Please use this identifier to cite or link to this item: https://hdl.handle.net/10321/4619
DC FieldValueLanguage
dc.contributor.authorMcineka, Christopher Thembinkosien_US
dc.contributor.authorPillay, Nelendranen_US
dc.date.accessioned2023-02-13T11:04:30Z-
dc.date.available2023-02-13T11:04:30Z-
dc.date.issued2022-10-27-
dc.identifier.citationMcineka, C.T. and Pillay, N. 2022. Machine learning classifiers based on HoG features extracted from locomotive neutral section images. Presented at: 2022 International Conference on Engineering and Emerging Technologies (ICEET). doi:10.1109/iceet56468.2022.10007093en_US
dc.identifier.isbn978-1-6654-9106-8-
dc.identifier.urihttps://hdl.handle.net/10321/4619-
dc.description.abstractThis paper presents a comparative study on machine learning algorithms for neutral section image classification. The classifiers are trained by employing the Histogram of Oriented Gradient features that are extracted from the neutral section dataset [1]. A neutral section is a phase break that is used on the Transnet freight rail system to separate the single-phase supply from the 25kV three-phase overhead traction supply. The 25kV is a stepped-down voltage from an 88kV three-phase supply coming from the national grid. While the main purpose of the neutral section is to separate phase voltages, electric locomotives can traverse through these phases by switching On and Off. This auto-switching is possible through induction magnets installed in between the rails and with magnet detection sensors installed underneath the locomotives. However, a computer vision model has been developed, trained, and tested with a neutral section dataset containing images having open and close markers [1]. This paper, therefore, utilises this dataset to provide performance comparison on several machine learning classification algorithms viz. Decision Tree, Discriminant Analysis, Support Vector Machine, K-Nearest Neighbors, Ensemble, Naïve Bayes, and Convolutional Neural Network. A confusion matrix, F1- measure and computation time are employed to measure the performance of each classifier. The MATLAB Classification Learner application was used to obtain the results. The results show that the Linear Support Vector Machine performs best when considering performance and prediction speed. The Linear Support Vector Machine achieved a training accuracy of 93.40% with a test accuracy reaching 94% at a prediction speed of 75 objects per second (computation time).en_US
dc.format.extent6 pen_US
dc.language.isoenen_US
dc.publisherIEEEen_US
dc.relation.ispartof2022 International Conference on Engineering and Emerging Technologies (ICEET)en_US
dc.subjectNeutral section dataseten_US
dc.subjectMachine learning classifiersen_US
dc.subjectHistogram of oriented gradienten_US
dc.subjectComputer visionen_US
dc.subjectMATLABen_US
dc.subjectConfusion matrixen_US
dc.subjectF1-measureen_US
dc.titleMachine learning classifiers based on HoG features extracted from locomotive neutral section imagesen_US
dc.typeConferenceen_US
dc.date.updated2023-02-07T12:41:28Z-
dc.identifier.doi10.1109/iceet56468.2022.10007093-
item.languageiso639-1en-
item.fulltextWith Fulltext-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.grantfulltextopen-
item.openairetypeConference-
item.cerifentitytypePublications-
Appears in Collections:Research Publications (Engineering and Built Environment)
Files in This Item:
File Description SizeFormat
Mcineka_Pillay_2022.pdfArticle409.41 kBAdobe PDFView/Open
Show simple item record

Page view(s)

200
checked on Dec 22, 2024

Download(s)

47
checked on Dec 22, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.