and topic-relevant information is a very important task in Web mining. Text classification using a small proportion of labeled data and a large proportion of unlabeled data, also called semi-supervised learning, is a well-known problem. Despite plenty of research on text classification, however, how to effectively and efficiently apply valuable frequent patterns and deal with high-dimensional data in text classification is still an open issue. Due to the increasing data volumes and plenty of high-dimensional data, both distance measures and time complexity could be influenced by the noisy data. This paper targets on this problem and presents a novel method for text classification called CTFP (Classification based on TFP-tree), which uses TFP-tree (Text-Frequent-Pattern-tree) to generate frequent patterns in tremendous amount of texts and conduct text classification in a relatively low dimensional data space. It effectively reduces the data dimensionality during constructing the classifier. Substantial experiments on three datasets (RCV1, SRAA and Reuters-21578) show that our proposed method can achieve better performance than many existing state-of-the-art methods on precision, efficiency and many other evaluation metrics. © 2018 - IOS Press and the authors. All rights reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A Simplified Rational Representation for Positive-Dimensional Polynomial Systems and SHEPWM Equations Solving

引用

Journal of Systems Science & Complexity 2017年第6期30卷 1470-1482页

作者： SHANG Baoxin ZHANG Shugong TAN Chang XIA Peng School of Mathematics Key Laboratory of Symbolic Computation and Knowledge Engineering (Ministry of Education) Jilin University College of Science Northeast Electric Power University College of Science Northeast Forestry University School of Mathematics Liaoning University

The paper is concerned with the improvement of the rational representation theory for solving positive-dimensional polynomial systems. The authors simplify the expression of rational representation set proposed by Tan and Zhang(2010), obtain the simplified rational representation with less rational representation sets, and hence reduce the complexity for representing the variety of a positive-dimensional ideal. As an application, the authors compute a "nearly" parametric solution for the SHEPWM problem with a fixed number of switching angles.

关键词： Positive-dimensional polynomial system solving rational univariate representation SHEPWM simplified rational representation

来源：评论

学校读者我要写书评

暂无评论

Adversarial sampling and training for semi-supervised information retrieval

arXiv

引用

arXiv 2018年

作者： Park, Dae Hoon Chang, Yi Huawei Research America California School of Artificial Intelligence Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education China

Ad-hoc retrieval models with implicit feedback often have problems, e.g., the imbalanced classes in the data set. Too few clicked documents may hurt generalization ability of the models, whereas too many non-clicked documents may harm effectiveness of the models and efficiency of training. In addition, recent neural networkbased models are vulnerable to adversarial examples due to the linear nature in them. To solve the problems at the same time, we propose an adversarial sampling and training framework to learn ad-hoc retrieval models with implicit feedback. Our key idea is (i) to augment clicked examples by adversarial training for better generalization and (ii) to obtain very informational non-clicked examples by adversarial sampling and training. Experiments are performed on benchmark data sets for common ad-hoc retrieval tasks such as Web search, item recommendation, and question answering. Experimental results indicate that the proposed approaches significantly outperformstrong baselines especially for high-ranked documents, and they outperform IRGAN in NDCG@5 using only 5% of labeled data for the Web search task. Copyright © 2018, The Authors. All rights reserved.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic node embedding for signed networks

arXiv

引用

arXiv 2019年

作者： Song, Wenzhuo Chen, Hongxu Liu, Xueyan Jiang, Hongzhe Wang, Shengsheng College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Advanced Analytics Institute School of Computer Science Faculty of Engineering and IT University of Technology Sydney NSW2007 Australia College of Mechanical and Electronic Engineering Nanjing Forestry University Nanjing210037 China

Signed network embedding methods aim to learn vector representations of nodes in signed networks. However, existing algorithms only managed to embed networks into low-dimensional Euclidean spaces whereas many intrinsic features of signed networks are reported more suitable for non-Euclidean spaces. For instance, previous works did not consider the hierarchical structures of networks, which is widely witnessed in real-world networks. In this work, we answer an open question that whether the hyperbolic space is a better choice to accommodate signed networks and learn embeddings that can preserve the corresponding special characteristics. We also propose a non-Euclidean signed network embedding method based on structural balance theory and Riemannian optimization, which embeds signed networks into a Poincar ball in a hyperbolic space. This space enables our approach to capture underlying hierarchy of nodes in signed networks because it can be seen as a continuous tree. We empirically compare our method against six Euclidean-based baselines in three tasks on seven real-world datasets, and the results show the effectiveness of our method. Copyright © 2019, The Authors. All rights reserved.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Genetic Fuzzy System in Weapon Control Module of Unmanned Tanks

Genetic Fuzzy System in Weapon Control Module of Unmanned Ta...

引用

2018 International Conference on Computer Modeling, Simulation and Algorithm（CMSA2018）

作者： Xinzhu Liu Di Ding Zihuan Yu Zhongshuai Wang Yuhan Dai Jing Huang School of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineer Jilin University Ministry of Education

The genetic fuzzy system is applied to weapon control module of unmanned tanks. In this paper, the simulation system is built to train the fuzzy rule base of genetic fuzzy system in order to get the optimal fuzzy rule base with training tasks. Testing tasks are used to test the success rate of different missions under the optimal rule base. The fuzzy inference system obtained by the algorithm achieves high success rate in various tasks.

