检索结果-内蒙古大学图书馆

International Conference on Computational Intelligence and Security

作者： Ming Fang Yong Wang Miao Ye School of information and communication Guilin University of Electronic Technology Guilin China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin China School of Information and Communication Guilin University of Electronic Technology Guilin China

ISBN: (数字)9781728160924

ISBN: (纸本)9781728160931

The reasonable multi-controller deployment in Software Defined Network (SDN) must reach a high requirement for the low latency between controllers and switches. Existing methods are mostly based on controller software platform to implement a deployment algorithm, which will increase latency and load of controllers. Aiming at minimizing the latency between a controller and switches, this paper proposes a method of multi-controller deployment in SDN based on FPGA to improve the algorithm efficiency and reduce the latency by utilizing the characteristics of FPGA parallel computing. Firstly, a cooperative model of multi-controller based on FPGA is designed, which can raise the performance of controllers by centralized management. Based on this model, the multi-controller deployment has been discussed, and the multi-controller deployment strategy based on the improved K-means clustering algorithm has been proposed. The algorithm was transplanted to the cooperative model based on FPGA for running. At last, this paper has verified the correctness of the multi-controller deployment method through software and FPGA simulation experiments. Extensive simulation results show that the algorithm model based on FPGA designed in this paper can effectively reduce the latency between controllers and switches, and the running time acceleration ratio can reach 14.

关键词： Field programmable gate arrays Control systems Partitioning algorithms Clustering algorithms Network topology Computational modeling Software algorithms

来源：评论

学校读者我要写书评

暂无评论

Publication recommendations of manuscripts using improved C4.5 decision tree algorithm 2nd

Publication recommendations of manuscripts using improved C4...

引用

2nd International Conference on intelligent and Interactive Systems and Applications, IISA 2017

作者： Jia, Didi Xie, Wu Chen, Zhiyong Qiang, Baohua School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guangxi Colleges and Universities Key Laboratory of Cloud Computing and Complex System Guilin541004 China Guangxi Key Laboratory of Trusted Software Guilin541004 China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin541004 China

ISBN: (纸本)9783319690957

In view of the problem that the result accuracy of the research publication recommendations of manuscripts is often low. It is very difficult for many contributors to find the suitable journals from many recommendation results. To solve this problem, a novel method of publication recommendations for authors’ manuscripts is proposed using our improved C4.5 decision tree algorithm. For the shortcomings of too many values of data samples during dealing with the traditional C4.5 methods, the five-value logic ideas are adopted to improve this C4.5 algorithm to apply in the research fields of publication recommendations. The experimental results show that the related publications are easier to obtain for authors via the decision trees with the improved C4.5 method than before, and this method has higher accuracy than ever. It is of great significance to help the researchers, especially for those who have no enough experience to choose the most suitable journals from a lot of publications. © 2018, Springer International Publishing AG.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Accumulative time-based ranking method to reputation evaluation in information networks

arXiv

引用

arXiv 2019年

作者： Liao, Hao Liu, Qi-Xin Huang, Ze-Cheng Yeung, Chi Ho Zhang, Yi-Cheng National Engineering Laboratory on Big Data System Computing Technology Guangdong Province Engineering Center of China-made High Performance Data Computing System College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Institute of Big Data Intelligent Management and Decision Shenzhen University Shenzhen518060 China Department of Science and Environmental Studies The Education University of Hong Kong Hong Kong Hong Kong Department of Physics University of Fribourg Fribourg Switzerland

With the rapid development of modern technology, the Web has become an important platform for users to make friends and acquire information. However, since information on the Web is over-abundant, information filtering becomes a key task for online users to obtain relevant suggestions. As most Websites can be ranked according to users’ rating and preferences, relevance to queries, and recency, how to extract the most relevant item from the over-abundant information is always a key topic for researchers in various fields. In this paper, we adopt tools used to analyze complex networks to evaluate user reputation and item quality. In our proposed accumulative time-based ranking (ATR) algorithm, we incorporate two behavioral weighting factors which are updated when users select or rate items, to reflect the evolution of user reputation and item quality over time. We showed that our algorithm outperforms state-of-the-art ranking algorithms in terms of precision and robustness on empirical datasets from various online retailers and the citation datasets among research publications. Copyright © 2019, The Authors. All rights reserved.

关键词： Information filtering

来源：评论

学校读者我要写书评

暂无评论

Improving the microenvironment of tracking photovoltaic systems promotes soil organic carbon accumulation by mediating plant carbon inputs and microbial necromass retention

引用

Journal of environmental management 2025年 388卷 125937页

作者： Siqi Zhang Jirui Gong Rui Wang Kai Zheng Weiyuan Zhang Xuede Dong Yuxia Hu Guisen Yang Chenyi Yan Shangpeng Zhang Ruijing Wang Tong Wang State Key Laboratory of Earth Surface Processes and Resource Ecology MOE Engineering Research Center of Desertification and Blown-sand Control Faculty of Geographical Science Beijing Normal University No. 19 Xinjiekouwai Street Haidian District Beijing 100875 China. State Key Laboratory of Earth Surface Processes and Resource Ecology MOE Engineering Research Center of Desertification and Blown-sand Control Faculty of Geographical Science Beijing Normal University No. 19 Xinjiekouwai Street Haidian District Beijing 100875 China. Electronic address: jrgong@***. CGN New Energy Holdings Co. Ltd. Hanwei International Plaza Fengtai District Beijing 100071 China. Inner Mongolia Ganze Desert Technology Co. Ltd. High-tech industrial park cloud computing big data enterprise headquarters Kangbashi District Ordos 017004 China.

