venerdì 18 gennaio 2019     |
Database riviste di LUOGOESPAZIO.INFO
La finestra di ricerca qui sotto interroga il database di LUOGOESPAZIO.INFO, creato esclusivamente per supportare la libera ricerca scientifica e senza nessuno scopo di lucro.

Il database contiene riferimenti, abstract e indicazioni bibliografiche su una selezione delle principali riviste geografiche scientifiche nazionali ed estere. La ricerca è sensibile alle maiuscole/minuscole ed è full-text (opera su tutte le onformazioni, abstract compreso, ove presente). 

Non è necessario l'uso del carattere jolly *: cercando una parte della parola verranno trovate automaticamente le occorrenze che la contengono (ad esempio cercando "rif" si troveranno tanto le occorrenze di "riferimento", quanto "rifugio", come "tariffa" ecc.).

Uno sguardo alle riviste geografiche italiane e internazionali


Al momento sono incluse, con tutti i fascicoli pubbicati nel 2009:

Il database viene continuamente aggiornato e implementato: altre riviste scientifiche verranno aggiunte progressivamente

This website support geographical scientific research. All the references included here are intended for scientific research only; every reference is reported with its own source. Please follow the source to buy the full paper, if interested.

Cliccare sulla lente d'ingrandimento per visualizzare la scheda completa con eventuale abstract o testo integrale -
Back
Logo testata: Logo testata
Link alla fonte (source): http://www.informaworld.com/smpp/title~db=all~content=g906616930
titolo articolo: Using Geometrical, Textural, and Contextual Information of Land Parcels for Classification of Detailed Urban Land Use
Autore/i (Cogn. Nome): Wu Shuo-Sheng; Qiu Xiaomin; Usery E. Lynn; Wang Le
Abstract:

Detailed urban land use data are important to government officials, researchers, and businesspeople for a variety of purposes. This article presents an approach to classifying detailed urban land use based on geometrical, textural, and contextual information of land parcels. An area of 6 by 14 km in Austin, Texas, with land parcel boundaries delineated by the Travis Central Appraisal District of Travis County, Texas, is tested for the approach. We derive fifty parcel attributes from relevant geographic information system (GIS) and remote sensing data and use them to discriminate among nine urban land uses: single family, multifamily, commercial, office, industrial, civic, open space, transportation, and undeveloped. Half of the 33,025 parcels in the study area are used as training data for land use classification and the other half are used as testing data for accuracy assessment. The best result with a decision tree classification algorithm has an overall accuracy of 96 percent and a kappa coefficient of 0.78, and two naive, baseline models based on the majority rule and the spatial autocorrelation rule have overall accuracy of 89 percent and 79 percent, respectively. The algorithm is relatively good at classifying single-family, multifamily, commercial, open space, and undeveloped land uses and relatively poor at classifying office, industrial, civic, and transportation land uses. The most important attributes for land use classification are the geometrical attributes, particularly those related to building areas. Next are the contextual attributes, particularly those relevant to the spatial relationship between buildings, then the textural attributes, particularly the semivariance texture statistic from 0.61-m resolution images.

rivista: Annals of the Association of American Geographers
numero: Issue 1 2009
anno: 2009
Pagine: 76-98
Parole chiave - keywords: contextual classification; field-based; land use classification; per field; textural classification
L&S ranking: nv

Modificato il: 05/08/2009 18.20 Modificato da: Massimiliano Tabusi
Creato il: 05/08/2009 18.20 Creato da: Massimiliano Tabusi
CopyLeft (cL) www.luogoespazio.info (placeandspace.info) [citare questa fonte]   |  Dichiarazione per la Privacy  |  Condizioni d'Uso