Rough set theory with discriminant analysis in analyzing electricity loads

Authors:
Ping-Feng Pai;Tai-Chi Chen
Affiliations:
Department of Information Management, National Chi Nan University, 1, University Rd., Puli, Nantou 545, Taiwan;Department of Information Management, National Chi Nan University, 1, University Rd., Puli, Nantou 545, Taiwan
Venue:
Expert Systems with Applications: An International Journal
Year:
2009

Citing 5
Cited 3

Knowledge discovery in clinical databases and evaluation of discovered knowledge in outpatient clinic

Information Sciences—Informatics and Computer Science: An International Journal
Feature extraction approaches based on matrix pattern: MatPCA and MatFLDA

Pattern Recognition Letters
A linear discriminant analysis framework based on random subspace for face recognition

Pattern Recognition
Network intrusion detection: Evaluating cluster, discriminant, and logit analysis

Information Sciences: an International Journal
Relevant attribute discovery in high dimensional data: application to breast cancer gene expressions

RSKT'06 Proceedings of the First international conference on Rough Sets and Knowledge Technology

PSOLDA: A particle swarm optimization approach for enhancing classification accuracy rate of linear discriminant analysis

Applied Soft Computing
A new discriminant analysis approach under decision-theoretic rough sets

RSKT'11 Proceedings of the 6th international conference on Rough sets and knowledge technology
Leak detection of pipeline: An integrated approach of rough set theory and artificial bee colony trained SVM

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

With the ability to deal with both numeric and nominal information, rough set theory (RST), which can express knowledge in a rule-based form, has been one of the most important techniques in data analysis. However, applications of rough set theory for analyzing electricity loads are not widely discussed. Thus, this investigation employs rough set theory to analyze electricity loads. Additionally, to reduce the time generating reducts by rough set theory, linear discriminant analysis (LDA) is used to generate a reduct for rough set model. Therefore, this study designs a hybrid discriminant analysis and rough set model (DARST) to provide decision rules representing relations in an electric load information system. In this investigation, nine condition factors and variations of electricity loads are employed to examine the feasibility of the hybrid model. Experimental results reveal that the proposed model can efficiently and accurately analyze the relation between condition variables and variations of electricity loads. Consequently, the proposed model is a promising alternative for developing an electric load information system and offers decision rules base for the utility management as well as operations staff.