检索结果-内蒙古大学图书馆

A New Cloudlet Placement Method Based on affinity propagation for Cyber-Physical-Social Systems in Wireless Metropolitan Area Networks

引用

IEEE ACCESS 2020年 8卷 34313-34325页

作者： Peng, Kai Qian, Xingda Zhao, Bohai Zhang, Kejia Liu, Yang Huaqiao Univ Coll Engn Quanzhou 362021 Peoples R China Heilongjiang Univ Sch Math Sci Harbin 150080 Peoples R China Univ Sci & Technol Liaoning Sch Comp Sci & Software Engn Anshan 114051 Peoples R China

Cyber-Physical-Social Systems (CPSS) integrates the cyber, physical and social spaces together. There are a large number of mobile users in CPSS that need low latency services. Fortunately, mobile edge computing (MEC) is a novel technology which can provide such services. The edge server plays a key role in MEC, but how to manage the edge server is an important challenge. For one thing, the number of cloudlets and the resource are limited. For another, the number of mobile devices (MDs) is very large and randomly distributed. And thus, how to determine the suitable number of cloudlets while serving the maximum number of MDs is significant. To this end, a new cloudlet placement method based on improved affinity propagation (AP) algorithm is proposed to solve the above problems. More specially, the improved AP algorithm can obtain the least number of cloudlets while covering the largest number of MDs. In addition, the load balancing strategy is used to ensure that the load of each cloudlet maintains a balanced state. Last but not the least, our proposed method can be used in scenarios where users move.

关键词： Cloud computing Load management Resource management Servers Heuristic algorithms Edge computing Mobile handsets Mobile edge computing cloudlet placement affinity propagation algorithm load balancing

来源：评论

学校读者我要写书评

暂无评论

affinity propagation algorithm in WLAN network deployment

Affinity propagation algorithm in WLAN network deployment

引用

International Symposium on Instrumentation and Measurement, Sensor Network and Automation

作者： Yushun Wang Peng Lei Hong Xu School of Information Science and Engineering Lanzhou University Lanzhou China

ISBN: (纸本)9781479927173

The coverage region of WLAN network is limited compare with cell phone system such as GSM and WCDMA. The favorable area to deploy WLAN is the area which has strong demand for wireless network. How to identify the needs and guide the deployment of WLAN, that isn't a easy issue. It will waste the investment if we deploy the WLAN in improper places. This paper proposes a solution which can collect customer feedback with the help of smart phone client software and affinity propagation algorithm is applied to determine which region should be deploy first according to giant user feedback from that client software. Actual results show that the method is feasible and effective. It can significantly improve the accuracy of deployment of WLAN and efficiency of operations.

关键词： component WLAN Telecom operator mobile client affinity propagation algorithm clustering algorithm GIS

来源：评论

学校读者我要写书评

暂无评论

Network Pruning via Weight Enhancement of Adaptive Exemplar Filters 23

Network Pruning via Weight Enhancement of Adaptive Exemplar ...

引用

Proceedings of the 2023 12th International Conference on Computing and Pattern Recognition

作者： Zhoufeng Liu Ke Yang Ningyu Chai Haipeng Jiao Ruimin Yang Zhongyuan University of Technology China

ISBN: (纸本)9798400707988

The redundant architecture and inefficient parameters of Convolutional Neural Networks (CNNs) can be drastically decreased by the model compression approaches while the network model's high performance is maintained. The structured model compression technique filter pruning is a persistent subject of research since it is hardware-friendly. Whereas many filter pruning methods use training data and human empirical design to determine important filters, this might result in inaccurate results after fine-tuning and the creation of suboptimal compression networks. In this paper, we propose the Weight Enhancement of Adaptive Exemplar Filter pruning algorithm (WEAEF), which merely processes the weights of filters to decide which filters to keep at each layer automatically, while strengthening the critical filter weights thereby improving the accuracy of the pruned network without destroying the model structure. affinity propagation (AP), a clustering algorithm, uses similarity information sent between data points to automatically locate grouping centers. Inspiring by this, we implement the AP algorithm to make filters as data points for discovering filters that, via the similarities of filters, represent the performance of all filters within the corresponding layer. To be able to obtain enhanced accuracy after fine-tuning, we further creatively deliver the Weight Enhancement (WD) module, which improves accuracy by boosting the utility of the filter weights yet maintaining the model's structure. Our method has been shown to be superior to other state-of-the-art methods in the datasets CIFAR-10 and ILSVRC-2012.

