检索结果-内蒙古大学图书馆

International Symposium on Computer Science, Digital Economy and Intelligent Systems (CSDEIS)

作者： Mutovkina, N. Yu Kuznetsov, V. N. Tver State Tech Univ Tver Russia

ISBN: (纸本)9783030392161;9783030392154

This article is devoted to the problem of identifying the most effective intelligent agents suitable in their personal qualities for solving nonstandard, complex, creative tasks. The effectiveness of the decisions made by intelligent agents determines the productivity of the entire system. The possibilities of generating creative solutions to complex, non-standard problems largely depend on the state of intelligent agents. An intelligent agent, taking into account its inherent anthropomorphic properties and qualities, can be in various psycho-emotional states: from a depressed mood to creative uplift and insight. The states of the agent change over time, which he informs the system about at specified points in time. It is assuming that all agents provide reliable information about their states to the system. Based on the data obtained, the system should determine the most and least stable agents and redistribute the functions and responsibilities between them to maximize own utility function. The task is characterizing by the need to analyze large volumes of subjective information and belongs to the class of difficulty formalized tasks. To solve it, fuzzy clustering algorithms that are well implementing in the Matlab software environment can be using.

关键词： Intelligent active system Intelligent agent Fuzzy clustering Creative solutions Coordination problem Optimization Agent status fcm algorithm

来源：评论

学校读者我要写书评

暂无评论

Borrowers' credit quality scoring model and applications, with default discriminant analysis based on the extreme learning machine

引用

TECHNOLOGICAL FORECASTING AND SOCIAL CHANGE 2021年 165卷 120462-120462页

作者： Pang, Sulin Hou, Xianyan Xia, Lianhu Jinan Univ Sch Emergency Management Management Sch Inst Finance Engn Guangzhou 510632 Peoples R China Guangzhou Pearl River Vocat Coll Technol Sch Econ & Management Sch Emergency Ind Huizhou 516131 Guangdong Peoples R China Guangdong Emergency Technol Res Ctr Risk Evaluat Guangzhou 510632 Peoples R China

Through evaluating the weight of evidence method and calculating the information value (IV), this article proposes a method to evaluate the credit qualities of borrowers based on the extreme learning machine, the fuzzy c-means (fcm) algorithm, and the calculation of a confusion matrix. Through screening credit rating indexes, we established a credit scoring model of the borrower. In addition, we constructed formulas to determine the probability of default and default loss rate. The model also classifies the credit qualities of borrowers. In addition, we designed a selection algorithm for the borrower's credit quality rating index, and a borrower's credit quality rating algorithm. This paper collects sample data of 7706 borrowers of Renren loans from the Internet. The credit scores of the borrower, the default probability, and the default loss rate of each type of borrower are calculated, and the repayment status of borrowers are analyzed. We divided the borrowers into 7 grades and 5 grades by calculating a confusion matrix. The experimental results show that the overall accuracy of the credit scoring model is 98.5%, in which the accuracy for non-default samples is 98.9%, and the accuracy for default samples is 88.3%. The accuracy of the established credit quality rating model proved to be relatively high, and it can provide important reference values and scientific guidance for banks, financial institutions, and major financial platforms. It can also judge and predict default behavior.

关键词： Borrower credit score model Accuracy of default discrimination Extreme learning machine fcm algorithm Confusion matrix

来源：评论

学校读者我要写书评

暂无评论

Unsupervised hyperspectral feature selection based on fuzzy c-means and grey wolf optimizer

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2019年第9期40卷 3344-3367页

作者： Xie, Fuding Lei, Cunkuan Li, Fangfei Huang, Dan Yang, Jun Liaoning Normal Univ Coll Urban & Environm 850 Huanghe Rd Dalian Liaoning Peoples R China Liaoning Normal Univ Coll Comp Sci Dalian Liaoning Peoples R China

Hyperspectral image (HSI) with hundreds of narrow and consecutive spectral bands provides substantial information to discriminate various land-covers. However, the existence of redundant features/bands not only gives rise to increasing of computation time but also interferes the classification result of hyperspectral images. Obviously, it is a very challenging problem how to select an effective feature subset from original bands to reduce the dimensionality of the hyperspectral dataset. In this study, a novel unsupervised feature selection method is suggested to remove the redundant features of HSI by feature subspace decomposition and optimization of feature combination. Feature subset decomposition is achieved by the fuzzy c-means (fcm) algorithm. The optimal feature selection is based on the optimization process of grey wolf optimizer (GWO) algorithm and maximum entropy (ME) principle. To evaluate the effectiveness of the proposed method, experiments are conducted on three well-known hyperspectral datasets, Indian Pines, Pavia University, and Salinas. Six state-of-the-art feature selection methods are used to compare with the proposed method. Experimental results successfully confirm the superior performance of our proposal with respect to three classification accuracy indices overall accuracy (OA), average accuracy (AA) and kappa coefficient (kappa).

