检索结果-内蒙古大学图书馆

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Xu, Mengchu Zeng, Yan Xue, Meiting Zhang, Ji-Lin Wan, Jian Zhou, Mingyao Wen, Yilin Shi, Yukun Hangzhou Dianzi University School of Computer Science and Technology Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education Hangzhou China Zhejiang Engineering Research Center of Data Security Governance Hangzhou China Hangzhou Dianzi University School of Cyberspace Hangzhou China Huawei Enterprise Communication Technology Co Hangzhou China

ISBN: (纸本)9798350345384

Federated learning is a distributed machine learning approach that trains models with multiple clients and data locally. However, the existing methods ignore the differences between local models caused by the data heterogeneity, and give a high aggregation weight for the low-quality local model, which leads to low accuracy of the global model. For this problem, we propose a federated learning method based on data importance weighted aggregation, FedAG. It constructs an evaluation model of data importance based on the data distribution skewness, data volume, and data quality of clients, and aggregates local models with different weights computed by the evaluation model of data importance into a global model. We make experiments on five datasets including EMNIST, MNIST, and CIFAR-10. The results show that the accuracy of FedAG is respectively improved by 6.5%, 1.8%, 1.3% and 2.1%, compared with FedAvg, FedProx, FedVar, and Scaffold algorithms. © 2023 IEEE.

关键词： Scaffolds

来源：评论

学校读者我要写书评

暂无评论

BthyDra+: Towards a Comprehensive Model to Conduct Cross-project Defect Prediction

引用

Journal of Computers (Taiwan) 2018年第6期29卷 52-65页

作者： Huang, Ning Fang, Jinglong Wei, Dan Chen, Bin Wang, Xingqi School of Computer Science Hangzhou Dianzi University ZheJiang Province China Key Laboratory of Complex Systems Modeling and Simulation Ministry of Education School of Computer Science Hangzhou Dianzi University ZheJiang Province China

Cross-project defect prediction (CPDP) is a field of study where researchers need to build a universal model by using within-project data to predict defects on other projects. However, variations in the distribution of source and target projects have an influence on the performance of classifiers. To enable effective cross-project defect prediction, we propose a comprehensive model containing data preprocessing and classifier transferring to construct a better classification space and strengthen the performance of classifiers. In preprocessing step, one baseline is calculated for every dataset from its non-defective samples based on the distance to all other non-defective samples and the data is transformed by using rank function. Genetic algorithm and ensemble learning are selected as the way in transferring step to extract effective representation from source projects and boost the capability of weak classifiers. We use Naive Bayes, Support Vector Machine and Classification and Regression Trees as classifiers and apply this model on five open resource projects (one Apache and four Eclipse projects) and NASA MDP dataset. Selecting accuracy as fitness in genetic algorithm improves the performance of classification. The model we proposed yields similar results and obtains higher precision comparing the within-project models. Meanwhile, it obtains better performance than the state-of-the-art methods on cross-project defect prediction. These results show that our model provides an opportunity to training classifiers by using more samples from different projects. © 2018 Computer Society of the Republic of China. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of multiple volume servers block level storage system based on load-balanced strategy

International Journal of Database Theory and Application

引用

International Journal of Database Theory and Application 2014年第4期7卷 59-78页

作者： Wan, Jian Chen, Xun You, Xindong School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex System Modeling and Simulation Ministry of Education China

Block level storage system has been widely used as it can provide users raw block device. On the basis of Orthrus system, this paper designs and implements a multiple volume servers block level storage system based on load-balanced strategy-Orthrus Plus. This system uses the dynamic load-balanced strategy based on genetic algorithm strategy to load balance the volume servers clusters and proposes an iSCSI pause and resume method to solve the breakpoint retransmission problem during load-balancing. At last, we design a hierarchical management mechanism based on volume life cycle at storage. Experiments show that the load balancing capability in Orthrus Plus is more accurate and efficient under the situation of larger amount of data, and the hierarchical storage strategy also increases the I/O throughout capacity. © 2013 SERSC.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

