Please use this identifier to cite or link to this item:
Title: A comparative study of various supervised learning approaches to selective omission in a road network
Authors: Zhou, Q
Li, Z 
Keywords: Road network
Selective omission
Supervised learning
Issue Date: 2017
Publisher: Taylor & Francis
Source: Cartographic journal, 2017, v. 54, no. 3, p. 254-264 How to cite?
Journal: Cartographic journal 
Abstract: Selective omission is necessary for road network generalisation. This study investigates the use of supervised learning approaches for selective omission in a road network. To be specific, at first, the properties to measure the importance of a road in the network are viewed as input attributes, and the decision of such a road is retained or not at a specific scale is viewed as an output classMergeCell then, a number of samples with known input and output are used to train a classifierMergeCell finally, this classifier can be used to determine whether other roads to be retained or not. In this study, a total of nine supervised learning approaches, i.e., ID3, C4·5, CRT, Random Tree, support vector machine (SVM), naive Bayes (NB), K-nearest neighbour (KNN), multilayer perception (MP) and binary logistic regression (BLR), are applied to three road networks for selective omission. The performances of these approaches are evaluated by both quantitative assessment and visual inception. Results show that: (1) in most cases, these approaches are effective and their classification accuracy is between 70% and 90%MergeCell (2) most of these approaches have similar performances, and they do not have any statistically significant differenceMergeCell (3) but sometimes, ID3 and BLR performs significantly better than NB and SVMMergeCell NB and KNN perform significantly worse than MP, SVM and BLR.
ISSN: 0008-7041
EISSN: 1743-2774
DOI: 10.1179/1743277414Y.0000000083
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Apr 6, 2019

Page view(s)

Last Week
Last month
Citations as of Jul 16, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.