A study on the use of imputation methods for experimentation with Radial Basis Function Network classifiers handling missing attribute values: The good synergy between RBFNs and Event Covering method

被引：73

作者：

Luengo, Julian ^{[1
]}

Garcia, Salvador ^{[2
]}

Herrera, Francisco ^{[1
]}

机构：

[1] Univ Granada, CITIC, Dept Comp Sci & Artificial Intelligence, E-18071 Granada, Spain

[2] Univ Jaen, Dept Comp Sci, Jaen 23071, Spain

来源：

NEURAL NETWORKS | 2010年 / 23卷 / 03期

关键词：

Classification; Imputation methods; Missing values; Radial Basis Function Networks; ARTIFICIAL NEURAL-NETWORKS; STATISTICAL COMPARISONS; TRAINING ALGORITHM; INCOMPLETE DATA; PREDICTION; SELECTION;

D O I：

10.1016/j.neunet.2009.11.014

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

The presence of Missing Values in a data set can affect the performance of a classifier constructed using that data set as a training sample. Several methods have been proposed to treat missing data and the one used more frequently is the imputation of the Missing Values of an instance. In this paper, we analyze the improvement of performance on Radial Basis Function Networks by means of the use of several imputation methods in the classification task with missing values. The study has been conducted using data sets with real Missing Values, and data sets with artificial Missing Values. The results obtained show that EventCovering offers a very good synergy with Radial Basis Function Networks. It allows us to overcome the negative impact of the presence of Missing Values to a certain degree. (C) 2009 Elsevier Ltd. All rights reserved.

引用

页码：406 / 418

页数：13

共 51 条

[21] A new EM-based training algorithm for RBF networks [J].

Lázaro, M ;

Santamaría, I ;

Pantaleón, C .

NEURAL NETWORKS, 2003, 16 (01) :69-77

[22] Vector quantization: a weighted version for time-series forecasting [J].

Lendasse, A ;

Francois, D ;

Wertz, V ;

Verleysen, M .

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2005, 21 (07) :1056-1067

[23]

Li D, 2004, LECT NOTES ARTIF INT, V3066, P573

[24] Relaxed conditions for radial-basis function networks to be universal approximators [J].

Liao, Y ;

Fang, SC ;

Nuttle, HLW .

NEURAL NETWORKS, 2003, 16 (07) :1019-1028

[25] A hybrid neural network system for pattern classification tasks with missing features [J].

Lim, CP ;

Leong, JH ;

Kuan, MM .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2005, 27 (04) :648-653

[26]

Little R. J. A., 1987, STAT ANAL MISSING DA

[27] Impact of missing data in evaluating artificial neural networks trained on complete data [J].

Markey, MK ;

Tourassi, GD ;

Margolis, M ;

DeLong, DM .

COMPUTERS IN BIOLOGY AND MEDICINE, 2006, 36 (05) :516-525

[28]

Mileva-Boshkoska B, 2007, INFORM-J COMPUT INFO, V31, P425

[29]

MORRIS CW, 2001, INT J SMART ENG SYST, V3, P195

[30] ON THE TRAINING OF RADIAL BASIS FUNCTION CLASSIFIERS [J].

MUSAVI, MT ;

AHMED, W ;

CHAN, KH ;

FARIS, KB ;

HUMMELS, DM .

NEURAL NETWORKS, 1992, 5 (04) :595-603

← 1 2 3 4 5 6 →