The view growth pattern of user generated videos on YouTube

引用

International Journal of u- and e- Service, Science and Technology 2016年第6期9卷 433-444页

作者： Zhou, Renjie Xia, Dongchen Yin, Yuyu Zhang, Jilin Zhang, Wei College of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory Complex System Modeling and Simulation Ministry of Education Hangzhou China

With the rapid development of social media, video sharing sites like YouTube are getting more and more attention. Discovering the view growth pattern have become interesting topics for researchers as well as advertisers, media companies. In this paper, we analyze two aspects about video view growth pattern of YouTube videos. Firstly, the pattern of aggregated view is studied. It is found that the aggregated view rate peaks in the first few days, and falls quickly in the following days, and then decrease slowly during the consecutive weeks. Finally, the view rate tends to be a constant on the long run. The aggregated view count after a period of two months can be fitted with a linear line. Secondly, the view growth pattern of individual video is explored. The results indicate that the majority of videos peak at the very beginning of videos’ lifetime, and the category of view sources causes the peak is different. The view count of individual video and the view count from each source item also stabilize after a period of two months, and we finally show the referring time and active period of each source item. © 2016 SERSC.

关键词： Growth rate

来源：评论

学校读者我要写书评

暂无评论

Statistics of active and passive scalars in one-dimensional compressible turbulence

引用

Physical Review E 2012年第6期86卷 066307-066307页

作者： Qionglin Ni Shiyi Chen State Key Laboratory of Turbulence and Complex Systems Center for Applied Physics and Technology and Key Laboratory of High Energy Density Physics Simulation Ministry of Education College of Engineering Peking University 100871 Beijing People's Republic of China

Statistics of the active temperature and passive concentration advected by the one-dimensional stationary compressible turbulence at Reλ=2.56×106 and Mt=1.0 is investigated by using direct numerical simulation with all-scale forcing. It is observed that the signal of velocity, as well as the two scalars, is full of small-scale sawtooth structures. The temperature spectrum corresponds to G(k)∝k−5/3, whereas the concentration spectrum acts as a double power law of H(k)∝k−5/3 and H(k)∝k−7/3. The probability distribution functions (PDFs) for the two scalar increments show that both δT and δC are strongly intermittent at small separation distance r and gradually approach the Gaussian distribution as r increases. Simultaneously, the exponent values of the PDF tails for the large negative scalar gradients are qθ=−4.0 and qζ=−3.0, respectively. A single power-law region of finite width is identified in the structure function (SF) of δT; however, in the SF of δC, there are two regions with the exponents taken as a local minimum and a local maximum. As for the scalings of the two SFs, they are close to the Burgers and Obukhov-Corrsin scalings, respectively. Moreover, the negative filtered flux at large scales and the time-increasing total variance give evidences to the existence of an inverse cascade of the passive concentration, which is induced by the implosive collapse in the Lagrangian trajectories.

关键词： TURBULENCE TEMPERATURE COMPUTER simulation GAUSSIAN distribution LAGRANGIAN functions TRAJECTORIES (Mechanics) POWER law (Mathematics)

来源：评论

学校读者我要写书评

暂无评论

Linear Array Synthesis Based on Artificial Neural Network Agent Model with Fast Fourier Transform

Linear Array Synthesis Based on Artificial Neural Network Ag...

引用

International Conference on Microwave and Millimeter Wave Technology Proceedings

作者： Aowei Li Jiahao Liu Xin Zhang Zhe Liu Foxiang Liu School of Information Engineering Nanchang University Nanchang China Key Laboratory of Numerical Simulation for Large Scale Complex Systems Ministry of Education

ISBN: (数字)9798350389968

ISBN: (纸本)9798350389975

This paper introduces a new array synthesis method based on back propagation (BP) neural network agent model with a training set quickly generated by fast Fourier transform. Moreover, it can be conveniently generalized to array models on different scenarios. A test example for synthesizing uniformly spaced linear array with non-uniform excitations is conducted. Synthesis results prove the effectiveness and superiority of the proposed method.

