检索结果-内蒙古大学图书馆

Combined deep belief network in deep learning with affinity propagation clustering algorithm for roller bearings fault diagnosis without data label

引用

JOURNAL OF VIBRATION AND CONTROL 2019年第2期25卷 473-482页

作者： Xu, Fan Tse, Peter W. City Univ Hong Kong Dept Syst Engn & Engn Management Hong Kong Peoples R China

Unlike many traditional feature extraction methods of vibration signal such as ensemble empirical mode decomposition (EEMD), deep belief network (DBN) in deep learning can extract the useful information automatically and reduce the reliance on experts, with signal processing technology, and troubleshooting experience. In conventional fault diagnosis, data labels are required for classifiers such as support vector machine, random forest, and artificial neural networks. These are usually based on expert knowledge, for training and testing. But the process is usually tedious. The clustering model, on the other hand, can finish the roller bearings fault diagnosis without data labels, which is more efficient. There are some common clustering models which include fuzzy C-means (FCM), Gustafson-Kessel (GK), Gath-Geva (GG) models, and affinity propagation (AP). Unlike FCM, GK, and GG, which require knowledge or experience to pre-set the number of cluster center points, AP clustering algorithm can obtain the cluster center point according to the responsibility and availability calculations for all data points automatically. To the best of the authors' knowledge, AP is rarely used for fault diagnosis. In this paper, a method which combines DBN, with several hidden layers, and AP for roller bearings fault diagnosis is proposed. For data visualization, the principal component analysis (PCA) is deployed to reduce the dimension of the extracted feature. The first two principal components are employed as the input of the FCM, GK, GG, and AP models for roller bearings faults diagnosis. Compared with other combination models such as EEMD-PCA-FCM/GK/GG and DBN-PCA-FCM/GK/GG, the proposed method, from the experimental results, is superior to the aforementioned combination models.

关键词： Deep belief network deep learning affinity propagation clustering algorithm roller bearings fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient clustering algorithm for Magnetic Induction-Based Underwater Wireless Sensor Networks

引用

IEEE ACCESS 2019年 7卷 5975-5983页

作者： Wang, Sai Nguyen, Thu L. N. Shin, Yoan Soongsil Univ Sch Elect Engn Seoul 06978 South Korea

Magnetic induction (MI) communication is a promising technology for next-generation low-power underwater wireless sensor networks (UWSNs). clustering algorithm design becomes an important and challenging issue in today's MI-based UWSNs. In contrast to the conventional approaches which suffer from continuous movement of ocean current and traffic loads in different areas of the network, we consider a clustering algorithm based on the Voronoi diagram and node density distribution to improve the energy efficiency and to prolong the network lifetime. In particular, we propose a jellyfish breathing process for cluster head selection and an automatic adjustment algorithm for sensor nodes. The simulation results show that the proposed clustering algorithm achieves a high network capacity rate and a good equalization for the remaining energy.

关键词： Underwater sensor network magnetic induction communication clustering algorithm Poisson point distribution Voronoi diagram jellyfish breathing process

来源：评论

学校读者我要写书评

暂无评论

Identifying trip ends from raw GPS data with a hybrid spatio-temporal clustering algorithm and random forest model: a case study in Shanghai

引用

TRANSPORTATION PLANNING AND TECHNOLOGY 2019年第8期42卷 739-756页

作者： Zhou, Yang Yang, Chao Zhu, Rongrong Tongji Univ Coll Transportat Engn Minist Educ Key Lab Rd & Traff Engn 4800 Caoan Rd Shanghai Peoples R China ZheJiang Dahua Technol Co Ltd Hangzhou Zhejiang Peoples R China

Smartphones have been advocated as the preferred devices for travel behavior studies over conventional surveys. But the primary challenges are candidate stops extraction from GPS data and trip ends distinction from noise. This paper develops a Resident Travel Survey System (RTSS) for GPS data collection and travel diary verification, and then uses a two-step method to identify trip ends. In the first step, a density-based spatio-temporal clustering algorithm is proposed to extract candidate stops from trajectories. In the second step, a random forest model is applied to distinguish trip ends from mode transfer points. Results show that the clustering algorithm achieves a precision of 96.2%, a recall of 99.6%, mean absolute error of time within 3?min, and average offset distance within 30 meters. The comprehensive accuracy of trip ends identification is 99.2%. The two-step method performs well in trip ends identification and promotes the efficiency of travel survey systems.