Photovoltaic systems greatly reduce greenhouse gas emissions. However, the microenvironmental changes of photovoltaic modules affect soil organic carbon (SOC) and improve carbon sequestration in terrestrial ecosystems to mitigate global climate change is unclear. We analyzed the effects of different photovoltaic systems on SOC and its fractions in semi-arid grassland, and revealed the SOC formation and stability mechanisms. Tracking photovoltaic systems increased carbon stock, especially proportion of mineral-associated organic carbon (MAOC) in SOC by more than 10 %, and depended on the responses of plant inputs and microbial necromass to microenvironmental changes. Suitable amounts of light and water in the systems improved litter biomass and quality, and promoted MAOC accumulation by increasing the exogenous carbon supply and microbial activity. Such systems also reduced soil carbon loss by reducing heterotrophic respiration caused by low levels of organic acids and recruiting effective microorganisms such as Schizothecium and Lactobacillus. Moreover, changes in litter and root exudates promoted microbial biomass and enzyme activity, mediating the retention of microbial necromass and SOC. The contribution of bacterial necromass carbon to SOC increased by more than 8.5 %. However, fixed photovoltaic systems reduced soil carbon stock by 0.46 kg m due to water limitations that decreased both plant carbon inputs and microbial necromass. Our results revealed the importance of plant inputs and microbial necromass in regulating SOC in photovoltaic systems, and demonstrated that photovoltaic systems can achieve synergies between CO emission reduction and soil carbon sequestration. This provides new insights for formulating carbon management policy and promoting sustainable eco-economic development.

关键词： Litter quantity and quality Microbial necromass Photovoltaic system Root exudates Soil microbes Soil organic carbon

来源：评论

学校读者我要写书评

暂无评论

Multiview feature selection combining latent space and similarity structure learning

引用

Pattern Recognition 2026年 169卷

作者： Zhuowen Li Hongmei Chen Tengyu Yin Zhong Yuan Chuan Luo Shi-Jinn Horng Tianrui Li School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu 611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu 611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu 611756 PR China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Southwest Jiaotong University Chengdu 611756 PR China College of Computer Science Sichuan University Chengdu 610065 China Department of Computer Science and Information Engineering Asia University Taichung 41354 Taiwan Department of Medical Research China Medical University Hospital China Medical University Taichung 404327 Taiwan

Unsupervised multiview feature selection dependent on similar or clustering structures has dramatically progressed, but both ignore the mutually reinforcing relationship between structure learning. Firstly, the two methods of appeal ignore the possibility of shared joint learning, although they can learn coherent information. Secondly, they are inadequate for data structure learning and lack awareness of co-learning global and local structures. This paper proposes an unsupervised feature selection method (SCSF_FS) that integrates similarity and clustering structures learning to capture intrinsic information in data. Specifically, we use latent space learning to partition multiple data matrices into view-specific base matrices and clustering metrics. Structural learning is used to transform specific clustering metrics into coherent clustering structures. In addition, adaptive weights are used on each view’s similarity matrix to learn a consistent similarity structure, while laplacian graph learning is introduced to unify the similarity and clustering structures. Consequently, a unified framework is designed to unify multiview consistency learning, global structure, and local structure preservation. Moreover, an optimization iteration algorithm is designed to solve it. Comparison with eight algorithms shows the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Construction Method of Regeneration Tree for Single Node Fault Repair Mechanism in Distributed Storage System

A New Construction Method of Regeneration Tree for Single No...

引用

International Conference on Computational Intelligence and Security

作者： Wei Guo Yong Wang Miao Ye School of Computer Science and Information Security Guilin University of Electronic Technoloay Guilin Guangxi China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin Guangxi China Guangxi Colleges and Universities Key Laboratory of Cloud Computing and Complex Systems Guilin University of Electronic Technology Guilin Guangxi China School of Information and Communication Guilin University of Electronic Technology Guilin Guangxi China

ISBN: (数字)9781728160924

ISBN: (纸本)9781728160931

Comparing with the classic redundancy policy of multi-replica technology, Erasure code is preferred due to its higher utilization rate of storage space in distributed storage system. As one kind of the important Erasure code, the traditional regeneration code with star recovery topology cost more time and more network bandwidth in the data recovery process. An efficient approach to reduce the delay time and network consumption is to construct an optimal recovery tree with the best possible bottleneck bandwidth, which is proved to be a Non-deterministic Polynomial problem. To solve this problem, this paper proposed a hybrid genetic algorithm which utilizes the designed crossover operation and mutation operation according to the problem property. A series of experiments have been conducted and the results show that our proposed method has good convergent ability and reduce the regeneration time.

