Centre dedocumentation
scientifique

Investigation of automatic feature weighting methods (Fisher, Chi-square and Relief-F) for landslide susceptibility mapping / Emrehan Kutlug Sahin in Geocarto international, vol 32 n° 9 (September 2017)  

Public [article]  inGeocarto international > vol 32 n° 9 (September 2017) . - pp 956 - 977 Titre : Investigation of automatic feature weighting methods (Fisher, Chi-square and Relief-F) for landslide susceptibility mapping Type de document : Article/Communication Auteurs : Emrehan Kutlug Sahin, Auteur ; Cengizhan Ipbuker, Auteur ; Taskin Kavzoglu, Auteur Année de publication : 2017 Article en page(s) : pp 956 - 977 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique [Termes descripteurs IGN] analyse comparative [Termes descripteurs IGN] cartographie des risques [Termes descripteurs IGN] distribution de Fisher [Termes descripteurs IGN] effondrement de terrain [Termes descripteurs IGN] khi carré [Termes descripteurs IGN] pondération [Termes descripteurs IGN] processus d'analyse hiérarchisée [Termes descripteurs IGN] risque naturel [Termes descripteurs IGN] surveillance géologique [Termes descripteurs IGN] test de performance [Termes descripteurs IGN] vulnérabilité Résumé : (Auteur) In landslide susceptibility mapping, factor weights have been usually determined by expert judgements. A novel methodology for weighting landslide causative factors by integrating statistical feature weighting algorithms was proposed. The primary focus of this study is to investigate the effectiveness of automatic feature weighting algorithms, namely Fisher, Chi-square and Relief-F algorithms. Analytic hierarchy process (AHP) method was used as a benchmark method to compare the performances of the weighting algorithms. All weighted factors were tested using factor-weighted overlay method, and quality of these maps was assessed using overall accuracy, area under the ROC curve (AUC) and success rate curve. In addition, Wilcoxon’s signed-rank test was applied to evaluate statistical differences between both estimated overall accuracies and AUCs, respectively. Results showed that the weights determined by feature weighting methods outperformed the conventional AHP method by about 6% and this level of differences was found to be statistically significant. Numéro de notice : A2017-458 Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2016.1170892 date de publication en ligne : 11/04/2016 En ligne : http://dx.doi.org/10.1080/10106049.2016.1170892 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86383 [article]

The use of logistic model tree (LMT) for pixel- and object-based classifications using high-resolution WorldView-2 imagery / Ismail Colkesen in Geocarto international, vol 32 n° 1 (January 2017)  

Public [article]  inGeocarto international > vol 32 n° 1 (January 2017) . - pp 71 - 86 Titre : The use of logistic model tree (LMT) for pixel- and object-based classifications using high-resolution WorldView-2 imagery Type de document : Article/Communication Auteurs : Ismail Colkesen, Auteur ; Taskin Kavzoglu, Auteur Année de publication : 2017 Article en page(s) : pp 71 - 86 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes descripteurs IGN] algorithme d'apprentissage [Termes descripteurs IGN] arbre de décision [Termes descripteurs IGN] classification orientée objet [Termes descripteurs IGN] classification par arbre de décision [Termes descripteurs IGN] classification pixellaire [Termes descripteurs IGN] image Worldview [Termes descripteurs IGN] régression logistique Résumé : (auteur) Logistic model tree (LMT), a new method integrating standard decision tree (DT) induction and linear logistic regression algorithm in a single tree, have been recently proposed as an alternative to DT-based learning algorithms. In this study, the LMT was applied in the context of pixel- and object-based classifications using high-resolution WorldView-2 imagery, and its performance was compared with C4.5, random forest and Adaboost. Results of the study showed that the LMT generally produced more accurate classification results than the other methods for both pixel- and object-based classifications. The improvement in classification accuracy reached to 3% in pixel-based and 5% in object-based classifications. It was also estimated that the LMT algorithm produced the most accurate results considering the allocation and overall disagreement errors. Based on the Wilcoxon’s Signed-Ranks tests, the performance differences between the LMT and the other methods were statistically significant for both pixel- and object-based image classifications. Numéro de notice : A2017-085 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2015.1128486 date de publication en ligne : 12/01/2016 En ligne : http://dx.doi.org/10.1080/10106049.2015.1128486 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84410 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2017011	SL	Revue	Centre de documentation	Revues en salle	Disponible

Mapping urban road infrastructure using remotely sensed images / Taskin Kavzoglu in International Journal of Remote Sensing IJRS, vol 30 n° 7 (April 2009)

Public [article]  inInternational Journal of Remote Sensing IJRS > vol 30 n° 7 (April 2009) . - pp 1759 - 1769 Titre : Mapping urban road infrastructure using remotely sensed images Type de document : Article/Communication Auteurs : Taskin Kavzoglu, Auteur ; Y. Sen, Auteur ; M. Cetin, Auteur Année de publication : 2009 Article en page(s) : pp 1759 - 1769 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes descripteurs IGN] carte thématique [Termes descripteurs IGN] chaussée [Termes descripteurs IGN] image Ikonos [Termes descripteurs IGN] Istanbul (Turquie) [Termes descripteurs IGN] réalité de terrain [Termes descripteurs IGN] réseau routier Résumé : (Auteur) Comprehensive and accurate information on the conditions of the road infrastructure is essential for effective management and planning of the road network, especially in cities facing serious traffic congestion problems, as in the city of Istanbul, Turkey. One of the most important services of the local authorities is the rehabilitation of road surfaces. Asphalt resurfacing is carried out to renew the road surface and restore its resistance to weathered and traffic worn pavements. Today, the determination of pavement surface conditions is usually carried out through visual inspections by the experts and interpretation of in situ photographs/videos. In this study, an investigation has been made to understand the spectral behaviour of the asphalt in terms of its contents and age, also to discover the feasibility of using widely available satellite sensors in the determination of road surface conditions. Two datasets in the study area from D-100 road and TEM highway were used to examine asphalt road aging and deterioration. The changes to the conditions of the roads were detected using multispectral IKONOS images and ground spectral measurements for asphalt samples were obtained using an Analytical Spectral Devices full range (ASD FR) instrument in a laboratory environment. It was found that the road deformations mainly occur in areas where vehicles reduce or increase their speeds suddenly. Road sections just before toll booths and junctions are found to be more prone to deformations. IKONOS images can be effectively used to determine the condition of the asphalt pixels. Copyright Taylor & Francis Numéro de notice : A2009-171 Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29801 [article]

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
080-09041	RAB	Revue	Centre de documentation	En réserve 3L	Exclu du prêt