THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION

Methods of classification by nature of decision-making divide on methods using global optimization (all training samples are used), and local optimization (only samples in the neighbourhood of the studied object are used). The perspective direction of research is combination of advantages of each ap...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Victor V. Kitov
Formato:	article
Lenguaje:	RU
Publicado:	Plekhanov Russian University of Economics 2017
Materias:	classification decisive trees metric signs type of a forest cover Economics as a science HB71-74
Acceso en línea:	https://doaj.org/article/d7813279126b44f4990673f076e32e41
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d7813279126b44f4990673f076e32e41
record_format	dspace
spelling	oai:doaj.org-article:d7813279126b44f4990673f076e32e412021-11-15T05:20:43ZTHE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION2413-28292587-925110.21686/2413-2829-2015-4-148-152https://doaj.org/article/d7813279126b44f4990673f076e32e412017-09-01T00:00:00Zhttps://vest.rea.ru/jour/article/view/74https://doaj.org/toc/2413-2829https://doaj.org/toc/2587-9251Methods of classification by nature of decision-making divide on methods using global optimization (all training samples are used), and local optimization (only samples in the neighbourhood of the studied object are used). The perspective direction of research is combination of advantages of each approach in one integrated classifier. In article the method of combination of these approaches by embedding of local metric features into the approach using global optimization is proposed. This approach is shown for a case when the classifier using global optimization is random forest and extra random trees. Various variants of metric features are evaluated. Performance of the proposed approach is illustrated on the forest cover type prediction task, where it leads to significant improvement in classification accuracy.Victor V. KitovPlekhanov Russian University of Economicsarticleclassificationdecisive treesmetric signstype of a forest coverEconomics as a scienceHB71-74RUВестник Российского экономического университета имени Г. В. Плеханова, Vol 0, Iss 4, Pp 148-152 (2017)
institution	DOAJ
collection	DOAJ
language	RU
topic	classification decisive trees metric signs type of a forest cover Economics as a science HB71-74
spellingShingle	classification decisive trees metric signs type of a forest cover Economics as a science HB71-74 Victor V. Kitov THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION
description	Methods of classification by nature of decision-making divide on methods using global optimization (all training samples are used), and local optimization (only samples in the neighbourhood of the studied object are used). The perspective direction of research is combination of advantages of each approach in one integrated classifier. In article the method of combination of these approaches by embedding of local metric features into the approach using global optimization is proposed. This approach is shown for a case when the classifier using global optimization is random forest and extra random trees. Various variants of metric features are evaluated. Performance of the proposed approach is illustrated on the forest cover type prediction task, where it leads to significant improvement in classification accuracy.
format	article
author	Victor V. Kitov
author_facet	Victor V. Kitov
author_sort	Victor V. Kitov
title	THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION
title_short	THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION
title_full	THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION
title_fullStr	THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION
title_full_unstemmed	THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION
title_sort	usage of metric features in prediction with decision trees demonstrated on the task of forest cover type classification
publisher	Plekhanov Russian University of Economics
publishDate	2017
url	https://doaj.org/article/d7813279126b44f4990673f076e32e41
work_keys_str_mv	AT victorvkitov theusageofmetricfeaturesinpredictionwithdecisiontreesdemonstratedonthetaskofforestcovertypeclassification AT victorvkitov usageofmetricfeaturesinpredictionwithdecisiontreesdemonstratedonthetaskofforestcovertypeclassification
_version_	1718428778793795584

THE USAGE OF METRIC FEATURES IN PREDICTION WITH DECISION TREES DEMONSTRATED ON THE TASK OF FOREST COVER TYPE CLASSIFICATION

Ejemplares similares