关键词： Travel survey GPS data trip end identification clustering algorithm smartphone case study

来源：评论

学校读者我要写书评

暂无评论

A K-anonymous clustering algorithm based on the analytic hierarchy process

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2019年 59卷 76-83页

作者： Wang, Kun Zhao, Wei Cui, Junjie Cui, Yanpeng Hu, Jianwei Xidian Univ Sch Cyber Engn Xian 710071 Shaanxi Peoples R China

To protect the privacy of users, tables generally must be anonymized before publication. All existing anonymous methods have deficiencies. They do not consider the differences in attributes, or the optimization of information loss and time efficiency. his paper proposes a new method called KACM to realize k-anonymity. This method is mainly used for hybrid tables. The calculation of the distance between records considers the connection between quasi-identifier attributes and sensitive attributes, their effect on the sensitive privacy, and the information loss during the anonymity process. In the clustering process, the records with the minimum distance are always selected to add, and the clustering is individually controlled according to k to realize the equalization division of the equivalence class and reduce the total amount of distance calculation. Finally, the validity and practicability of the method are proved using theory and experiment. (C) 2019 Elsevier Inc. All rights reserved.

关键词： clustering algorithm Analytic hierarchy process

来源：评论

学校读者我要写书评

暂无评论

Plane segmentation and fitting method of point clouds based on improved density clustering algorithm for laser radar

引用

INFRARED PHYSICS & TECHNOLOGY 2019年 96卷 133-140页

作者： Xu, Xiaobin Luo, Minzhou Tan, Zhiying Zhang, Min Yang, Hao Hohai Univ Coll Mech & Elect Engn Changzhou 213022 Peoples R China Hohai Univ Jiangsu Key Lab Special Robot Technol Changzhou 213022 Peoples R China

Plane segmentation and fitting method of point clouds based on improved density clustering algorithm is put forward. We proposed the plane segmentation and fitting framework, which comprises of four steps: coordinate transformation, filtering, coarse segmentation, fine segmentation, plane fitting. The global coordinates of laser radar are deduced. Abnormal points are removed using statistical filtering based on Gaussian distribution. After filtering, Point clouds are segmented roughly adopting improved density clustering algorithm with proposed threshold, which is originally related to the resolution of laser radar. The point clouds are segmented furthermore with normal vector, which could make up for shortcomings, which are over-segmentation and under segmentation. Finally planes are fitted with normal vector and centroid point. The laser radar was designed, and plane segmentations and fitting were carried out. The experimental results show that it is effective and automatic for plane segmentation with proposed method.

关键词： Segmentation Laser radar SLAM clustering algorithm Variable threshold

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Compensation Based on K-Means clustering algorithm for Nyquist PAM-4 VLC System

引用

IEEE PHOTONICS TECHNOLOGY LETTERS 2019年第12期31卷 935-938页

作者： Ma, Jie He, Jing Shi, Jin Zhou, Zhihua Deng, Rui Hunan Univ Coll Comp Sci & Elect Engn Changsha 410082 Hunan Peoples R China

In visible light communication (VLC) systems, the nonlinear effects induced by many devices, such as the electrical amplifiers and optoelectronic devices, can significantly degrade the overall system performance. In this letter, to mitigate the nonlinear distortion effects, a clustering algorithm based on k-means is proposed and experimentally demonstrated in the VLC systems. The experimental results show that with the help of clustering algorithm to compensate the nonlinear effects, the bit error rate (BER) can be reduced from 2.4x10(-1) to 3.6x10(-3). Moreover, the 400-Mbit/s Nyquist PAM-4 signal over 80-cm free space transmission can be successfully achieved.

关键词： Visible light communication (VLC) pulse amplitude modulation (PAM) Nyquist filtering clustering algorithm

来源：评论

学校读者我要写书评

暂无评论

A clustering algorithm for scintillator signals applied to neutron and gamma patterns identification

引用

FUSION ENGINEERING AND DESIGN 2019年第PartB期146卷 2110-2114页

作者： Pollastrone, Fabio Cardarilli, Gian Carlo Riva, Marco Pereira, Rita Costa Fernandes, Ana Cruz, Nuno Podda, Salvatore Pompili, Fulvio Pilion, Mario Angelone, Maurizio Marocco, Daniele Belli, Francesco ENEA CR Frascati Dipartimento FSN Via E Fermi 45 I-00044 Frascati Roma Italy Univ Roma Tor Vergata Dept Elect Engn Rome Italy Univ Lisbon Inst Super Tecn Inst Plasmas & Fusao Nucl P-1049001 Lisbon Portugal

In several nuclear applications, scintillators, coupled with a photomultiplier and pulse amplifier, are used in order to detect high energy particles, i.e. neutrons and gamma rays. The different particles incident on the scintillator produce electrical pulses having different shape;moreover, the amplitude of these signals is related to the particles energy. The electrical pulses of the scintillator chain are acquired by digital systems that, generally, perform a triggered acquisition consisting of a stream of pulse windows. The aim of this study is the development of a simplified clustering algorithm able to produce reference patterns in compliance with the pattern recognition algorithm based on the matched filter technique, starting from a stream of pulses generated by particles having different energy and type. This paper contains a general description of the clustering algorithm and of the main customizations performed for the scintillator signals. In order to test in real case the efficiency, the algorithm has been applied on the data acquired during a radiation test performed at Frascati Neutron Generator for Stilbene scintillator. The results show that this algorithm works properly, deriving the centroids of the clusters representing the neutron and gamma shapes, together with their occurrences in the analysed data stream.

