Optimal feature selection for classification of power quality disturbances using wavelet packet-based fuzzy k-nearest neighbour algorithm
- 1 March 2009
- journal article
- Published by Institution of Engineering and Technology (IET) in IET Generation, Transmission & Distribution
- Vol. 3 (3), 296-306
- https://doi.org/10.1049/iet-gtd:20080190
Abstract
The authors present an automatic classification of different power quality (PQ) disturbances using wavelet packet transform (WPT) and fuzzy k-nearest neighbour (FkNN) based classifier. The training data samples are generated using parametric models of the PQ disturbances. The features are extracted using some of the statistical measures on the WPT coefficients of the disturbance signal when decomposed upto the fourth level. These features are given to the fuzzy k-NN for effective classification. The genetic algorithm-based feature vector selection is done to ensure good classification accuracy by selecting 16 better features from all 96 features generated from the WPT coefficients. The necessity of selecting the best feature is to remove the redundant or irrelevant features, which may reduce the performance of the classification. It also reduces the computation time since it uses only 16 features instead of 96 features. The experimental analysis for the validation of the proposed algorithm is carried out in two stages. At the first stage, the sample data set is generated by varying the parameters in models in regular intervals and the proposed algorithm is applied to select the best features to obtain high accuracy. In the second stage, a new data set is generated by choosing the parameter values, which are not used in the first case and used to test the accuracy of the classifier with the same selected features as in stage one. The noisy and practical signals are also considered for the classification process to show the effectiveness of the proposed method.Keywords
This publication has 20 references indexed in Scilit:
- Detection and classification of power quality disturbances in noisy conditionsIEE Proceedings - Generation, Transmission and Distribution, 2003
- Experimental performance evaluation of a wavelet-based on-line voltage detection method for power quality applicationsIEEE Transactions on Power Delivery, 2002
- A de-noising scheme for enhancing wavelet-based power quality monitoring systemIEEE Transactions on Power Delivery, 2001
- Wavelet based on-line disturbance detection for power quality applicationsIEEE Transactions on Power Delivery, 2000
- Understanding Power Quality ProblemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- A measurement method based on the wavelet transform for power quality analysisIEEE Transactions on Power Delivery, 1998
- Power quality assessment via wavelet transform analysisIEEE Transactions on Power Delivery, 1996
- Application of wavelets to model short-term power system disturbancesIEEE Transactions on Power Systems, 1996
- The wavelet transform, time-frequency localization and signal analysisIEEE Transactions on Information Theory, 1990
- A theory for multiresolution signal decomposition: the wavelet representationIEEE Transactions on Pattern Analysis and Machine Intelligence, 1989