关键词： affinity propagation algorithm Filter pruning Model Compression Weight Enhancement module

来源：评论

学校读者我要写书评

暂无评论

Intelligent scanning for optimal rock discontinuity sets considering multiple parameters based on manifold learning combined with UAV photogrammetry

引用

ENGINEERING GEOLOGY 2022年 309卷

作者： Liu, Yongqiang Chen, Jianping Tan, Chun Zhan, Jiewei Song, Shengyuan Xu, Wanglai Yan, Jianhua Zhang, Yansong Zhao, Mingyu Wang, Qing Jilin Univ Coll Construction Engn Changchun 130026 Peoples R China China Water Northeastern Invest Design & Res Co Lt Changchun 130000 Jilin Peoples R China Engn Technol Res Ctr Minist Water Resource Cold Re Changchun 130000 Jilin Peoples R China Changan Univ Coll Geol Engn & Geomatics Xian 710054 Peoples R China

The Sichuan-Tibet railway, which spans many alpine canyon regions, is being built in southwestern China. Investigating the characteristics of rock discontinuity sets is the basis for identifying dangerous rock masses above the tunnel portals. The traditional methods of identifying discontinuity sets usually consider orientations and ignore other parameters, which results in incorrect guidance for rock engineering. To this end, the affinity propagation (AP) algorithm based on modified isometric mapping (Isomap) is proposed for partitioning discontinuity sets based on orientation, trace length, and aperture. The new unsupervised algorithm (ISOAP) uses manifold learning to complete the transformation process for orientations from spherical vectors to scalars and avoids selecting the initial clustering center to achieve global optimization. The Silhouette Index is used to intelligently scan the optimal clustering results. The proposed algorithm is tested on a complex artificial data set and on Shanley and Mahtab's data set. Since accurately obtaining discontinuity information is impossible by traditional means (i.e., using geological compasses and measurement tapes) due to the existence of a mass of high and steep slopes, the ISOAP algorithm is combined with semiautomatic technology based on unmanned aerial vehicle (UAV) photogrammetry and applied to a rock slope located along the railway. The introduction of manifold learning is beneficial for quickly applying abundant unmodified clustering algorithms to rock engi-neering and searching the optimal algorithm suitable for analyzing the structural characteristics of a specific fractured rock mass. The proposed method can simplify rock engineering analyses and provide more reasonable results.

关键词： Discontinuity sets Multiple parameters Manifold learning affinity propagation algorithm UAV photogrammetry

来源：评论

学校读者我要写书评

暂无评论

Batch process fault detection for multi-stage broad learning system

引用

NEURAL NETWORKS 2020年 129卷 298-312页

作者： Peng, Chang RuiWei, Lu Kang, Olivia Kai, Wang Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China

In the real industrial production process, some minor faults are difficult to be detected by multivariate statistical analysis methods with mean and variance as detection indicators due to the aging equipment and catalyst deactivation. With structural characteristics, deep neural networks can better extract data features to detect such faults. However, most deep learning models contain a large number of connection parameters between layers, which causes the training time-consuming and thus makes it difficult to achieve a fast-online response. The Broad Learning System (BLS) network structure is expanded without a retraining process and thus saves a lot of training time. Considering that different stages of the batch production process have different production characteristics, we use the affinity propagation (AP) algorithm to separate the different stages of the production process. This paper conducts research on a multi-stage process monitoring framework that integrates AP and the BLS. Compared with other monitoring models, the monitoring results in the penicillin fermentation process have verified the superiority of the AP-BLS model. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： affinity propagation algorithm Broad learning system Penicillin fermentation process Fault detection

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Nonlinear Regression with Missing Data UsingQuasilinearKernel