关键词： Training Microwave technology Microwave integrated circuits Fast Fourier transforms Millimeter wave technology Training data Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Interest Representation Network for Click-Through Rate Prediction

Evolutionary Interest Representation Network for Click-Throu...

引用

IEEE International Conference on Web Services (ICWS)

作者： Renjie Zhou Zhenming Jin Jian Wan Jilin Zhang Xingyu Guo Qiang Liu Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory of Complex Systems Modeling and Simulation of the Ministry of Education ITMO Joint Institute Hangzhou Dianzi University Hangzhou China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou China Dept. of Computer and Information Technology Zhejiang Police College Hangzhou China

The rapid development of the Internet has revo-lutionized our lives, providing us with an array of convenient services. However, this revolution has also led to the problem of data overload. Personalized recommendation services have been widely recognized as an effective solution to this problem by both the industrial and academic communities. Accurate prediction of click-through rate (CTR) is a critical task in personalized recommendation systems since it can improve the user’s shopping experience, ultimately increasing revenue for the platform. To achieve accurate CTR prediction, it is crucial to capture user interests. While several methods for interest modeling exist, challenges related to user interest evolution and user behavior noise need further attention. This paper proposes a novel CTR prediction model named the Evolutionary Interest Representation Network (EIRN), which learns the evolving interest representation of users from their behaviors, profiles, and environmental attributes. In the model, we introduce an advertisement correlation graph decomposition layer and a noise filter layer to enhance and purify the user behavior representation. An interest extraction layer is designed to capture sequential correlations and common characteristics between user behaviors, representing their interests. Additionally, as user interests evolve over time and their importance changes, an attention-based interest evolution layer is designed to track the evolution of user interests. Our proposed method is validated using four public datasets and an industrial dataset, showing its superiority over existing CTR prediction methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

数据驱动框架下基于基因表达编程的非线性K-L湍流混合模型

引用

Acta Mechanica Sinica 2023年第2期39卷 147-164页

作者：谢寒松赵耀民张又升 Key Laboratory of High Energy Density Physics Simulation Ministry of EducationCenterfor Applied Physics and Technology and College of EngineeringPeking UniversityBeijing 100871China State Key Laboratory for Turbulence and Complex Systems College of EngineeringPeking UniversityBeijing 100871China institute of Applied Physics and Computational Mathematics Beijing 100094China

由Rayleigh-Taylor(RT)、Richtmyer-Meshkov(RM)、Kelvin-Helmholtz(KH)等流体力学界面不稳定性诱导的湍流混合现象广泛存在于自然界和工程问题中,准确预测其演化具有十分重要的意义.考虑到实际问题的高雷诺数及复杂性,在可预见的未来,... 详细信息

由Rayleigh-Taylor(RT)、Richtmyer-Meshkov(RM)、Kelvin-Helmholtz(KH)等流体力学界面不稳定性诱导的湍流混合现象广泛存在于自然界和工程问题中,准确预测其演化具有十分重要的意义.考虑到实际问题的高雷诺数及复杂性,在可预见的未来,雷诺平均(RANS)方法仍将是工程实践中最具可实现性的选择.一般而言,传统RANS混合模型中至关重要的雷诺应力项是基于经典的Boussinesq线性涡粘假设封闭的.然而,这种线性模型无法充分描述在实际工程流动中发挥着重要作用的湍流各向异性特征.相比之下,非线性模型在这方面具有显著优势.本研究首次将基因表达编程(GEP)方法应用于湍流混合问题,发展了数据驱动的非线性K-L湍流混合模型.与常见的“黑箱”型机器学习模型不同,GEP模型显式给出模型方程,从而具有更强的物理可解释性.具体地,本研究基于二阶截断的广义Cayley-Hamilton非线性本构关系,利用GEP方法中的符号回归功能,形式化地给出了待封闭的模型系数与伽利略不变量之间的函数关系.此外,为了保证训练模型的物理性,我们将可实现性原则引入到了惩罚函数中.模型泛化性测试的结果表明:尽管新模型仅利用倾斜RT混合问题训练得到,但对于几个典型的混合问题均具有良好的鲁棒性.与标准的K-L模型相比,新模型不但具有更高的预测精度,而且能够更好地捕捉湍流的物理特性.此外,通过分析显式的封闭模型,本文进一步给出了新模型的预测效果得以提升的原因.

