000842290 001__ 842290
000842290 005__ 20210129232245.0
000842290 0247_ $$2doi$$a10.1109/IGARSS.2017.8127797
000842290 037__ $$aFZJ-2018-00537
000842290 1001_ $$0P:(DE-Juel1)132190$$aMemon, Mohammad Shahbaz$$b0$$eCorresponding author
000842290 1112_ $$a2017 IEEE International Geoscience and Remote Sensing Symposium$$cFort Worth, TX$$d2017-07-23 - 2017-07-28$$gIGARSS 2017$$wUSA
000842290 245__ $$aFacilitating efficient data analysis of remotely sensed images using standards-based parameter sweep models
000842290 260__ $$bIEEE$$c2017
000842290 29510 $$a[Proceedings] - IEEE, 2017. - ISBN 978-1-5090-4951-6
000842290 300__ $$a3680-3683
000842290 3367_ $$2ORCID$$aCONFERENCE_PAPER
000842290 3367_ $$033$$2EndNote$$aConference Paper
000842290 3367_ $$2BibTeX$$aINPROCEEDINGS
000842290 3367_ $$2DRIVER$$aconferenceObject
000842290 3367_ $$2DataCite$$aOutput Types/Conference Paper
000842290 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1516869462_22606
000842290 3367_ $$0PUB:(DE-HGF)7$$2PUB:(DE-HGF)$$aContribution to a book$$mcontb
000842290 520__ $$aClassification of remote sensing images often use Support Vector Machines (SVMs) that require an n-fold cross-validation phase in order to do model selection. This phase is characterized by sweeping through a wide set of parameter combinations of SVM kernel and cost parameters. As a consequence this process is computationally expensive but represents a principled way of tuning a model for better accuracy and to prevent overfitting together with regularization that is in SVMs inherently solved in the optimization. Since the cross-validation technique is done in a principled way also known as ‘gridsearch’, we aim at supporting remote sensing scientists in two ways. Firstly by reducing the time-to-solution of the cross-validation by applying state-of-the-art parallel processing methods because the sweep of parameters and cross-validation runs itself can be nicely parallelized. Secondly by reducing manual labour by automating the parallel submission processes since manually performing cross-validation is very time consuming, unintuitive, and error-prone especially in large-scale cluster or supercomputing environments (e.g., batch job scripts, node/core/task parameters, etc.).
000842290 536__ $$0G:(DE-HGF)POF3-512$$a512 - Data-Intensive Science and Federated Computing (POF3-512)$$cPOF3-512$$fPOF III$$x0
000842290 588__ $$aDataset connected to CrossRef Conference
000842290 65027 $$0V:(DE-MLZ)SciArea-250$$2V:(DE-HGF)$$aOthers$$x0
000842290 7001_ $$0P:(DE-Juel1)171343$$aCavallaro, Gabriele$$b1$$ufzj
000842290 7001_ $$0P:(DE-Juel1)132239$$aRiedel, Morris$$b2$$ufzj
000842290 7001_ $$0P:(DE-Juel1)169980$$aNeukirchen, Helmut$$b3
000842290 773__ $$a10.1109/IGARSS.2017.8127797
000842290 909CO $$ooai:juser.fz-juelich.de:842290$$pVDB
000842290 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132190$$aForschungszentrum Jülich$$b0$$kFZJ
000842290 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)171343$$aForschungszentrum Jülich$$b1$$kFZJ
000842290 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)132239$$aForschungszentrum Jülich$$b2$$kFZJ
000842290 9131_ $$0G:(DE-HGF)POF3-512$$1G:(DE-HGF)POF3-510$$2G:(DE-HGF)POF3-500$$3G:(DE-HGF)POF3$$4G:(DE-HGF)POF$$aDE-HGF$$bKey Technologies$$lSupercomputing & Big Data$$vData-Intensive Science and Federated Computing$$x0
000842290 9141_ $$y2017
000842290 920__ $$lyes
000842290 9201_ $$0I:(DE-Juel1)JSC-20090406$$kJSC$$lJülich Supercomputing Center$$x0
000842290 980__ $$acontrib
000842290 980__ $$aVDB
000842290 980__ $$acontb
000842290 980__ $$aI:(DE-Juel1)JSC-20090406
000842290 980__ $$aUNRESTRICTED