引用

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2020年第12期15卷 1791-1800页

作者： Zhu, Huilin Tian, Yanling Ren, Yanni Hu, Jinglu Waseda Univ Grad Sch Informat Prod & Syst Wakamatsu Ku Hibikino 2-7 Kitakyushu Fukuoka 8080135 Japan

In both the research and engineering fields, missing data is a serious problem that cannot be overlooked. Therefore, available datasets with missing data are a challenge to be modeled by conventional global prediction models. In this paper, we propose a hybrid model consisting of an autoencoder and a gated linear network for solving the regression problem under missing value scenario. A sophisticated modeling and identifying algorithm is developed. First, an extended affinity propagation (AP) clustering algorithm is applied to obtain a self-organized competitive net dividing the datasets into several clusters. Second, a multiple imputation tool with topp%winner-take-all denoising autoencoders (DAE) is introduced to realize better predictions of missing values, in which rough estimates of missing values by using the mean imputation and similarity method within the clusters are used as teacher signals of DAE. Finally, a gated linear network is designed to construct a piecewise linear regression model with interpolations in the exact same way as a support vector regression with a quasilinear kernel composed using the cluster information obtained in the AP clustering step. Based on the experiments of five datasets, our proposed method demonstrates its effectiveness and robustness compared with other traditional kernels and state-of-the-art methods, even on datasets with a large percentage of missing values. (c) 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

关键词： nonlinear regression missing data affinity propagation algorithm denoising autoencoder support vector regression quasilinear kernel

来源：评论

学校读者我要写书评

暂无评论

Quality relevant over-complete independent component analysis based monitoring for non-linear and non-Gaussian batch process

引用

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS 2020年 205卷 104140-104140页

作者： Peng, Chang Kai, Wang Pu, Wang Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China

A large number of multivariate statistical methods have been applied to process monitoring, but conventional methods only extract limited feature information that often cannot effectively monitor the quality related changes of production characteristics in batch processes. In order to improve the effect of the process monitoring, this paper proposes a batch process monitoring method based on Multistage Over-complete Independent Component Analysis (OICA) algorithm. Firstly, the affinity propagation algorithm (AP) is used to divide the batch production process. Secondly, the extra quality information extracted by Partial Least Squares (PLS) algorithm is input into OICA algorithm. Finally, a monitoring model is established for process monitoring in each sub-stage. The effectiveness of the proposed method has been verified by comparing with the conventional methods in the fed-batch penicillin fermentation process.

关键词： Batch process Fault monitoring affinity propagation algorithm Over-complete independent component analysis Partial least squares

来源：评论

学校读者我要写书评

暂无评论

SDN-Based Load Balancing Scheme for Multi-Controller Deployment

引用

IEEE ACCESS 2019年 7卷 39612-39622页

作者： Li, Guoyan Wang, Xinqiang Zhang, Zhigang Tianjin Chengjian Univ Sch Comp & Informat Engn Tianjin 300384 Peoples R China Tianjin Sino German Univ Appl Sci Sch Software & Commun Tianjin 300350 Peoples R China

Software-defined networking (SDN) separates the control plane from the data forwarding plane and realizes the flexible management of the network resources. With the explosive growth of network traffic and scale, multi-controllers need to be deployed to improve the scalability and reliability of the control plane. However, unreasonable subdomain partitioning of SDN controllers may cause the unbalanced distribution of controller loads and reduces the communication performance of the network. Therefore, in this paper, a dynamic multi-controller deployment scheme based on load balancing is proposed. We transform the flow requests into a queuing model and consider the traffic propagation delay and the capacity of controllers as two main factors affecting the deployment of the multi-controllers. In the initial static network, a modified affinity propagation algorithm (PSOAP) based on particle swarm optimization is proposed to solve the problem of clustering performance being affected by the initial values of the bias parameters and convergence coefficients, getting the reasonable network planning. With the dynamic traffic network, switches in different sub-domains are reassigned by breadth-first search (BFS) algorithm to achieve controller load balancing. The extensive evaluations demonstrate that the scheme can provide better stable, accurate, and load balancing multi-controller deployment when compared with affinity propagation (AP) and genetic algorithms.

