{"id":7424,"date":"2026-08-28T12:12:47","date_gmt":"2026-08-28T10:12:47","guid":{"rendered":"https:\/\/francestat.com\/?page_id=7424"},"modified":"2026-08-29T11:51:32","modified_gmt":"2026-08-29T09:51:32","slug":"uniwin-spectral","status":"publish","type":"page","link":"https:\/\/francestat.com\/index.php\/uniwin-spectral\/","title":{"rendered":"UNIWIN – SPECTRAL"},"content":{"rendered":"

[vc_row][vc_column]

<\/div>

UNIWIN - Classification spectrale<\/h2><\/div><\/div>[\/vc_column][\/vc_row][vc_row][vc_column][vc_empty_space][\/vc_column][\/vc_row][vc_row][vc_column][vc_column_text css=\u00a0\u00bb\u00a0\u00bb]La classification spectrale est une technique utilis\u00e9e pour partitionner un ensemble de donn\u00e9es en classes. Contrairement aux m\u00e9thodes traditionnelles de regroupement, la classification spectrale est particuli\u00e8rement puissante pour les ensembles de donn\u00e9es dont la structure n\u2019est pas n\u00e9cessairement convexe.<\/p>\n

Pratiquement, les trois \u00e9tapes suivantes sont r\u00e9alis\u00e9es\u00a0:<\/p>\n

1) Construction du graphe des similarit\u00e9s : calcul d\u2019une matrice de similarit\u00e9s entre les points de donn\u00e9es en utilisant un noyau \u00e0 base radiale (RBF) pour former un graphe o\u00f9 les ar\u00eates relient les points proches.<\/p>\n

2) Projection spectrale : calcul du laplacien du graphe et extraction de ses vecteurs propres associ\u00e9s aux plus petites valeurs propres pour projeter les donn\u00e9es dans un nouvel espace de dimension r\u00e9duite.<\/p>\n

3) Regroupement : utilisation de l\u2019algorithme de partitionnement des k-moyennes sur ces nouvelles coordonn\u00e9es spectrales, lin\u00e9airement s\u00e9parables, pour obtenir les groupes finaux.<\/p>\n

La proc\u00e9dure affiche un rapport indiquant notamment es valeurs propres, vecteurs propres et coefficients de silhouette spectraux, les classes affect\u00e9es aux observations et les coefficients de silhouette. Les graphiques des valeurs et vecteurs propres, des sauts dans les valeurs propres, des coefficients de silhouette spectraux et des observations, des distances d’accessibilit\u00e9 par densit\u00e9 ainsi que des nuages des points des classes sont propos\u00e9s.<\/p>\n

Cette proc\u00e9dure est bas\u00e9e sur les packages R ‘kernlab’, ‘cluster’ et ‘clusterCrit’.[\/vc_column_text][\/vc_column][\/vc_row][vc_row][vc_column][vc_single_image image=\u00a0\u00bb7437″ img_size=\u00a0\u00bblarge\u00a0\u00bb alignment=\u00a0\u00bbcenter\u00a0\u00bb css=\u00a0\u00bb\u00a0\u00bb][vc_empty_space height=\u00a0\u00bb5px\u00a0\u00bb][vc_column_text css=\u00a0\u00bb\u00a0\u00bb]<\/p>\n

Tableaux<\/u><\/span><\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n
\n

Moyennes et \u00e9carts-types des donn\u00e9es<\/p>\n<\/td>\n<\/tr>\n

\n

Sigma, nombre de classes, silhouette<\/p>\n<\/td>\n<\/tr>\n

\n

Sigma, nombre de classes, sauts<\/p>\n<\/td>\n<\/tr>\n

\n

Valeurs propres et vecteurs propres<\/p>\n<\/td>\n<\/tr>\n

\n

Synth\u00e8se de la classification<\/p>\n<\/td>\n<\/tr>\n

\n

Classification des observations<\/p>\n<\/td>\n<\/tr>\n

\n

Centro\u00efdes non standardis\u00e9s des classes<\/p>\n<\/td>\n<\/tr>\n

\n

Centro\u00efdes standardis\u00e9s des classes<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

Graphiques<\/u><\/span><\/strong><\/p>\n\n\n\n\n\n\n\n\n\n
\n

Graphique des coefficients de silhouette (espace spectral)<\/p>\n<\/td>\n<\/tr>\n

\n

Graphique des sauts (espace spectral)<\/p>\n<\/td>\n<\/tr>\n

\n

Graphique des valeurs propres (espace spectral)<\/p>\n<\/td>\n<\/tr>\n

\n

Graphique codifi\u00e9 des vecteurs propres (espace spectral)<\/p>\n<\/td>\n<\/tr>\n

