[1]陈阳.准熵的性质及其应用[J].东南大学学报(自然科学版),2006,36(2):222-225.[doi:10.3969/j.issn.1001-0505.2006.02.009]
 Chen Yang.Properties of quasi-entropy and their application[J].Journal of Southeast University (Natural Science Edition),2006,36(2):222-225.[doi:10.3969/j.issn.1001-0505.2006.02.009]
点击复制

准熵的性质及其应用()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
36
期数:
2006年第2期
页码:
222-225
栏目:
信息与通信工程
出版日期:
2006-03-20

文章信息/Info

Title:
Properties of quasi-entropy and their application
作者:
陈阳
东南大学无线电工程系, 南京 210096
Author(s):
Chen Yang
Department of Radio Engineering, Southeast University, Nanjing 210096, China
关键词:
凸函数 混沌
Keywords:
convex function entropy chaos
分类号:
TN911.2
DOI:
10.3969/j.issn.1001-0505.2006.02.009
摘要:
准熵将信息论中熵的特定凸函数推广到任意凸函数,研究了这种推广能否提高熵的性能.提出并证明了准熵与熵的一些共同性质.以独立性度量问题为例,研究了凸函数对准熵最小值形状的影响,提出了凸函数品质因数的概念,用来刻画准熵最小值的显著性.发现了品质因数比熵中凸函数更好的无穷多凸函数.给出了凸函数品质因数在混沌信号分析中的应用实例.结果表明,根据特定应用,恰当选取凸函数,可令准熵获得比熵更好的性能.
Abstract:
Quasi-entropy(QE)generalizes the specific convex function in the entropy in information theory to an arbitrary convex function. Whether this generalization can improve the performance of entropy was studied. Some common properties of QE and entropy were proposed and proved. Using the independence-measuring problem as an example, the influence of the convex function on the shape of the minima of QE was studied. The concept of the quality factor of convex function was proposed, which was used to characterize the prominence of the minimum of QE. Infinitely many convex functions with quality factors better than that of the convex function in entropy were discovered. An application of the quality factor of convex function to chaotic signal analysis was given. The results show that, by properly choosing convex function according to specific application, the performance of QE can be made better than that of entropy.

参考文献/References:

[1] Shannon C E.A mathematical theory of communication [J]. The Bell System Technical Journal,1948,27(3):379-423.
[2] Renyi A.On measures of entropy and information[C] //Neyman J.Proceedings of the 4th Berkeley Symposium on Mathematical Statistics and Probability.Berkeley,CA:University of California Press,1961:547-561.
[3] 陈阳.新的独立性度量及其在混沌信号分析中的应用[J].东南大学学报:自然科学版,2003,33(1):13-18.
  Chen Yang.New independence measures and its application to chaotic signal analysis [J]. Journal of Southeast University:Natural Science Edition,2003,33(1):13-18.(in Chinese)
[4] Chen Y,He Z.Blind separation using a class of new independence measures[C] //2003 IEEE International Conference on Acoustics,Speech,and Signal Processing(ICASSP 2003).Hong Kong,2003:309-312.

相似文献/References:

[1]龚坚,李立源,陈维南.二维熵阈值分割的快速算法[J].东南大学学报(自然科学版),1996,26(4):33.[doi:10.3969/j.issn.1001-0505.1996.04.007]
 Gong Jian,Li Liyuan,Chen Weinan.A Fast Two Dimensonal Entropic Thresholding Method[J].Journal of Southeast University (Natural Science Edition),1996,26(2):33.[doi:10.3969/j.issn.1001-0505.1996.04.007]
[2]郭孜政,潘毅润,潘雨帆,等.基于EEG熵值的驾驶员脑力负荷水平识别方法[J].东南大学学报(自然科学版),2015,45(5):980.[doi:10.3969/j.issn.1001-0505.2015.05.028]
 Guo Zizheng,Pan Yirun,Pan Yufan,et al.Recognition method of driving mental workload based on EEG entropy[J].Journal of Southeast University (Natural Science Edition),2015,45(2):980.[doi:10.3969/j.issn.1001-0505.2015.05.028]

备注/Memo

备注/Memo:
基金项目: 国家自然科学基金资助项目(60202014)、东南大学科技基金资助项目(XJ0504183).
作者简介: 陈阳(1975—),男,博士,副教授,cheny@seu.edu.cn.
更新日期/Last Update: 2006-03-20