DSpace logo

Please use this identifier to cite or link to this item: http://142.54.178.187:9060/xmlui/handle/123456789/19033
Full metadata record
DC FieldValueLanguage
dc.contributor.authorI.S. Bajwa-
dc.contributor.authorM.N. Asghar-
dc.contributor.authorM.A. Naeem-
dc.date.accessioned2023-03-14T05:56:29Z-
dc.date.available2023-03-14T05:56:29Z-
dc.date.issued2017-12-14-
dc.identifier.citationBajwa, I. S. (2017). Automated detection of early tropical cyclones formation in satellite images. Pakistan Journal of Science, 69(4).en_US
dc.identifier.issn0030-9877-
dc.identifier.urihttp://142.54.178.187:9060/xmlui/handle/123456789/19033-
dc.description.abstractThe satellite imagery based weather predictions especially identification and classification of pressure zones that leads to formation of tropical cyclones was the objective of this paper. The presented approach was based on Principal Component Analysis (PCA) algorithm and Markov Logic Networks (MLN) for identification of pressure zones where PCA was used to extract features and Markov Logic for classification purposes. The system worked in two phases: Firstly, National Oceanic and Atmospheric Administration (NOAA) satellite images which were used to train the system and in training phase, an image space was generated on the basis of the spatial features of the input images. The results of the experiments showed that Markov Logic improved the accuracy of low level clouds by 8% and for high level clouds 12% classification of pressure zones in NOAA satellite images.en_US
dc.language.isoenen_US
dc.publisherLahore: Pakistan Association for the Advancement of Scienceen_US
dc.subjectImage Classificationen_US
dc.subjectPrincipal Component Analysis,en_US
dc.subjectMarkov Logicen_US
dc.subjectSatellite Imagesen_US
dc.subjectTropical Cyclones.en_US
dc.titleAUTOMATED DETECTION OF EARLY TROPICAL CYCLONES FORMATION IN SATELLITE IMAGESen_US
dc.typeArticleen_US
Appears in Collections:Issue 04

Files in This Item:
File Description SizeFormat 
PJS-305-5572.htm120 BHTMLView/Open


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