关键词： Turbulent mixing GEP method Nonlinear model Machine learning Interpretable model

来源：评论

学校读者我要写书评

暂无评论

FedECCR: Federated Learning Method with Encoding Comparison and Classification Rectification 19th

FedECCR: Federated Learning Method with Encoding Comparison...

引用

19th EAI International Conference on Collaborative Computing: Networking, Applications and Worksharing, CollaborateCom 2023

作者： Zeng, Yan Zheng, Hui Wang, Xin Zhang, Beibei Zhou, Mingyao Zhang, Jilin Ren, YongJian School of Computer Science and Technology Hangzhou Dianzi University Hangzhou310018 China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou310018 China Data Security Governance Zhejiang Engineering Research Center Hangzhou310018 China Zhejiang Lab Hangzhou311100 China Hangzhou Huawei Communication Technology Co. Ltd. Hangzhou310052 China

ISBN: (纸本)9783031545306

Federated learning is a distributed training method that integrates multi-party data information using privacy-preserving technologies through dispersed client data sets to jointly construct a global model under the coordination of a central server. However, in practical applications, there is a high degree of data distribution skewness among clients, which causes the optimization direction of the client models to diverge, resulting in model bias and reducing the accuracy of the global model. Existing methods require the calculation and transmission of much information to correct the optimization direction of the client models, or only roughly limit the deviation of the client models end-to-end, ignoring targeted processing of the internal structure of the model, resulting in unclear improvement effects. To address these problems, we propose a federated optimization algorithm FedECCR based on encoding contrast and classification correction. This algorithm divides the model into an encoder and a classifier. It utilizes prototype contrastive training of the model encoder and unbiased classification correction of the classifier. This approach notably improves the accuracy of the global model while maintaining low communication costs. We conducted experiments on multiple data sets to evaluate the validity of our method, and the quantified results showed that FedECCR can improve the global model classification accuracy by approximately 1% to 6% compared to FedAvg, FedProx, and MOON. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Research on Prediction Method for Pivotal Indicator of Hospital Medical Quality Using Decision Tree

Research on Prediction Method for Pivotal Indicator of Hospi...

引用

2015 6th IEEE International Conference on Software Engineering and Service Science(ICSESS 2015)

作者： Liujian Chen Lujia Bi Huayou Si Jilin Zhang Yongjian Ren Key Laboratory of Complex System Modeling and Simulation Ministry of Education Department of Computer Science and Technology Hangzhou Dianzi University Department of Information First Hospital of Jiaxing

Indicators of medical quality is the main basis of medical quality evaluation, predictive analyzing the indicators by using data mining technology, we can find and solve the problems of hospital quality management more timely. The study, basing on the medical homepage records, analyzes the key indicators of the hospital medical quality by decision tree C4.5 algorithm. Decision tree is a prediction model which can assist hospital to make related decision on medical quality management issues. By using decision tree C4.5 algorithm with appropriate modification, a high quality model of decision tree can be made. It can not only do the statistic of medical quality indicators, but also predict the indicators with high relative accuracy to improve hospital’s medical quality management.

关键词： medical quality data mining decision tree C4.5

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：