2010
DOI: 10.1016/j.eswa.2009.11.015
|View full text |Cite
|
Sign up to set email alerts
|

A new algorithm for automatic classification of power quality events based on wavelet transform and SVM

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
48
0

Year Published

2012
2012
2021
2021

Publication Types

Select...
9

Relationship

0
9

Authors

Journals

citations
Cited by 90 publications
(48 citation statements)
references
References 16 publications
0
48
0
Order By: Relevance
“…The analysis includes the data with noise and without noise which is able to prove the robustness of system. In [124], authors proposed classification system based on the WT and SVM using only single feature vector at 8th decomposition level. The increased decomposition level causes to increase the computational cost and for better classification system selected feature vectors must be strong enough.…”
Section: Neural Network Based Methodsmentioning
confidence: 99%
“…The analysis includes the data with noise and without noise which is able to prove the robustness of system. In [124], authors proposed classification system based on the WT and SVM using only single feature vector at 8th decomposition level. The increased decomposition level causes to increase the computational cost and for better classification system selected feature vectors must be strong enough.…”
Section: Neural Network Based Methodsmentioning
confidence: 99%
“…Moreover, LMTs have the computational complexity of inducing the logistic regression models in a tree. Recently, SVMs have been used as an attractive tool for pattern classification because of their superior features such as producing single, optimum, and automatic sparse solutions by simultaneously minimizing both generalization and training error and separating data by a large margin in high-dimensional space [29]. Furthermore, no study has been reported yet about ST-SVM-based protection schema for SCTLs with fixed capacitors.…”
Section: Introductionmentioning
confidence: 99%
“…Recently, SVMs have been used as effective tools for fault classification in power systems [3,8,18,29,32]. This approach constructs the separating hyperplane for pattern recognition.…”
Section: Fault Classification and Faulty Section Identification By Svmsmentioning
confidence: 99%
“…On the contrary, considering the wavelet transform, it is difficult to obtain a reduced set of variables that provide a good classification accuracy. In [120], an approach for automatic classification of power quality events based on the wavelet transform and SVM is proposed. The problem is tackled as a multi-class classification problem with seven classes (corresponding to the seven different power quality disturbances to be detected) that obtains the predictive variables from the wavelet transform.…”
Section: Classification Problems and Algorithms In Power Quality Distmentioning
confidence: 99%