Supervised learning for the analysis of process operational data

被引：10

作者：

Yamashita, Y ^{[1
]}

机构：

[1] Tohoku Univ, Dept Chem Engn, Sendai, Miyagi 9808579, Japan

来源：

COMPUTERS & CHEMICAL ENGINEERING | 2000年 / 24卷 / 2-7期

关键词：

machine learning; classification; operational knowledge; data mining;

D O I：

10.1016/S0098-1354(00)00497-X

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

For the extraction of useful knowledge from recorded process operational data, several data mining algorithms are examined on a data set generated by a dynamic simulator of a debutanizer plant. Decision tree inducer can directly extract reasonable operational rules from the data-set with no previous knowledge. By integrating the feature-subset selection wrapper algorithm, Naive-Bayes classifier and nearest-neighbor classifier can also estimate the action of operation successfully. (C) 2000 Elsevier Science Ltd. All rights reserved.

引用

页码：471 / 474

页数：4

共 9 条

[1] TOLERATING NOISY, IRRELEVANT AND NOVEL ATTRIBUTES IN INSTANCE-BASED LEARNING ALGORITHMS [J].

AHA, DW .

INTERNATIONAL JOURNAL OF MAN-MACHINE STUDIES, 1992, 36 (02) :267-287

[2]

Fayyad U. M., 1996, ADV KNOWLEDGE DISCOV, P1, DOI DOI 10.1609/AIMAG.V17I3.1230

[3]

*JAP SOC SCI, 2000, 21 JAP SOC SCI

[4]

Kohavi R., 1995, KDD-95 Proceedings. First International Conference on Knowledge Discovery and Data Mining, P192

[5]

Langley P, 1999, MACHINE LEARNING, PROCEEDINGS, P220

[6]

Michalski RS, 1998, MACHINE LEARNING DAT, P71

[7] Improved use of continuous attributes in C4.5 [J].

Quinlan, JR .

JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 1996, 4 :77-90

[8]

Quinlan R, 1993, C4.5: Programs for Machine Learning

[9]

WANG XZ, 1999, DATA MINING KNOWLEDG

← 1 →