关键词： hyperspectral image feature selection fcm algorithm GWO algorithm

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic power prediction model based on parallel dendritic neural model

Photovoltaic power prediction model based on parallel dendri...

引用

第33届中国控制与决策会议

作者： Hao LI Tengfei ZHANG Yang YU Chen PENG College of Automation & College of Artificial Intelligence Nanjing University of Posts and Telecommunications School of Mechatronics Engineering and Automation Shanghai University

Dendritic neural model（DNM） has characteristics of a simple structure and a fast convergence ***,when a single DNM is applied to a scene with a large data set,the number of branch layers often needs to be increased,which makes the structure of DNM larger and leads to a poor prediction *** this perspective,this paper proposes a parallel-structure based DNM with multiple sub-networks,which uses a fuzzy C-means clustering（fcm） algorithm to divide the data *** fcm algorithm can effectively reduce the amount of data required for the training of each ***,actual photovoltaic data simulation results verify that the accuracy of the photovoltaic power prediction model can be further improved,and the proposed model is effective and efficiency.

关键词： Photovoltaic power prediction Dendritic neural model Parallel sub-networks fcm algorithm

来源：评论

学校读者我要写书评

暂无评论

Effective convolution method for privacy preserving in cloud over big data using map reduce framework

引用

IET SOFTWARE 2019年第3期13卷 187-194页

作者： Sudhakar, Katherapaka Farquad, M. A. H. Narshimha, G. Univ JNTUH Hyderabad Telangana India Islamic Univ Madinah Fac Comp & Informat Syst Medina Saudi Arabia JNTUH Karimnagar Telangana India

Cloud computing is used to connect several number of remote servers through Internet to accumulate and recover large data anywhere and anytime. As of the conventional privacy defending process, there is a possibility for malevolent assault on the sensitive information accumulated in the cloud. In this research, the authors have proposed a competent large data convert among privacy defending by Hadoop map reduce in the cloud. The procedure exploits fuzzy C-means clustering (fcm) algorithm grouping the data. For dimensionality reduction, map reduce framework will be used. In evaluation module, the recommended technique performed with the aid of K-nearest neighbour (KNN) classification algorithm in this phase using KNN technique to check the convolution process based on the threshold value, which is improving the utility of the privacy data. The consequence acquired illustrates that authors' proposed scheme has enhanced the clustering exactness and also accomplishes the effectual convolution procedure to improve the privacy. From the experimental results, the proposed research achieved an effective clustering accuracy 76.07% and the existing K-means approach gets the clustering accuracy of 73.5% which is minimum value when compared to the proposed researches. The suggested technique is implemented in JAVA with Cloud Sim platform.

关键词： data privacy pattern clustering Big Data parallel processing fuzzy set theory cloud computing security of data pattern classification nearest neighbour methods sensitive information Hadoop map dimensionality reduction evaluation module recommended technique KNN technique convolution process privacy data clustering exactness effectual convolution procedure effective clustering accuracy Cloud Sim platform effective convolution method big data remote servers conventional privacy defending process malevolent assault fcm algorithm K-means approach cloud computing privacy preserving map reduce framework Internet fuzzy C-means clustering algorithm K-nearest neighbour classification algorithm threshold value JAVA

来源：评论

学校读者我要写书评

暂无评论

Measuring Linear Density of Threads in Single-System-Melange Color Fabrics with fcm algorithm

引用

COLOR RESEARCH AND APPLICATION 2013年第6期38卷 456-462页

作者： Pan, Ruru Liu, Jihong Gao, Weidong Jiangnan Univ Sch Text & Clothing Key Lab Ecotext Wuxi Jiangsu Peoples R China

According to the color yarns in the fabric, the fabrics can be divided into three categories: solid color fabrics, single-system-melange color fabrics, and double-system-melange color fabrics. The density of solid fabrics can be inspected with gray-projection method or Fourier analysis method. But the methods cannot be applied to yarn-dyed fabrics directly. A method for detecting the density of single-system-melange color fabrics will be discussed in this article. By analyzing the pattern and color characters of single-system-melange color fabrics, fuzzy C-means algorithm is proposed to classify the colors in the fabric image based on CIELAB color space first. With the color segmentation results, the fabric can be divided into different blocks. The yarns can be located in different blocks with different average gray-levels, and then the number of yarns can be counted in each block. The linear density of threads can be obtained by counting the yarns in a unit length finally. The experiment proved that the algorithm proposed in this study can inspect the density of single-system-melange color fabric successfully. (c) 2012 Wiley Periodicals, Inc. Col Res Appl, 38, 456-462, 2013

关键词： linear density of threads single-system-melange color fabric fcm algorithm CIELAB color space color classification

