<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>3</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Kerroum, M A</style></author><author><style face="normal" font="default" size="100%">Hammouch, A</style></author><author><style face="normal" font="default" size="100%">Aboutajdine, D</style></author><author><style face="normal" font="default" size="100%">Bellaachia, A</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Using the maximum Mutual Information criterion to textural Feature Selection for satellite image classification</style></title><secondary-title><style face="normal" font="default" size="100%">Computers and Communications, 2008. ISCC 2008. IEEE Symposium on</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Cooccurrence Matrix</style></keyword><keyword><style  face="normal" font="default" size="100%">LDA</style></keyword><keyword><style  face="normal" font="default" size="100%">mutual information</style></keyword><keyword><style  face="normal" font="default" size="100%">PCA</style></keyword><keyword><style  face="normal" font="default" size="100%">Satellite Image Classi- fication</style></keyword><keyword><style  face="normal" font="default" size="100%">SVM</style></keyword><keyword><style  face="normal" font="default" size="100%">Textural Feature Selection</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2008</style></year></dates><pages><style face="normal" font="default" size="100%">1005-1009</style></pages><isbn><style face="normal" font="default" size="100%">1530-1346 VO -</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">This paper presents and evaluates the use of the maximum mutual information criterion to textural feature selection for satellite image classification. Our approach is based on a recent work of Mutual Information Feature Selector Algorithm. The effectiveness of the proposed approach is evaluated on real data. In fact, the textural features are extracted using the cooccurrence matrix from two forest zones of SPOT HRV(XS) image in the region of Rabat, Morocco. The experimental tests of this study prove that the proposed approach gives a better performance for satellite image classification than classical methods such as principal components analysis (PCA) and linear discriminant analysis (LDA). The classifier used in this work is the support vectors machine (SVM).</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Kaniewski, D</style></author><author><style face="normal" font="default" size="100%">Renault-Miskovsky, J</style></author><author><style face="normal" font="default" size="100%">de Lumley, H</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Palaeovegetation from a Homo neanderthalensis occupation in Western Liguria: archaeopalynology of Madonna dell'Arma (San Remo, Italy)</style></title><secondary-title><style face="normal" font="default" size="100%">JOURNAL OF ARCHAEOLOGICAL SCIENCE</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">archaeopalynology</style></keyword><keyword><style  face="normal" font="default" size="100%">Italy</style></keyword><keyword><style  face="normal" font="default" size="100%">Liguria</style></keyword><keyword><style  face="normal" font="default" size="100%">Middle Palaeolithic</style></keyword><keyword><style  face="normal" font="default" size="100%">OIS 4</style></keyword><keyword><style  face="normal" font="default" size="100%">PCA</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">2005</style></year></dates><publisher><style face="normal" font="default" size="100%">ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD</style></publisher><pub-location><style face="normal" font="default" size="100%">24-28 OVAL RD, LONDON NW1 7DX, ENGLAND</style></pub-location><volume><style face="normal" font="default" size="100%">32</style></volume><pages><style face="normal" font="default" size="100%">827-840</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">This study presents a short local vegetation history of Western Liguria (San Remo), northwest Italy, based on a palynological analyses of an 8.30-m-long archaeological section in the dune covering Madonna dell'Arma cave. Madonna dell'Arma is one of the Mousterian caves currently located on the Ligurian coastal zone. The site contains Levallois-type Mousterian tools, four pieces of skull attributed to Homo neanderthalensis and fauna remains belonging to Rhinoceros mercki, Elephas sp. and Hippopotamus amphibius. This study is of interest as the site is situated in an area where data on palaeovegetation. are scarce. In fact, the archaeopollen analyses of Madonna dell'Arma cave's surroundings provide a rare local picture of vegetation during the beginning of OIS 4, posterior to 73,100 yr BP. The palynological taxa are grouped into three vegetation units by PCA (principal components analysis). These data suggest a huge Mediterranean pre-steppic forest (Pinus, Quercus ilex and several herbs) colonizing the area during this substage. The adjacent valleys were colonized by a caducifoliate-alluvial forest and Mediterranean scrub vegetation. These vegetation characteristics suggest a semi-arid coastal climate with an increase of precipitation according to altitude. The PCA analyses of the palynological sections inside and outside the cave suggest a nearly continuous vegetation succession from OIS 5a to OIS 4. (c) 2005 Elsevier Ltd. All rights reserved.</style></abstract></record></records></xml>