[1]车丽美 肖洋 王甦易[] 姜倩倩.Kmeans聚类分析在形音字表音度中的应用[J].计算机技术与发展,2011,(02):223-225.
　CHE Li-mei,XIAO Yang,WANG Su-yi,et al.Application of Kmeans Clustering Analysis in Chinese Pronunciation Degree[J].,2011,(02):223-225.
点击复制

Kmeans聚类分析在形音字表音度中的应用()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2011年02期
页码:
223-225
栏目:
应用开发研究
出版日期:
1900-01-01

文章信息/Info

Title:
Application of Kmeans Clustering Analysis in Chinese Pronunciation Degree
文章编号:
1673-629X（2011）02-0223-03
作者:
车丽美1 肖洋2 王甦易[3] 姜倩倩1
[1]北京师范大学信息科学与技术学院计算机系[2]北京师范大学管理学院[3]北京师范大学物理学系
Author(s):
CHE Li-mei; XIAO Yang; WANG Su-yi; JIANG Qian-qian
[1]Department of Computer,School of Information Science and Technology,Beijing Normal University[2]School of Management,Beijing Normal University[3]School of Physics,Beijing Normal University
关键词:
拼音; 特征向量; Kmeans聚类分析; 平方误差法则
Keywords:
Pinyin;  eigenvector;  Kmeans cluster analysis;  square error of law
分类号:
TP39
文献标志码:
A
摘要:
文章通过分析现代汉语拼音的组成结构,总结出汉语拼音对于汉字发音的影响因素。利用计算机对现代汉语中3500个常用字进行汉字拼音表GB2312版录入,提出了基于K均值聚类分析的分级模型。此模型通过建立形声字声符的表音特征向量,利用Kmeans聚类分析的方法,将形声字按表音程度的高低分为6级,使得每一级内形声字的表音度更为相似和紧密,并通过每一个分级（聚类中的簇）中特征向量的模的大小对聚类结果按表音度高低进行排序。提出了新的形音字分级模型,对形音字声符表音度分析提供了新的视角
Abstract:
By analyzing the composition of the structure of modern Pinyin,Hanyu Pinyin for the Chinese pronunciation summed up the impact factor.Using computers to 3,500 in modern Chinese characters commonly used version of Chinese characters and Pinyin input table GB2312 proposed Kmeans clustering analysis based on the classification model.This model through the establishment of Tonal sound symbols and phonetic feature vector,using Kmeans cluster analysis method,will form words by phonetic sound level is divided into six levels,making each one sound within a word and phonetic form more similar degree of and close,and through each grade（cluster of clusters） in the feature vector model of the size of the cluster results according to degree level phonetic sort.Present a new form of sound words classification model,form,sound character phonogram sound analysis provides a new perspective

相似文献/References:

[1]常庆 周明全 耿国华.基于PageRank和HITS的Web搜索[J].计算机技术与发展,2008,(07):77.
　CHANG Qing,ZHOU Ming-quan,GENG Guo-hua.PageRank and HITS- Based Web Search[J].,2008,(02):77.
[2]王峰 王浩 王秀友.一种基于点模式的指纹分阶段匹配算法的研究[J].计算机技术与发展,2007,(11):114.
　WANG Feng,WANG Hao,WANG Xiu-you.Study of Fingerprint Grading Matching Algorithm Based on Point Pattern[J].,2007,(02):114.
[3]张靖 葛玮 郝克刚.软件度量中主成分分析方法的研究[J].计算机技术与发展,2006,(12):144.
　ZHANG Jing,GE Wei,HAO Ke-gang.Research of Principal Component Analysis in Software Metrics[J].,2006,(02):144.
[4]刘勇 林景栋 穆伟力.基于H-K算法的MIDI音乐主旋律提取[J].计算机技术与发展,2011,(06):154.
　LIU Yong,LIN Jing-dong,MU Wei-li.Melody Extraction Method from MIDI Based on H-K Algorithm[J].,2011,(02):154.
[5]章鹏程.基于单因素方差分析的P2P流特征向量优化方法[J].计算机技术与发展,2012,(04):101.
　ZHANG Peng-cheng.Optimal Method Based on One-Way Analysis of Variance for P2P Feature Vector[J].,2012,(02):101.
[6]贾志先.考试数据分析及孤立点检测的谱聚类方法[J].计算机技术与发展,2013,(01):103.
　JIA Zhi-xian.Spectral Clustering Method for Exam Data Analysis and Outlier Detection[J].,2013,(02):103.
[7]张培颖,王雷全.基于语义距离的文本分类方法[J].计算机技术与发展,2013,(01):128.
　ZHANG Peo-ying,WANG Lei-quan.Text Classification Method Based on Semantic Distance[J].,2013,(02):128.
[8]王玉军.一种相关快速软阈值坐标下降算法[J].计算机技术与发展,2013,(12):55.
　WANG Yu-jun.A Relative Fast Soft-thresholding Coordinate Descent Algorithm[J].,2013,(02):55.
[9]夏士明,李骞,谢凯翔.形状特征的卫星云图检索方法研究[J].计算机技术与发展,2014,24(04):60.
　XIA Shi-ming,LI Qian,XIE Kai-xiang.A Method of Satellite Cloud Image Retrieval of Shape Feature[J].,2014,24(02):60.
[10]肖红,许少华. 改进的话题检测和跟踪算法研究[J].计算机技术与发展,2014,24(09):84.
　XIAO Hong,XU Shao-hua. Improved Algorithm Study on Topic Detection and Tracking[J].,2014,24(02):84.

备注/Memo

备注/Memo:
全国教育科学“十一五”规划教育部重点课题（DCA060097）车丽美（1987-），女，河北廊坊人，研究方向为数据挖掘、模式识别
更新日期/Last Update: 1900-01-01