{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,8,11]],"date-time":"2024-08-11T17:50:09Z","timestamp":1723398609231},"reference-count":38,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2016,1,28]],"date-time":"2016-01-28T00:00:00Z","timestamp":1453939200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"Power quality signal feature selection is an effective method to improve the accuracy and efficiency of power quality (PQ) disturbance classification. In this paper, an entropy-importance (EnI)-based random forest (RF) model for PQ feature selection and disturbance classification is proposed. Firstly, 35 kinds of signal features extracted from S-transform (ST) with random noise are used as the original input feature vector of RF classifier to recognize 15 kinds of PQ signals with six kinds of complex disturbance. During the RF training process, the classification ability of different features is quantified by EnI. Secondly, without considering the features with zero EnI, the optimal perturbation feature subset is obtained by applying the sequential forward search (SFS) method which considers the classification accuracy and feature dimension. Then, the reconstructed RF classifier is applied to identify disturbances. According to the simulation results, the classification accuracy is higher than that of other classifiers, and the feature selection effect of the new approach is better than SFS and sequential backward search (SBS) without EnI. With the same feature subset, the new method can maintain a classification accuracy above 99.7% under the condition of 30 dB or above, and the accuracy under 20 dB is 96.8%.<\/jats:p>","DOI":"10.3390\/e18020044","type":"journal-article","created":{"date-parts":[[2016,1,28]],"date-time":"2016-01-28T15:31:20Z","timestamp":1453995080000},"page":"44","source":"Crossref","is-referenced-by-count":31,"title":["Feature Selection of Power Quality Disturbance Signals with an Entropy-Importance-Based Random Forest"],"prefix":"10.3390","volume":"18","author":[{"given":"Nantian","family":"Huang","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-1968-0504","authenticated-orcid":false,"given":"Guobo","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China"}]},{"given":"Guowei","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China"}]},{"given":"Dianguo","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Harbin Institute of Technology, Harbin 150001, China"}]},{"given":"Jiafeng","family":"Xu","sequence":"additional","affiliation":[{"name":"Dongguan Power Supply Bureau, Guangdong Power Grid Corporation, Dongguan 523000, China"}]},{"given":"Fuqing","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China"}]},{"given":"Liying","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Northeast Dianli University, Jilin 132012, China"}]}],"member":"1968","published-online":{"date-parts":[[2016,1,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.ijepes.2012.04.045","article-title":"Classification of power quality events\u2014A review","volume":"43","author":"Saini","year":"2012","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.rser.2014.11.035","article-title":"Power-quality issues and the need for reactive-power compensation in the grid integration of wind power","volume":"43","author":"Saqib","year":"2015","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1049\/iet-rpg.2014.0215","article-title":"Power quality surveys of photovoltaic power plants: Characterisation and analysis of grid-code requirements","volume":"9","author":"Muljadi","year":"2015","journal-title":"IET Renew. Power Gener."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/j.rser.2014.08.070","article-title":"A critical review of detection and classification of power quality events","volume":"41","author":"Mahela","year":"2015","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2134","DOI":"10.1109\/TPWRD.2013.2264948","article-title":"Analysis of Nonstationary Power-Quality Waveforms Using Iterative Hilbert Huang Transform and SAX Algorithm","volume":"28","author":"Afroni","year":"2013","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1016\/j.epsr.2012.09.007","article-title":"A new classification for power quality events in distribution systems","volume":"95","author":"Ozgonenel","year":"2013","journal-title":"Electr. Power Syst. Res."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"2465","DOI":"10.1109\/TIM.2013.2258761","article-title":"A real-time power quality disturbances classification using hybrid method based on s-transform and dynamics","volume":"62","author":"He","year":"2013","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1002\/etep.1776","article-title":"A new fast discrete S-transform and decision tree for the classification and monitoring of power quality disturbance waveforms","volume":"24","author":"Babu","year":"2014","journal-title":"Int. Trans. Electr. Energy Syst."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.epsr.2011.12.009","article-title":"Rule-based classification of power quality disturbances using s-transform","volume":"86","author":"Aguado","year":"2012","journal-title":"Electr. Power Syst. Res."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"6075","DOI":"10.1016\/j.eswa.2015.04.002","article-title":"An effective power quality classifier using wavelet transform and support vector machines","volume":"42","author":"Yong","year":"2015","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.epsr.2012.11.016","article-title":"Power quality and the un-decimated wavelet transform: An analytic approach for time-varying disturbances","volume":"96","author":"Zafar","year":"2013","journal-title":"Electr. Power Syst. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.ijepes.2012.11.005","article-title":"Power quality disturbance classification using a statistical and wavelet-based hidden markov model with dempster\u2013shafer algorithm","volume":"47","author":"Dehghani","year":"2012","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.neucom.2011.06.041","article-title":"Power quality disturbances classification based on s-transform and probabilistic neural network","volume":"98","author":"Huang","year":"2012","journal-title":"Neurocomputing"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1049\/iet-gtd.2011.0733","article-title":"Automatic classification of power quality events and disturbances using wavelet transform and support vector machines","volume":"6","author":"Demir","year":"2012","journal-title":"IET Gener. Transm. Distrib."