\n

Graphique des coefficients individuels de silhouette<\/p>\n<\/td>\n<\/tr>\n

\n

Graphique des distances d’accessibilit\u00e9 par densit\u00e9<\/p>\n<\/td>\n<\/tr>\n

\n

Nuages de points des classes form\u00e9es<\/p>\n<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

[\/vc_column_text][vc_empty_space height=\u00a0\u00bb5px\u00a0\u00bb][\/vc_column][\/vc_row][vc_row][vc_column][vc_btn title=\u00a0\u00bbConsulter la documentation compl\u00e8te\u00a0\u00bb align=\u00a0\u00bbcenter\u00a0\u00bb css=\u00a0\u00bb\u00a0\u00bb link=\u00a0\u00bburl:http%3A%2F%2Fwww.francestat.com%2Ftelecharg%2FUniwin%2Fpdf%2FClassification%20spectrale.pdf|title:UNIWIN%20-%20SPECTRAL\u00a0\u00bb][\/vc_column][\/vc_row]<\/p>\n<\/div>","protected":false},"excerpt":{"rendered":"

[vc_row][vc_column][\/vc_column][\/vc_row][vc_row][vc_column][vc_empty_space][\/vc_column][\/vc_row][vc_row][vc_column][vc_column_text css=\u00a0\u00bb\u00a0\u00bb]La classification spectrale est une technique utilis\u00e9e pour partitionner un ensemble de donn\u00e9es en classes. Contrairement aux m\u00e9thodes traditionnelles de regroupement, la classification spectrale est particuli\u00e8rement puissante pour les ensembles de donn\u00e9es dont la structure n\u2019est pas n\u00e9cessairement convexe. Pratiquement, les trois \u00e9tapes suivantes sont r\u00e9alis\u00e9es\u00a0: 1) Construction du graphe des similarit\u00e9s : calcul…<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-7424","page","type-page","status-publish","hentry","description-off"],"yoast_head":"\nUNIWIN - SPECTRAL - FRANCESTAT<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/francestat.com\/index.php\/uniwin-spectral\/\" \/>\n<meta property=\"og:locale\" content=\"fr_FR\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"UNIWIN - SPECTRAL - FRANCESTAT\" \/>\n<meta property=\"og:description\" content=\"[vc_row][vc_column][\/vc_column][\/vc_row][vc_row][vc_column][vc_empty_space][\/vc_column][\/vc_row][vc_row][vc_column][vc_column_text css=\u00a0\u00bb\u00a0\u00bb]La classification spectrale est une technique utilis\u00e9e pour partitionner un ensemble de donn\u00e9es en classes. Contrairement aux m\u00e9thodes traditionnelles de regroupement, la classification spectrale est particuli\u00e8rement puissante pour les ensembles de donn\u00e9es dont la structure n\u2019est pas n\u00e9cessairement convexe. Pratiquement, les trois \u00e9tapes suivantes sont r\u00e9alis\u00e9es\u00a0: 1) Construction du graphe des similarit\u00e9s : calcul…\" \/>\n<meta property=\"og:url\" content=\"https:\/\/francestat.com\/index.php\/uniwin-spectral\/\" \/>\n<meta property=\"og:site_name\" content=\"FRANCESTAT\" \/>\n<meta property=\"article:modified_time\" content=\"2026-08-29T09:51:32+00:00\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Dur\u00e9e de lecture estim\u00e9e\" \/>\n\t<meta name=\"twitter:data1\" content=\"2 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/francestat.com\\\/index.php\\\/uniwin-spectral\\\/\",\"url\":\"https:\\\/\\\/francestat.com\\\/index.php\\\/uniwin-spectral\\\/\",\"name\":\"UNIWIN - SPECTRAL - FRANCESTAT\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/francestat.com\\\/#website\"},\"datePublished\":\"2026-08-28T10:12:47+00:00\",\"dateModified\":\"2026-08-29T09:51:32+00:00\",\"breadcrumb\":{\"@id\":\"https:\\\/\\\/francestat.com\\\/index.php\\\/uniwin-spectral\\\/#breadcrumb\"},\"inLanguage\":\"fr-FR\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\\\/\\\/francestat.com\\\/index.php\\\/uniwin-spectral\\\/\"]}]},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/francestat.com\\\/index.php\\\/uniwin-spectral\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Accueil\",\"item\":\"https:\\\/\\\/francestat.com\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"UNIWIN – SPECTRAL\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/francestat.com\\\/#website\",\"url\":\"https:\\\/\\\/francestat.com\\\/\",\"name\":\"FRANCESTAT\",\"description\":\"Logiciels, formations et services