检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Ma, Ke Xu, Qianqian Yang, Zhiyong Cao, Xiaochun State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

In the absence of prior knowledge, ordinal embedding methods obtain new representation for items in a low-dimensional Euclidean space via a set of quadruple-wise comparisons. These ordinal comparisons often come from human annotators, and sufficient comparisons induce the success of classical approaches. However, collecting a large number of labeled data is known as a hard task, and most of the existing work pay little attention to the generalization ability with insufficient samples. Meanwhile, recent progress in large margin theory discloses that rather than just maximizing the minimum margin, both the margin mean and variance, which characterize the margin distribution, are more crucial to the overall generalization performance. To address the issue of insufficient training samples, we propose a margin distribution learning paradigm for ordinal embedding, entitled Distributional Margin based Ordinal Embedding (DMOE). Precisely, we first define the margin for ordinal embedding problem. Secondly, we formulate a concise objective function which avoids maximizing margin mean and minimizing margin variance directly but exhibits the similar effect. Moreover, an Augmented Lagrange Multiplier based algorithm is customized to seek the optimal solution of DMOE effectively. Experimental studies on both simulated and real-world datasets are provided to show the effectiveness of the proposed algorithm. Copyright © 2018, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

Robust ordinal embedding from contaminated relative comparisons

arXiv

引用

arXiv 2018年

作者： Ma, Ke Xu, Qianqian Cao, Xiaochun State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences School of Cyber Security University of Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences

Existing ordinal embedding methods usually follow a two-stage routine: outlier detection is first employed to pick out the inconsistent comparisons;then an embedding is learned from the clean data. However, learning in a multi-stage manner is well-known to suffer from sub-optimal solutions. In this paper, we propose a unified framework to jointly identify the contaminated comparisons and derive reliable embeddings. The merits of our method are three-fold: (1) By virtue of the proposed unified framework, the sub-optimality of traditional methods is largely alleviated;(2) The proposed method is aware of global inconsistency by minimizing a corresponding cost, while traditional methods only involve local inconsistency;(3) Instead of considering the nuclear norm heuristics, we adopt an exact solution for rank equality constraint. Our studies are supported by experiments with both simulated examples and real-world data. The proposed framework provides us a promising tool for robust ordinal embedding from the contaminated comparisons. Copyright © 2018, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Microphone Array Acoustic Source Localization system based on Deep Learning

Microphone Array Acoustic Source Localization system based o...

引用

International Symposium on Chinese Spoken Language processing

作者： Junhao Ding Bin Ren Nengheng Zheng Guangdong Key Laboratory of Intelligent Information Processing College of Information Engineering Shenzhen University Shenzhen China School of Electrical Engineering & Intelligentization Dongguan University of Technology Dongguan China

ISBN: (纸本)9781538656280;9781538656273

This paper presents a microphone array sound source localization system based on deep learning algorithms. Currently, the most popular acoustic source localization algorithms are based on the traditional array signal processing methods. These methods have good localization performance in the ideal acoustic environment. However, the performances degraded significantly in low signal-to-noise ratio (SNR) and strong reverberation environments. To deal with this problem, this study developed a deep neural network (DNN) based system. Unlike the traditional algorithms with poor adaptability to environmental conditions, the proposed system can automatically learn the spatial information of sound sources under various conditions through training a large amount of data. Furthermore, it can fully utilize all the information of the original data without additional feature extraction. A set of experiments are carried out to evaluate the performance of the proposed system in comparison with the generalized cross correlation phase transform (GCC-PHAT) method. Results verify that the DNN based system achieves higher accuracy under low SNR conditions.

