Differential evolution for rule extraction and its application in recognizing oil reservoir

Jin Ling Li, Hai Xiang Guo, Ke Jun Zhu, De Yun Wang, Takayuki Furuzuki

Research output: Contribution to journalArticle

Abstract

The method of rule extraction based on differential evolution (DE-Rule) is proposed in this paper. The style of rule is IF-THEN. Connection word is AND in the antecedent of rule. The consequence of rule is class label. The above rule is encoded and expressed to individual in population of differential evolution. Then the population is iterated through differential mutation and binomial crossover. Optimal rule set is obtained after decoding the optimal individual. Finally, DE-Rule, RS-Rule and ANN-GA-Cascades-Rule are used to recognize oil reservoir (dry layer, water layer, inferiority layer and oil layer) in the Jianghan oil field. Data of well oilsk81 is training data and data of well oilsk83 is testing data. The results show that performance of accuracy and interpretability in DE-Rule is the best.

Original languageEnglish
Pages (from-to)435-440
Number of pages6
JournalJournal of Digital Information Management
Volume11
Issue number6
Publication statusPublished - 2013 Dec

Fingerprint

Oil fields
Decoding
Labels
class rule
Testing
Water
water
Oils
Oil
Differential evolution
performance
Gas
Cascade
Crossover
Mutation

Keywords

  • Differential Evolution
  • Oil Reservoir
  • Rule Extraction

ASJC Scopus subject areas

  • Management Information Systems
  • Information Systems
  • Library and Information Sciences

Cite this

Differential evolution for rule extraction and its application in recognizing oil reservoir. / Li, Jin Ling; Guo, Hai Xiang; Zhu, Ke Jun; Wang, De Yun; Furuzuki, Takayuki.

In: Journal of Digital Information Management, Vol. 11, No. 6, 12.2013, p. 435-440.

Research output: Contribution to journalArticle

Li, Jin Ling ; Guo, Hai Xiang ; Zhu, Ke Jun ; Wang, De Yun ; Furuzuki, Takayuki. / Differential evolution for rule extraction and its application in recognizing oil reservoir. In: Journal of Digital Information Management. 2013 ; Vol. 11, No. 6. pp. 435-440.
@article{2201925f61314e138d7f8550c53bbe04,
title = "Differential evolution for rule extraction and its application in recognizing oil reservoir",
abstract = "The method of rule extraction based on differential evolution (DE-Rule) is proposed in this paper. The style of rule is IF-THEN. Connection word is AND in the antecedent of rule. The consequence of rule is class label. The above rule is encoded and expressed to individual in population of differential evolution. Then the population is iterated through differential mutation and binomial crossover. Optimal rule set is obtained after decoding the optimal individual. Finally, DE-Rule, RS-Rule and ANN-GA-Cascades-Rule are used to recognize oil reservoir (dry layer, water layer, inferiority layer and oil layer) in the Jianghan oil field. Data of well oilsk81 is training data and data of well oilsk83 is testing data. The results show that performance of accuracy and interpretability in DE-Rule is the best.",
keywords = "Differential Evolution, Oil Reservoir, Rule Extraction",
author = "Li, {Jin Ling} and Guo, {Hai Xiang} and Zhu, {Ke Jun} and Wang, {De Yun} and Takayuki Furuzuki",
year = "2013",
month = "12",
language = "English",
volume = "11",
pages = "435--440",
journal = "Journal of Digital Information Management",
issn = "0972-7272",
publisher = "Digital Information Research Foundation",
number = "6",

}

TY - JOUR

T1 - Differential evolution for rule extraction and its application in recognizing oil reservoir

AU - Li, Jin Ling

AU - Guo, Hai Xiang

AU - Zhu, Ke Jun

AU - Wang, De Yun

AU - Furuzuki, Takayuki

PY - 2013/12

Y1 - 2013/12

N2 - The method of rule extraction based on differential evolution (DE-Rule) is proposed in this paper. The style of rule is IF-THEN. Connection word is AND in the antecedent of rule. The consequence of rule is class label. The above rule is encoded and expressed to individual in population of differential evolution. Then the population is iterated through differential mutation and binomial crossover. Optimal rule set is obtained after decoding the optimal individual. Finally, DE-Rule, RS-Rule and ANN-GA-Cascades-Rule are used to recognize oil reservoir (dry layer, water layer, inferiority layer and oil layer) in the Jianghan oil field. Data of well oilsk81 is training data and data of well oilsk83 is testing data. The results show that performance of accuracy and interpretability in DE-Rule is the best.

AB - The method of rule extraction based on differential evolution (DE-Rule) is proposed in this paper. The style of rule is IF-THEN. Connection word is AND in the antecedent of rule. The consequence of rule is class label. The above rule is encoded and expressed to individual in population of differential evolution. Then the population is iterated through differential mutation and binomial crossover. Optimal rule set is obtained after decoding the optimal individual. Finally, DE-Rule, RS-Rule and ANN-GA-Cascades-Rule are used to recognize oil reservoir (dry layer, water layer, inferiority layer and oil layer) in the Jianghan oil field. Data of well oilsk81 is training data and data of well oilsk83 is testing data. The results show that performance of accuracy and interpretability in DE-Rule is the best.

KW - Differential Evolution

KW - Oil Reservoir

KW - Rule Extraction

UR - http://www.scopus.com/inward/record.url?scp=84892182107&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84892182107&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:84892182107

VL - 11

SP - 435

EP - 440

JO - Journal of Digital Information Management

JF - Journal of Digital Information Management

SN - 0972-7272

IS - 6

ER -