关键词： Topology Bandwidth Genetic algorithms Encoding Network topology Sociology Statistics

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Outlier Detection Based on Full Convolutional Network

Network Traffic Outlier Detection Based on Full Convolutiona...

引用

International Conference on Computational Intelligence and Security

作者： Jingrong Mo Yong Wang Miao Ye School of Computer Science and Information Security Guilin University of Electronic Technology Guilin Guangxi China Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin Guangxi China Guangxi Colleges and Universities Key Laboratory of Cloud Computing and Complex Systems Guilin University of Electronic Technology Guilin Guangxi China School of Information and Communication Guilin University of Electronic Technology Guilin Guangxi China

ISBN: (数字)9781728160924

ISBN: (纸本)9781728160931

Network traffic flow can be represented as time series. Outliers of these time series is important for the computer network security. The existing methods for the time series anomaly detection mainly operate on the entire time series to detect the abnormal series, seldom find out the position of the abnormal point. To solve this defect, we propose a method to discover the location of the outliers in time series based on a full convolutional network. We first map the time series into two-dimensional grayscale images by sliding window approach, and then feed them into the full convolutional network. In the classified stage, the feature maps of the last convolution layer are restored to the same size as the input image by up-sampling. Finally, we predict the class for each pixel and calculate the loss on a pixel-by-pixel basis. We tested the model on Yahoo Webscope S5 anomaly benchmark dataset, and the results show that our proposed method can achieve a mean pixel accuracy of 99.4% and mean IOU of 97% on the test dataset.

关键词： Time series analysis Telecommunication traffic Anomaly detection Convolution Feature extraction Gray-scale Machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of an intelligent shipborne terminal system 12th

Design and implementation of an intelligent shipborne termin...

引用

12th International Conference on Communications and Networking in China, CHINACOM 2017

作者： Chen, Wenqiu Yao, Rongbin Ye, Jincai Tang, Xin Li, Xiaohuan Guangxi Cooperative Innovation Center of Cloud Computing and Big Data Guilin University of Electronic Technology Guilin China Key Laboratory of Cognitive Radio and Information Processing Ministry of Education Guilin University of Electronic Technology Guilin China Beihang University Beijing China

ISBN: (纸本)9783319781389

To solve the problem that network services provided by ships can’t distinguish different users and the Quality of Service (QoS) is poor, an intelligent shipborne terminal system which combines advanced positioning technology and wireless communication technology is designed in this paper. The overall design of the system including hardware design and software design is proposed. The test results show that the system can distinguish between different users’ Wi-Fi connection, intelligentize the management of system users, realizes the function of GPS positioning navigation and has a rich local resource storage, which all proved its good application value. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2018.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Predicting Virtual Machine Resource Consumption Based on Optimized Grey Model

引用

IOP Conference Series: Materials Science and Engineering 2019年第5期563卷

作者： Shi Aiwu Gao Di He Kai Cloud Computing and Big Data Research Center Wuhan Textile University Wuhan 430200 China

In order to relatively change the computing specifications of virtual machines (VMs for short) for the changing resource consumption of VMs, and reduce the impact of the changes, this paper proposes the optimized grey GM(1, 1) model to predict the resource consumption of VMs. Because VM resources may fluctuate greatly in a short time, the initial data are smoothed first, and then modeled, the model edge value is optimized according to the characteristics of cloud environment. Experiments show that the accuracy and stability of the prediction model can be improved by sorting out the initial data and optimizing the model. The prediction value is helpful to design the allocation scheme of VM resources, improve the utilization rate of physical resources in cloud environment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Practical adaptive time-varying output formation tracking for high-order nonlinear multi-agent systems using neural networks

Practical adaptive time-varying output formation tracking fo...

引用

第三十八届中国控制会议

作者： Jianglong Yu Xiwang Dong Qingdong Li Zhang Ren Ming Ma School of Automation Science and Electrical Engineering Science and Technology on Aircraft Control Laboratory Beihang University Shananxi Key Laboratory of Integrated and Intelligent Navigation Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Xi'an Research Institute of Navigation Technology

Practical adaptive time-varying output formation tracking problems for high-order nonlinear strict-feedback multiagent systems are investigated in this paper. The time-varying output formation tracking requires the followers' output vectors to track the output vector of the leader while achieving a time-varying formation. The dynamics of the leader and the followers can have uncertain mismatched nonlinearities while the leader's control input is also unknown. To deal with the mismatched nonlinearities, the backstepping techniques are utilized to construct the protocols. Firstly, visual controllers are designed to overcome the effects of the uncertainties while guaranteeing the stability of each layer. The complicated visual controllers are estimated by the neural networks. A full adaptive protocol is constructed with adaptive gains to avoid using the global information of the interaction topology. Then, an algorithm is presented to design the protocol, whose parameters are much less. Besides, the stability of the algorithm is proved by Lyapunov theories. Finally, simulation results are presented to prove the effectiveness.

关键词： Practical time-varying formation tracking Adaptive control High-order nonlinear dynamics Multi-agent systems Neural networks

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：