[1]闫晓波,王士同,郭慧玲.基于Parzen窗的高阶统计量特征降维方法[J].智能系统学报,2013,8(1):1-10.[doi:10.3969/j.issn.1673-4785.201210046]
YAN Xiaobo,WANG Shitong,GUO Huiling.Feature reduction of high order statistics based on Parzen window[J].CAAI Transactions on Intelligent Systems,2013,8(1):1-10.[doi:10.3969/j.issn.1673-4785.201210046]
点击复制
YAN Xiaobo,WANG Shitong,GUO Huiling.Feature reduction of high order statistics based on Parzen window[J].CAAI Transactions on Intelligent Systems,2013,8(1):1-10.[doi:10.3969/j.issn.1673-4785.201210046]
基于Parzen窗的高阶统计量特征降维方法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
8
期数:
2013年第1期
页码:
1-10
栏目:
学术论文—人工智能基础
出版日期:
2013-03-25
- Title:
- Feature reduction of high order statistics based on Parzen window
- 文章编号:
- 1673-4785(2013)01-0001-10
- Keywords:
- KCCA; higher-order statistics; Parzen window; feature reduction
- 分类号:
- TP181
- 文献标志码:
- A
- 摘要:
- 高阶统计量通常能比低阶统计量提取更多原数据的信息，但是较高的阶数带来了较高的时间复杂度.基于Parzen窗估计构造了高阶统计量，通过论证得出：对于所提出的核协方差成分分析（KCCA）方法，通过调节二阶统计量广义D vs E的参数就能够达到整合高阶统计量的目的，而无需计算更高阶统计量.即核协方差成分分析方法能够对高阶统计量的特征降维的同时，又不增加计算复杂性.
- Abstract:
- The high order statistics method can often extract more information regarding original data than a low order statistics; yet in the meantime create higher time complexity. The high order statistics methods were constructed by utilizing estimation based on Parzen window. It was revealed that the kernel covariance component analysis (KCCA) method proposed earlier by the researchers, contained useful information on the high order statistics and could be obtained by only adjusting the parameters of the proposed generalized D vs E. Also based on the second order statistics, the heavy computational burden about the highorder statistics can be avoided. That is to say, the KCCA method can accomplish the feature reduction of high order statistics without increasing its computational complexity.
- 参考文献/References:
-
［1］LU Wei, SUN Wei, CHUNG Fulai, et al. Revealing digital fakery using multiresolution decomposition and higher order statistics［J］. Engineering Applications of Artificial Intelligence, 2011, 24(4): 666-672.
［2］MUNSHI D, KITCHING T, HEAVENS A, et al. Higher order statistics for threedimensional shear and flexion［J］. Monthly Notices of the Royal Astronomical Society, 2011, 416(3): 1629-1653.
［3］NAPOLITANO A, TESAURO M. Almostperiodic higher order statistic estimation［J］. IEEE Transactions on Information Theory, 2011, 57(1): 514533.
［4］KALIDINDI S, NIEZGODA S, SALEM A. Microstructure informatics using higherorder statistics and efficient datamining protocols［J］. JOM, 2011, 63(4): 34-41.
［5］AGUERAPEREZ A, PALOMARESSALAS J, De LA ROSA J, et al. Characterization of electrical sags and swells using higher order statistical estimators［J］. Measurement, 2011, 44(8): 1453-1460.
［6］LABBI A, BOSCH H, PELLEGRINI C. High order statistics for image classification［J］. International Journal of Neural Systems, 2001, 11(4): 371378.
［7］张丽琴，詹麒，朱培民，等．地震散射波场的高阶统计分析［J］．石油地球物理勘探, 2004, 39(1): 45-49.
ZHANG Liqin, ZHAN Qi, ZHU Peimin, et al. Highorder statistic analysis of seismic dispersive wavefield［J］. Oil Geophysical Prospecting, 2004, 39(1): 45-49.
［8］ANASTASSIOU G, DUMAN O. High order statistical fuzzy Korovkin theory［J］. Stochastic Analysis and Applications, 2009, 27(3): 543-554.
［9］NIKORA V, GORING D. Martian topography: scaling, craters, and highorder statistics［J］. Mathematical Geology, 2005, 37(4): 337-355.
［10］PORAT B, FRIEDLANDER B. Direction finding algorithms based on highorder statistics［J］. IEEE Transactions on Signal Processing, 1991, 39(9): 2016-2024.
［11］COURNAPEAU D, KAWAHARA T. Voice activity detection based on high order statistics and online EM algorithm［J］. IEICE Transactions on Information and Systems, 2008, 91(12): 2854-2861.
［12］REN Hsuan, DU Qian, WANG Jing, et al. Automatic target recognition for hyperspectral imagery using highorder statistics［J］. IEEE Transactions on Aerospace and Electronic Systems, 2006, 42(4): 1372-1385.
［13］TAOUFIKI M, ADIB A, ABOUTAJDINE D. Blind separation of any source distributions via highorder statistics［J］. Signal Processing, 2007, 87(8): 1882-1889.
［14］YUAN Jinghe, HU Ziqiang. Highorder statistical blind deconvolution of spectroscopic data with a GaussNewton algorithm［J］. Applied Spectroscopy, 2006, 60(6):? 692-697.
［15］JENSSEN R. Kernel entropy component analysis［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(5): 847-860.
［16］闫晓波,王士同,郭慧玲.核协方差成分分析方法及其在聚类中的应用［J］.计算机科学, 2012, 39(9): 229-234.
YAN Xiaobo, WANG Shitong, GUO Huiling. Kernel covariance component analysis and its application in clustering［J］. Computer Science, 2012, 39(9): 229-234.
［17］RENYI A. On measures of entropy and information［C］//Proceedings of the 4th Berkeley Symposium on Mathematical Statistics and Probability. Berkeley, USA, 1961: 547-561.
［18］PARZEN E. On estimation of a probability density function and mode［J］. The Annals of Mathematical Statistics, 1962, 33(3): 1065-1076.
［19］DENG Zhaohong, CHUNG Fulai, WANG Shitong. FRSDE: fast reduced set density estimator using minimal enclosing ball approximation［J］. Pattern Recognition, 2008, 41(4): 1363-1372.
［20］KOLLIOS G, GUNOPULOS D, KOUDAS N, et al. Efficient biased sampling for approximate clustering and outlier detection in large data sets［J］. IEEE Transactions on Knowledge and Date Engineering, 2003, 15(5): 1170-1187.
备注/Memo
收稿日期: 2012-10-22
网络出版日期：2013-01-25.
基金项目：国家自然科学基金资助项目（90820002）；江苏省自然科学基金资助项目（BK2009067）.?
通信作者：闫晓波.
E-mail：hnpyyxb@163.com.
作者简介：
闫晓波，女，1987年生，硕士研究生，主要研究方向为人工智能、模式识别.
王士同，男，1964年生，教授，博士生导师.主要研究方向为人工智能、模式识别、神经模糊系统、生物信息学及其应用.先后主持或参与国家自然科学基金项目6项、省部级科研项目10余项.获教育部、江苏省等省部级政府类科技进步奖一、三等奖共7项.发表学术论文百余篇，出版著作5部.
郭慧玲，女，1989年生，硕士研究生，主要研究方向为人工智能、模式识别、图像处理.
更新日期/Last Update:
2013-04-12