关键词： unmanned tanks genetic fuzzy system fuzzy rule base weapon control module

来源：评论

学校读者我要写书评

暂无评论

A cloud-based evaluation system for science-and-engineering students 4th

A cloud-based evaluation system for science-and-engineering ...

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Huang, Qian Ye, Feng Chen, Yong Xu, Peiling College of Computer and Information Hohai University Nanjing211100 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Postdoctoral Centre Nanjing Longyuan Micro-Electronic Company Nanjing211106 China Suzhou College of Information Technology Suzhou215200 China

ISBN: (纸本)9789811322051

With the burgeoning of IT industry, more and more companies and universities concentrate on the scientific evaluation of science-and-engineering students. Existing evaluation strategies typically lie on grades or scores of the courses taken by students, which have obvious drawbacks nowadays and cannot lead to a proper improvement of education management. This paper proposes an overall student evaluation system architecture that includes three levels, i.e. data collection infrastructure which comprises student data collection and student data transmission, data center which is composed of four sub-levels, and unified portal which defines unified applications and classes of visiting terminals. In the proposed architecture, the main contribution lie in the upper most sub-level of data center, i.e. evaluation services. Four categories of student evaluation services, i.e. moral trait, civic literacy, knowledge level and comprehensive ability, are defined. Furthermore, in order to have a satisfactory feedback in the practical teaching process, the most important comprehensive ability for science-and-engineering students is fractionized into four sub-categories and visualized from several different aspects for a good feedback in practical teaching process. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Approximate Model Counting by Partial knowledge Compilation

arXiv

引用

arXiv 2018年

作者： Lai, Yong College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education Changchun China

Model counting is the problem of computing the number of satisfying assignments of a given propositional formula. Although exact model counters can be naturally furnished by most of the knowledge compilation (KC) methods, in practice, they fail to generate the compiled results for the exact counting of models for certain formulas due to the explosion in sizes. Decision-DNNF is an important KC language that captures most of the practical compilers. We propose a generalized Decision-DNNF (referred to as partial Decision-DNNF) via introducing a class of new leaf vertices (called unknown vertices), and then propose an algorithm called PARTIALKC to generate randomly partial Decision-DNNF formulas from the given formulas. An unbiased estimate of the model number can be computed via a randomly partial Decision-DNNF formula. Each calling of PARTIALKC consists of multiple callings of MICROKC, while each of the latter callings is a process of importance sampling equipped with KC technologies. The experimental results show that PARTIALKC is more accurate than both SampleSearch and SearchTreeSampler, PARTIALKC scales better than SearchTreeSampler, and the KC technologies can obviously accelerate sampling. Copyright © 2018, The Authors. All rights reserved.

关键词： Importance sampling

来源：评论

学校读者我要写书评

暂无评论

A Cascaded Co-evolutionary Model for Attribute Reduction and Classification Based on Coordinating Architecture with Bidirectional Elitist Optimization

引用

Chinese Journal of Electronics 2017年第1期26卷 13-21页

作者： DING Weiping WANG Jiandong LI Yuehua CHENG Xueyun School of Computer Science and Technology Nantong University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Provincial Key Laboratory for Computer Information Processing Technology Soochow University College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics

A cascaded co-evolutionary model for Attribute reduction and classification based on Coordinating architecture with bidirectional elitist optimization(ARC-CABEO) is proposed for the more practical applications. The regrouping and merging coordinating strategy of ordinary-elitist-role-based population is introduced to represent a more holistic cooperative co-evolutionary framework of different populations for attribute reduction. The master-slave-elitist-based subpopulations are constructed to coordinate the behaviors of different elitists, and meanwhile the elitist optimization vector with the strongest balancing between exploration and exploitation is selected out to expedite the bidirectional attribute co-evolutionary reduction process. In addition, two coupled coordinating architectures and the elitist optimization vector are tightly cascaded to perform the co-evolutionary classification of reduction subsets. Hence the preferring classification optimization goal can be achieved better. Some experimental results verify that the proposed ARC-CABEO model has the better feasibility and more superior classification accuracy on different UCI datasets, compared with representative algorithms.

关键词： Attribute reduction for classification Bidirectional elitist optimization Coordinating architecture Cascaded co-evolutionary model

来源：评论

学校读者我要写书评

暂无评论

Image clustering segmentation based on SLIC superpixel and transfer learning

引用

Pattern Recognition and Image Analysis 2017年第4期27卷 838-845页

作者： Li, X.X. Shen, X.J. Chen, H.P. Feng, Y.C. College of Computer Science and Technology Jilin University ChangchunJilin130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University ChangchunJilin130012 China

Traditional fuzzy C-means clustering algorithm has poor noise immunity and clustering results in image segmentation. To overcome this problem, a novel image clustering algorithm based on SLIC superpixel and transfer learning is proposed in this paper. In the proposed algorithm, SLIC superpixel method is used to improve the edge matching degree of image segmentation and enhances the robustness to noise. Transfer learning is adopted to correct the image segmentation result and further improve the accuracy of image segmentation. In addition, the proposed algorithm improves the original SLIC superpixel algorithm and makes the edge of the superpixel more accurate. Experimental results show that the proposed algorithm can obtain better segmentation results. © 2017, Pleiades Publishing, Ltd.

关键词： Image segmentation

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：