statistiques\",\"publisher\":{\"@id\":\"https:\\\/\\\/francestat.com\\\/#organization\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\\\/\\\/francestat.com\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"fr-FR\"},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/francestat.com\\\/#organization\",\"name\":\"FRANCESTAT\",\"url\":\"https:\\\/\\\/francestat.com\\\/\",\"logo\":{\"@type\":\"ImageObject\",\"inLanguage\":\"fr-FR\",\"@id\":\"https:\\\/\\\/francestat.com\\\/#\\\/schema\\\/logo\\\/image\\\/\",\"url\":\"https:\\\/\\\/francestat.com\\\/wp-content\\\/uploads\\\/2018\\\/05\\\/logo_horizontal_small_francestat.jpg\",\"contentUrl\":\"https:\\\/\\\/francestat.com\\\/wp-content\\\/uploads\\\/2018\\\/05\\\/logo_horizontal_small_francestat.jpg\",\"width\":155,\"height\":51,\"caption\":\"FRANCESTAT\"},\"image\":{\"@id\":\"https:\\\/\\\/francestat.com\\\/#\\\/schema\\\/logo\\\/image\\\/\"}}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"UNIWIN - SPECTRAL - FRANCESTAT","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/francestat.com\/index.php\/uniwin-spectral\/","og_locale":"fr_FR","og_type":"article","og_title":"UNIWIN - SPECTRAL - FRANCESTAT","og_description":"[vc_row][vc_column][\/vc_column][\/vc_row][vc_row][vc_column][vc_empty_space][\/vc_column][\/vc_row][vc_row][vc_column][vc_column_text css=\u00a0\u00bb\u00a0\u00bb]La classification spectrale est une technique utilis\u00e9e pour partitionner un ensemble de donn\u00e9es en classes. Contrairement aux m\u00e9thodes traditionnelles de regroupement, la classification spectrale est particuli\u00e8rement puissante pour les ensembles de donn\u00e9es dont la structure n\u2019est pas n\u00e9cessairement convexe. Pratiquement, les trois \u00e9tapes suivantes sont r\u00e9alis\u00e9es\u00a0: 1) Construction du graphe des similarit\u00e9s : calcul…","og_url":"https:\/\/francestat.com\/index.php\/uniwin-spectral\/","og_site_name":"FRANCESTAT","article_modified_time":"2026-08-29T09:51:32+00:00","twitter_card":"summary_large_image","twitter_misc":{"Dur\u00e9e de lecture estim\u00e9e":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/francestat.com\/index.php\/uniwin-spectral\/","url":"https:\/\/francestat.com\/index.php\/uniwin-spectral\/","name":"UNIWIN - SPECTRAL - FRANCESTAT","isPartOf":{"@id":"https:\/\/francestat.com\/#website"},"datePublished":"2026-08-28T10:12:47+00:00","dateModified":"2026-08-29T09:51:32+00:00","breadcrumb":{"@id":"https:\/\/francestat.com\/index.php\/uniwin-spectral\/#breadcrumb"},"inLanguage":"fr-FR","potentialAction":[{"@type":"ReadAction","target":["https:\/\/francestat.com\/index.php\/uniwin-spectral\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/francestat.com\/index.php\/uniwin-spectral\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Accueil","item":"https:\/\/francestat.com\/"},{"@type":"ListItem","position":2,"name":"UNIWIN – SPECTRAL"}]},{"@type":"WebSite","@id":"https:\/\/francestat.com\/#website","url":"https:\/\/francestat.com\/","name":"FRANCESTAT","description":"Logiciels, formations et services statistiques","publisher":{"@id":"https:\/\/francestat.com\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/francestat.com\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"fr-FR"},{"@type":"Organization","@id":"https:\/\/francestat.com\/#organization","name":"FRANCESTAT","url":"https:\/\/francestat.com\/","logo":{"@type":"ImageObject","inLanguage":"fr-FR","@id":"https:\/\/francestat.com\/#\/schema\/logo\/image\/","url":"https:\/\/francestat.com\/wp-content\/uploads\/2018\/05\/logo_horizontal_small_francestat.jpg","contentUrl":"https:\/\/francestat.com\/wp-content\/uploads\/2018\/05\/logo_horizontal_small_francestat.jpg","width":155,"height":51,"caption":"FRANCESTAT"},"image":{"@id":"https:\/\/francestat.com\/#\/schema\/logo\/image\/"}}]}},"_links":{"self":[{"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/pages\/7424","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/comments?post=7424"}],"version-history":[{"count":12,"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/pages\/7424\/revisions"}],"predecessor-version":[{"id":7442,"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/pages\/7424\/revisions\/7442"}],"wp:attachment":[{"href":"https:\/\/francestat.com\/index.php\/wp-json\/wp\/v2\/media?parent=7424"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}