关键词： Microphone arrays Arrays Array signal processing Reverberation Data models

来源：评论

学校读者我要写书评

暂无评论

A Multiscale Superpixel-Level Salient Object Detection Model Using Local-Global Contrast Cue

引用

Journal of Shanghai Jiaotong university(Science) 2017年第1期22卷 121-128页

作者：穆楠徐新王英林张晓龙 School of Computer Science and Technology Wuhan University of Science and Technology Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan University of Science and Technology School of Information Management and Engineering Shanghai University of Finance and Economics

The goal of salient object detection is to estimate the regions which are most likely to attract human's visual attention. As an important image preprocessing procedure to reduce the computational complexity, salient object detection is still a challenging problem in computer vision. In this paper, we proposed a salient object detection model by integrating local and global superpixel contrast at multiple scales. Three features are computed to estimate the saliency of superpixel. Two optimization measures are utilized to refine the resulting saliency map. Extensive experiments with the state-of-the-art saliency models on four public datasets demonstrate the effectiveness of the proposed model.

关键词： salient object detection superpixel multiple scales local contrast global contrast TP 391.4 A

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Spectrum Allocation Algorithm in Ultra-Dense Network

An Adaptive Spectrum Allocation Algorithm in Ultra-Dense Net...

引用

International Conference on Communication Software and Networks, ICCSN

作者： Jun Zhu Chaochao Jia Chao Wang Kai Li Key laboratory of Intelligent Computing & Signal Processing (Anhui University) Ministry of Education Hefei China Technology and Innovation Department Shanghai Research Center for Wireless Communication Shanghai China

In this paper, we propose a novel method to adaptively adjust the parameter threshold used in overlapping frequency. We verify the performance of the proposed algorithm from the system simulation. Compared with the traditional network planning scheme which needs setting parameters manually, the optimal threshold is adaptively adjusted according to the distribution of the users. The simulation results show that the algorithm can improve the signal-to-interference-plus-noise-ratio (SINR) performance of users and the cell throughput when the users are distributed in the edge of cell coverage which owns the same optimization result as traditional optimization method. So the algorithm can effectively solve the decrease problem of spectral efficiency when the threshold in frequency overlap is set unreasonable and also save a lot of labour cost on setting parameters.

关键词： Interference Signal to noise ratio Throughput Clustering algorithms Bandwidth Radio spectrum management Resource management

来源：评论

学校读者我要写书评

暂无评论

Universal enzymatic numerical P systems with small number of enzymatic variables

引用

Science China(Information Sciences) 2018年第9期61卷 38-49页

作者： Zhiqiang ZHANG Tingfang WU ANDrei P■UN Linqiang PAN Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Automation Huazhong University of Science and Technology Department of Computer Science Faculty of Mathematics and Computer ScienceUniversity of Bucharest Bioinformatics Department National Institute of Research and Development for Biological Sciences School of Electric and Information Engineering Zhengzhou University of Light Industry

Numerical P systems(for short, NP systems) are distributed and parallel computing models inspired from the structure of living cells and economics. Enzymatic numerical P systems(for short, ENP systems) are a variant of NP systems, which have been successfully applied in designing and implementing controllers for mobile robots. Since ENP systems were proved to be Turing universal, there has been much work to simplify the universal systems, where the complexity parameters considered are the number of membranes, the degrees of polynomial production functions or the number of variables used in the *** the number of enzymatic variables, which is essential for ENP systems to reach universality, has not been investigated. Here we consider the problem of searching for the smallest number of enzymatic variables needed for universal ENP systems. We prove that for ENP systems as number acceptors working in the all-parallel or one-parallel mode, one enzymatic variable is sufficient to reach universality; while for the one-parallel ENP systems as number generators, two enzymatic variables are sufficient to reach *** results improve the best known results that the numbers of enzymatic variables are 13 and 52 for the all-parallel and one-parallel systems, respectively.

关键词： bio-inspired computing numerical P system mobile robot membrane controller universality

来源：评论

学校读者我要写书评

暂无评论

H∞ consensus control of fractional-order multi-agent systems over the directed graph

H∞ consensus control of fractional-order multi-agent system...

