| 基于遗传神经网络的相似重复记录检测方法研究 |
| |
| 引用本文： | 肖蕾,郭乐江,胡亚慧,程敏. 基于遗传神经网络的相似重复记录检测方法研究[J]. 舰船电子工程, 2011, 31(2): 168-170,176 |
| |
| 作者姓名： | 肖蕾 郭乐江 胡亚慧 程敏 |
| |
| 作者单位： | 空军雷达学院,武汉,430019 |
| |
| 摘 要： | 设计实现了一个相似重复记录检测系统，该系统包括预处理模块、聚类模块、字段匹配模块和记录匹配模块，支持聚类算法和字段匹配算法的定制扩充。并通过实验对比了几种著名的算法，实验结果表明该系统提高了相似重复记录检测的精确度。
|
| 关 键 词： | 遗传神经网络 相似重复记录检测系统 聚类算法 字段匹配算法 |
Study on Approximately Duplicate Record Detection Method Based on Genetic Neural Network |
| |
| Xiao Lei,Guo Lejiang,Hu Yahui,Cheng Min. Study on Approximately Duplicate Record Detection Method Based on Genetic Neural Network[J]. Ship Electronic Engineering, 2011, 31(2): 168-170,176 |
| |
| Authors: | Xiao Lei Guo Lejiang Hu Yahui Cheng Min |
| |
| Affiliation: | Xiao Lei Guo Lejiang Hu Yahui Cheng Min(Air Force Radar Academy,Wuhan 430019) |
| |
| Abstract: | An extensible duplicates detecting system is designed and implemented.This system includes data preparation module,clustering module,field matching module and record matching module.The working principle and implementation mechanism in process of the four modules are given respectively in this dissertation.In our experiments,we compare the performance of our method with some famous approximately duplicate records detecting algorithms.The experiment results show that the system improved the precision. |
| |
| Keywords: | genetic neural network approximately duplicates detecting system clustering algorithm field matching algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