来源：评论

学校读者我要写书评

暂无评论

A study on semi-supervised fcm algorithm

引用

KNOWLEDGE AND INFORMATION SYSTEMS 2013年第3期35卷 585-612页

作者： Zeng, Shan Tong, Xiaojun Sang, Nong Huang, Rui Huazhong Univ Sci & Technol Inst Pattern Recognit & Artificial Intelligence Wuhan 430074 Hubei Peoples R China Wuhan Text Univ Coll Math & Comp Sci Wuhan 430077 Hubei Peoples R China

Most variants of fuzzy c-means (fcm) clustering algorithms involving prior knowledge are generally based on the modification of the objective function or the clustering process. This paper proposes a new weighted semi-supervised fcm algorithm (SSfcm-HPR) that transforms the prior knowledge in the labeled samples into constraint conditions in terms of fuzzy membership degrees, assigns different weights according to the representativeness of the samples, and then uses the HPR multiplier to solve the clustering problem. The "representativeness" of the labeled samples is decided by their distances to the cluster centers they belong to. In this paper, we take the ratio of the largest to the second largest fuzzy membership degree from a labeled sample as its weight. This algorithm not only retains the fuzzy partition of the labeled samples, which guarantees the effective guidance on the clustering process, but also can detect whether a sample is an outlier or not. Moreover, when part of the supervised information of the labeled samples is wrong, this algorithm can reduce the influence of the incorrectly labeled samples on the final clustering results. The experimental evaluation on synthetic and real data sets demonstrates the efficiency and effectiveness of our approach.

关键词： fcm algorithm Semi-supervised clustering HPR multiplier Incorrectly labeled samples

来源：评论

学校读者我要写书评

暂无评论

Quality Evaluation of Marine Statistical Data on the Basis of Clustering algorithms

引用

JOURNAL OF COASTAL RESEARCH 2019年第Sup1期000卷 151-154页

作者： Cui, Yingji Xianyang Normal Univ Shaanix 712000 Peoples R China

The quality of marine statistical data is the life of marine statistical work, and it is the key to reflecting the level of marine statistical work, which is related to the credibility of marine statistical departments. Therefore, in marine statistics work, we need to establish perfect marine statistical data quality evaluation criteria. Only by meeting the basic standards will we gradually establish a comprehensive and systematic marine statistical data quality monitoring system, which will guarantee the authority of the marine statistical data. This paper further improves the quality of marine statistical data in China by using a clustering algorithm.

关键词： Quality evaluation marine statistical data clustering algorithms fcm algorithm

来源：评论

学校读者我要写书评

暂无评论

Watermark Scheme of Database Based on Fuzzy C-Means 19

Watermark Scheme of Database Based on Fuzzy C-Means

引用

2nd International Conference on Big Data Technologies (ICBDT) / 3rd International Conference on Business Information Systems Workshop (ICBIS)

作者： Di, Guandong Wang, Xiao Xian, Hequn Qingdao Univ 308 Ningxia Rd Qingdao Peoples R China Qingdao Ocean Shipping Mariners Coll 84 Ningxia Rd Qingdao Peoples R China

ISBN: (纸本)9781450371926

In order to protect the copyright of relational database data, a watermark embedding algorithm based on fcm clustering is proposed. When embedding, the embedded watermark data is filtered by the clustering algorithm, and then embedded by the user key watermark. The algorithm can only extract the watermark if it has the key and the secret clustering parameters. The experimental results show that the accuracy of watermark extraction is high, and the algorithm is also excellent in security and concealment. Even in the case of key leakage, the security of the database can be guaranteed.

关键词： Relation database watermarking fcm algorithm Imperceptibility

来源：评论

学校读者我要写书评

暂无评论

An Intrusion Detection Scheme Combining fcm and Kohonen Network 11

An Intrusion Detection Scheme Combining FCM and Kohonen Netw...

引用

11th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA)

作者： Chen Ming-xia Zhang Han Li Shun-yan Dept Guilin Univ Technol Guilin City 541006 The Guangxi Zhu Peoples R China

ISBN: (纸本)9781728121659

In order to solve the shortcomings of traditional industrial control network intrusion detection schemes, such as insensitivity to detection samples and inaccurate judgment of internal anomalies. An industrial control network intrusion detection scheme based on fcm algorithm and supervised Kohonen is proposed. fcm algorithm, fcm-GRNN network algorithm, fcm-BP network algorithm, fcm-Kohonen network algorithm and fcm-S_ Kohonen network algorithm are built on MATLAB software platform to test DARPA data samples. The accuracy of clustering results of different types of intrusion is counted according to five algorithms. The scheme can detect NORMAL, U2R, R2L, DoS and PRB network attacks more accurately, and the overall average classification accuracy rate is more than 95%.

关键词： control net fcm algorithm fcm-S_Kohonen network algorithm clustering algorithm Network intrusion detection

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：