引用

第37届中国控制会议

作者： Lin Chen Wen-Sen Wang Hao Wu Yan Lei Jiang-Wen Xiao School of Automation Huazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control(Huazhong University of Science and Technology) Ministry of Education State grid shanxi electric power research institute

In this paper, the H∞ consensus of fractional-order multi-agent systems with directed communication graph is investigated. It's the first time to introduce the H∞ control to investigate the consensus problem of the fractional-order multi-agent systems. In view of Mittag-Leffler stability theory and fractional Lyapunov directed method, a sufficient condition is presented to guarantee all the agents reach consensus with the desired H∞ performance. Finally, the results are verified by several numerical simulations.

关键词： Consensus H∞ control Multi-agent systems Fractional-order

来源：评论

学校读者我要写书评

暂无评论

Interdependent order allocation in the two-echelon supply chain using agent-based negotiation 36

Interdependent order allocation in the two-echelon supply ch...

引用

第36届中国控制会议

作者： Jian Wang Huimin Miao System Engineering Institute School of AutomationHuazhong University of Science and Technology Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Hubei Province Key Laboratory of Systems Science in Metallurgical Process Wuhan University of Science and Technology

ISBN: (纸本)9781538629185

Nowadays,many researches study the negotiation-based order allocation problem in the supply chain environment,aiming to improve the efficiency of the allocation and the profits of the supply chain *** competition and cooperation in supplier’s side are mainly addressed because of independent *** this paper,we analyze an interdependent order allocation problem in a two-echelon supply *** supply chain consists of a manufacturer echelon and a supplier *** to the interdependence,both the competition and cooperation in the manufacturer echelon are *** agent-based negotiation algorithm is developed to support the order allocation process and the conflicts *** show in experiments that orders under various supply chain contexts can be successfully allocated through the algorithm.

关键词： Supply chain system order allocation agent-based negotiation

来源：评论

学校读者我要写书评

暂无评论

Community discovery of complex network based on fuzzy density peak clustering algorithm

Community discovery of complex network based on fuzzy densit...

引用

IEEE Conference on Industrial Electronics and Applications (ICIEA)

作者： Ling Tao Wenjie Li Yu Jin Shuang Yin College of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology Wuhan China

Based on the similarity measure of the complex network node and the improved density peak clustering algorithm with information entropy, a community discovery method is proposed in this paper. First of all, the distance between nodes is measured by the Jaccard similarity and the shortest path generation algorithm. Then, the core communities with the improved density peak algorithm are selected automatically. Thirdly, applying the fuzzy clustering mechanism to calculate the membership degree matrix of each point, thus completing the division of the remaining points. Finally, overlapping nodes are distinguished by setting a threshold of degree difference. Experiments are conducted on four real-life networks and the Purity and the Extended Modularity are employed to evaluate the proposed algorithm. The comparison of experiments with some classical algorithms on real networks are given to demonstrate the feasibility and effectiveness of the proposed method.

关键词： Clustering algorithms Complex networks Entropy Information entropy Classification algorithms Clustering methods Dolphins

来源：评论

学校读者我要写书评

暂无评论

An object classification method based on the improved bacterial foraging optimisation algorithm

引用

International Journal of Wireless and Mobile Computing 2017年第2期12卷 166-173页

作者： Zeng, Zhigao Guan, Lianghua Yi, Shengqiu Zhu, Yanhui Liu, Qiang Tong, Qi Zeng, Sanyou College of Computer and Communication Hunan University of Technology Hunan412007 China Intelligent Information Perception and Processing Technology Hunan Province Key Laboratory Hunan China Department of Computer Science China University of GeoSciences Wuhan Hubei China

This paper proposes a new object classification method based on an improved bacterial foraging optimisation algorithm. Firstly, a dynamic step size is used instead of the fixed step size of the chemotaxis. Secondly, the fixed elimination-dispersal probability is replaced by the dynamic probability. Features are extracted to distinguish the objects, such as pedestrians, cars and pets. Ultimately, all the objects are classified using the improved bacterial foraging optimisation algorithm. The experimental results prove that the effectiveness of the object classification method proposed in this paper is better than that of other algorithms. Copyright © 2017 Inderscience Enterprises Ltd.

关键词： 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：