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2342","DOI":"10.1109\/TPWRD.2011.2149547","article-title":"Optimal feature selection for power-quality disturbances classification","volume":"26","author":"Lee","year":"2011","journal-title":"IEEE Trans. Power Deliv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"6766","DOI":"10.1016\/j.eswa.2013.06.055","article-title":"Genetic algorithm for s-transform optimisation in the analysis and classification of electrical signal perturbations","volume":"40","author":"Montoya","year":"2013","journal-title":"Expert Syst. Appl."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1109\/JSEN.2012.2219144","article-title":"Rough-set-based feature selection and classification for power quality sensing device employing correlation techniques","volume":"13","author":"Dalai","year":"2013","journal-title":"IEEE Sens. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"2473","DOI":"10.1109\/TIE.2013.2272276","article-title":"Detection and Classification of Single and Combined Power Quality Disturbances Using Neural Networks","volume":"61","year":"2014","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1016\/j.asoc.2014.09.050","article-title":"A modified fuzzy min\u2013max neural network for data clustering and its application to power quality monitoring","volume":"28","author":"Seera","year":"2015","journal-title":"Appl. Soft Comput."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1016\/j.asoc.2015.05.048","article-title":"Power quality disturbance detection and classification using wavelet and RBFNN","volume":"35","author":"Kanirajan","year":"2015","journal-title":"Appl. Soft Comput."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1007\/s00500-014-1472-9","article-title":"A novel data selection technique using fuzzy c-means clustering to enhance SVM-based power quality classification","volume":"19","author":"Manimala","year":"2015","journal-title":"Soft Comput."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.1109\/TSG.2015.2397431","article-title":"A classification method for complex power quality disturbances using EEMD and rank wavelet SVM","volume":"6","author":"Liu","year":"2015","journal-title":"IEEE Trans. Smart Grid"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.neucom.2012.08.031","article-title":"Power quality event characterization using support vector machine and optimization using advanced immune algorithm","volume":"103","author":"Biswal","year":"2013","journal-title":"Neurocomputing"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"549","DOI":"10.3390\/en8010549","article-title":"Power Quality Disturbances Recognition Based on a Multiresolution Generalized S-Transform and a Pso-Improved Decision Tree","volume":"8","author":"Huang","year":"2015","journal-title":"Energies"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1109\/TIA.2014.2356639","article-title":"Recognition of Power-Quality Disturbances Using S-transform-Based ANN Classifier and Rule-Based Decision Tree","volume":"51","author":"Kumar","year":"2015","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"5811","DOI":"10.3390\/e17085811","article-title":"Combined Power Quality Disturbances Recognition Using Wavelet Packet Entropies and S-Transform","volume":"17","author":"Liu","year":"2015","journal-title":"Entropy"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1109\/TSTE.2013.2278865","article-title":"Optimal feature and decision tree-based classification of power quality disturbances in distributed generation systems","volume":"5","author":"Ray","year":"2014","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1016\/j.ijepes.2014.04.010","article-title":"Automatic recognition system of underlying causes of power quality disturbances based on S-Transform and Extreme Learning Machine","volume":"61","author":"Demir","year":"2014","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_30","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"Cernadas","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.neucom.2014.10.101","article-title":"On random hyper-class random forest for visual classification","volume":"172","author":"Li","year":"2016","journal-title":"Neurocomputing"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"6490","DOI":"10.1063\/1.532660","article-title":"Information gain within nonextensive thermostatistics","volume":"39","author":"Borland","year":"1998","journal-title":"J. Math. Phys."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1016\/0165-1765(84)90126-5","article-title":"A note on the calculation and interpretation of the gini index","volume":"15","author":"Lerman","year":"1984","journal-title":"Econ. Lett."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"860","DOI":"10.3390\/e13040860","article-title":"A feature subset selection method based on high-dimensional mutual information","volume":"13","author":"Zheng","year":"2011","journal-title":"Entropy"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"10266","DOI":"10.1016\/j.eswa.2009.01.051","article-title":"The search for optimal feature set in power quality event classification","volume":"36","author":"Gunal","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1100","DOI":"10.1109\/T-C.1971.223410","article-title":"A direct method of nonparametric measurement selection","volume":"20","author":"Whitney","year":"1971","journal-title":"IEEE Trans. Comput."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.ijepes.2012.12.018","article-title":"Optimal feature selection for classification of the power quality events using wavelet transform and least squares support vector machines","volume":"49","author":"Demir","year":"2013","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"296","DOI":"10.1049\/iet-gtd:20080190","article-title":"Optimal feature selection for classification of power quality disturbances using wavelet packet-based fuzzy k-nearest neighbour algorithm","volume":"3","author":"Panigrahi","year":"2009","journal-title":"IET Gener. Transm. Distrib."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/18\/2\/44\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,4]],"date-time":"2024-06-04T10:43:23Z","timestamp":1717497803000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/18\/2\/44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,1,28]]},"references-count":38,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2016,2]]}},"alternative-id":["e18020044"],"URL":"http:\/\/dx.doi.org\/10.3390\/e18020044","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,1,28]]}}}
