Construction of the Concept Drift Detection Model Based on the Information Entropy of Feature Distribution and Dynamic Weighting Algorithm

SUN Xue; LI Kun-lun; HAN Lei; BAI Xiao-liang

doi:10.3969/j.issn.0372-2112.2015.07.016

您当前的位置：

首页 >

文章列表页 >

Construction of the Concept Drift Detection Model Based on the Information Entropy of Feature Distribution and Dynamic Weighting Algorithm

更新时间：2025-07-16

- Construction of the Concept Drift Detection Model Based on the Information Entropy of Feature Distribution and Dynamic Weighting Algorithm
- Acta Electronica Sinica Vol. 43, Issue 7, Pages: 1356-1361(2015)
- 作者机构：
  
  1. 河北大学工商学院,河北,保定,071002
  2. 河北大学电子信息工程学院,河北,保定,071000
  3. 河北大学工商学院,河北,保定,071002
  4. 河北大学电子信息工程学院,河北,保定,071000
- 作者简介：
- 基金信息：
  
  National Natural Science Foundation of China (No.61073121);Natural Science Foundation of Hebei Province (No.F2013201170);National Key Technology Research and Development Program of the Ministry of Science and Technology (No.2013BAK07B04);Key Project of Science and Technology Research in Higher Education of Hebei Province (No.ZD2014008);Youth foundation of Hebei University (No.2010Q17)
- DOI：10.3969/j.issn.0372-2112.2015.07.016
  CLC： TP391.4TP181
- Published：2015
- 稿件说明：
移动端阅览
SUN Xue, LI Kun-lun, HAN Lei, et al. Construction of the Concept Drift Detection Model Based on the Information Entropy of Feature Distribution and Dynamic Weighting Algorithm[J]. Acta Electronica Sinica, 2015, 43(7): 1356-1361.
DOI：

SUN Xue, LI Kun-lun, HAN Lei, et al. Construction of the Concept Drift Detection Model Based on the Information Entropy of Feature Distribution and Dynamic Weighting Algorithm[J]. Acta Electronica Sinica, 2015, 43(7): 1356-1361. DOI： 10.3969/j.issn.0372-2112.2015.07.016.

摘要

现有的概念漂移算法大多建立在数据流的分类模型上

忽略了特征空间与样本空间的分布特点

以及特征选择和加权的重要性.针对此问题提出了一种基于特征项分布的信息熵及特征动态加权算法

从概念漂移的动态演化性出发

根据样本和特征空间的拟合程度

运用特征信息熵理论对数据流中的概念漂移现象进行捕捉

以实现新旧概念的过渡.利用改进的隐含Dirichlet模型特征动态加权算法

以解决当前特征与历史特征的权重确定和无效特征的裁剪问题.在公开的语料库CCERT和Trec06上的测试实验证明了所提出算法的有效性.

Abstract

Most of the existing concept drift algorithm focuses on the classification model data streams

some of which overlook the distribution of the feature space and sample space

and the importance of feature selection and weighting.To solve this problem

we propose a dynamic information entropy and feature weighting algorithm based on the distribution of feature items from the dynamic evolution of the concept drift departure.To realize the concept transition

we capture the concept drifting of the data stream by the information entropy

according to the fitness degree between the sample and feature space.We improve the feature dynamic weighting latent dirichlet model

to overcome the problem of the current and historical feature weight assignment

as well as cropping the invalid features.Furthermore

the validity of the proposed algorithm was confirmed by the test in open corpus CCERT and Trec06.

关键词

Keywords

references

Views

1479

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

An Incremental Density-Based Clustering Algorithm for Concept Drift Detection and Adaption over Data Stream

Concept Drift Adaptive Prediction Method Based on Dynamic Sample Selection

Improved Adaptive Model Pools for Online Anomaly Detection Algorithms

Concept Drift Detection of Industrial Data Flow Based on Multivariate Region Set Partition

Fast PL-SLAM Algorithm Based on Improved Keyframe Extraction Strategy

Related Author

LU Hao-yang

FAN Yu-lei

GAO Nan

YANG Liang-huai

DAI Jin

LI Hao

WANG Guo-yin

XIANG Qiu-yan

Related Institution

College of Computer Science and Technology, Zhejiang University of Technology

Chongqing Key Laboratory of Computational Intelligence

School of Computer Science, Chongqing University of Posts and Telecommunications

School of Software, Chongqing University of Posts and Telecommunications

College of Computer and Information Science， Chongqing Normal University

⁰