关键词： affinity propagation algorithm load balancing queuing model software-defined networking

来源：评论

学校读者我要写书评

暂无评论

Stock price prediction based on stock price synchronicity and deep learning

引用

INTERNATIONAL JOURNAL OF FINANCIAL ENGINEERING 2021年第2期8卷

作者： Jing, Nan Liu, Qi Wang, Hefei Shanghai Univ SHU UTS SILC Business Sch Shanghai Peoples R China Renmin Univ China Int Coll Beijing Peoples R China

Deep learning technology has been widely used in the financial industry, primarily for improving financial time series prediction based on stock prices. To solve the problem of low fitting and poor accuracy in traditional stock price prediction models, this paper proposes a stock price prediction model based on stock price synchronicity and deep learning methods, which applied the stock price synchronicity theory in stock price trend analysis. This paper first uses the affinity propagation algorithm to build stock clusters, and then, based on convolution neural network (CNN), and feature weight to construct the stock price synchronicity factor. At last, the long short-term memory (LSTM) network with multifactor is built for stock price trend analysis. According to the theory of stock price synchronicity, the affinity propagation algorithm can find the potential related stocks of the target stock. The spatial data analysis ability of the CNN model provides a guarantee for the application in stock price synchronicity factor analysis. The LSTM model can better analyze the information contained in the stock price time series and predict the future price. The experimental results show that, compared with the traditional multilayer neural network model, the LSTM model has better accuracy in the trend prediction of the stock price. Simultaneously, the application of stock price synchronicity effectively improves the performance of the multifactor LSTM network.

关键词： Stock price synchronicity affinity propagation algorithm convolution neural network long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Localização de danos em estruturas isotrópicas com a utilização de aprendizado de máquina

Localização de danos em estruturas isotrópicas com a util...

引用

作者： Oliveira, Daniela Cabral de Universidade Estadual Paulista

Este trabalho introduz uma nova metodologia de Monitoramento da Integridade de Estruturas (SHM, do inglês Structural Health Monitoring) utilizando algoritmos de aprendizado de máquina não-supervisionado para localização e detecção de dano. A abordagem foi testada em material isotrópico (placa de alumínio). Os dados experimentais foram cedidos por Rosa (2016). O banco de dados disponibilizado é abrangente e inclui medidas em diversas situações. Os transdutores piezelétricos foram colados na placa de alumínio com dimensões de 500 x 500 x 2mm, que atuam como sensores e atuadores ao mesmo tempo. Para manipulação dos dados foram analisados os sinais definindo o primeiro pacote do sinal (first packet), considerando apenas o intervalo de tempo igual ao tempo da força de excitação. Neste caso, na há interferência dos sinais refletidos nas bordas da estrutura. Os sinais são obtidos na situação sem dano (baseline) e, posteriormente nas diversas situações de dano. Como método de avaliação do quanto o dano interfere em cada caminho, foram implementadas as seguintes métricas: pico máximo, valor médio quadrático (RMSD), correlação entre os sinais, normas H2 e H∞ entre os sinais baseline e sinais com dano. Logo após o cálculo das métricas para as diversas situações de dano, foi implementado o algoritmo de aprendizado de máquina não-supervisionado K-Means no matlab e também testado no toolbox Weka. No algoritmo K-Means há a necessidade da pré-determinação do número de clusters e isto pode dificultar sua utilização nas situações reais. Então, fez se necessário a implementação de um algoritmo de aprendizado de máquina não-supervisionado que utiliza propagação de afinidades, onde a determinação do número de clusters é definida pela matriz de similaridades. O algoritmo de propagação de afinidades foi desenvolvido para todas as métricas separadamente para cada *** paper introduces a new Structural Health Monitoring (SHM) methodology using unsupervised machine learning algorithms f

关键词： SHM Aprendizado de máquina não-supervisionado Algoritmo K-Means Algoritmo propagação de afinidade Unsupervised machine learning K-Means algorithm affinity propagation algorithm Dissertação de mestrado

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：