关键词： clustering algorithm Digital signal processing Stilbene scintillator Neutron and gamma discrimination Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A hybrid PSO-SVM model based on clustering algorithm for short-term atmospheric pollutant concentration forecasting

引用

TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE 2019年第Sep.期146卷 41-54页

作者： Chen, Shuixia Wang, Jian-qiang Zhang, Hong-yu Cent S Univ Sch Business Changsha 410083 Hunan Peoples R China

Air pollution can lead to a wide range of hazards and can affect most organisms on Earth. Therefore, managing and controlling air pollution has become a top priority for many countries. An effective short-term atmospheric pollutant concentration forecasting (SAPCF) can mitigate the negative effects of atmospheric pollution. In this paper, we propose a new hybrid forecasting model for SAPCF. Firstly, we analyse the influential factors of pollutants to obtain the optimal combination of input variables. Secondly, we use a clustering algorithm to enhance the regularity of our modelling data. Thirdly, we build a particle swarm optimisation (PSO)-support vector machine (SVM) hybrid model called PSO-SVM and perform a case study in Temple of Heaven, Beijing to test its forecasting accuracy and validate its performance against three contrastive models. The first model inputs all possible variables in equal weight without influence factor analysis. The second model integrates the same input variables used in the proposed model without clustering. The third model inputs these same variables with genetic-algorithm optimised SVM parameters. The comparison amongst these models demonstrates the superior performance of our proposed hybrid model. We further verify the forecasting results of our hybrid model by conducting statistical tests.

关键词： Short-term atmospheric pollutant concentration forecasting Influential factors analysis clustering algorithm Particle swarm optimisation Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Massive Data Mining algorithm for Web Text Based on clustering algorithm

引用

JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS 2019年第2期23卷 362-365页

作者： Luo, Nan-Chao Aba Teachers Univ Sch Math & Comp Sci Wenchuan 623002 Sichuan Peoples R China

The massive data of Web text has the characteristics of high dimension and sparse spatial distribution, which makes the problems of low mining precision and long time consuming in the process of mining mass data of Web text by using the current data mining algorithms. To solve these problems, a massive data mining algorithm of Web text based on clustering algorithm is proposed. By using chi square test, the feature words of massive data are extracted and the set of characteristic words is gotten. Hierarchical clustering of feature sets is made, TF-IDF values of each word in clustering set are calculated, and vector space model is constructed. By introducing fair operation and clone operation on bee colony algorithm, the diversity of vector space models can be improved. For the result of the clustering center, K-means is introduced to extract the local centroid and improve the quality of data mining. Experimental results show that the proposed algorithm can effectively improve data mining accuracy and time consuming.

关键词： clustering algorithm Web text massive data data mining algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel ICA-based clustering algorithm for heart arrhythmia diagnosis

引用

PATTERN ANALYSIS AND APPLICATIONS 2019年第2期22卷 285-297页

作者： Naseri, E. Ghaffari, A. Abdollahzade, M. KN Toosi Univ Technol Dept Mech Engn Tehran Iran KN Toosi Univ Technol CardioVasc Res Grp CVRG Tehran Iran

Thousands of people around the world are suffered from heart diseases;however, a considerable amount of them can have a chance of survival if there is an accurate and accessible diagnosis method. This paper introduces a new method for clustering of Holter electrocardiogram QRS complexes based on imperialist competitive optimization algorithm (ICA) which is the main contribution of this paper to raise the accuracy of diagnosis and find the methods for heart disease accessible machine diagnosis. The procedure of clustering is carried out using a mathematical modeling based on defining a cost function which is the ratio between the distance of each pattern's features within each cluster (DWC) and the distance between the clusters. Hence, the clustering problem is reduced to an optimization process. The recently introduced optimization algorithm of ICA, inspired by imperialistic competition, is applied to solve the resulting optimization problem and to find the appropriate weighting factors. To demonstrate the effectiveness of the proposed clustering method, it was implemented on 5 set of MIT records obtained from MIT-BIH Arrhythmia Database records and also on hand-designed datasets (HDD). HDDs developed by selecting and combining some sets of computer-based simulated QRS complexes developed by CVRG group. To compare the effectiveness of the proposed approach, simulated annealing and genetic algorithm were also employed as other optimization algorithms. The results were promising and showed the ability of the proposed method for the clustering applications.

关键词： Feature extraction Curve length method Optimization algorithm Imperialist competitive algorithm clustering algorithm ECG clustering

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：