skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery

Sensors (Basel, Switzerland), 2017-12, Vol.18 (1), p.18 [Peer Reviewed Journal]

2018. This work is licensed under https://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. ;2017 by the authors. 2017 ;ISSN: 1424-8220 ;EISSN: 1424-8220 ;DOI: 10.3390/s18010018 ;PMID: 29271909

Full text available

Citations Cited by
  • Title:
    Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery
  • Author: Thanh Noi, Phan ; Kappas, Martin
  • Subjects: Classification ; classification algorithms ; Classifiers ; Datasets ; Image classification ; k-Nearest Neighbor (kNN) ; Land cover ; Land use ; Pixels ; Random Forest (RF) ; Remote sensing ; Sentinel-2 ; Support Vector Machine (SVM) ; Support vector machines ; Training ; training sample size
  • Is Part Of: Sensors (Basel, Switzerland), 2017-12, Vol.18 (1), p.18
  • Description: In previous classification studies, three non-parametric classifiers, Random Forest (RF), k-Nearest Neighbor (kNN), and Support Vector Machine (SVM), were reported as the foremost classifiers at producing high accuracies. However, only a few studies have compared the performances of these classifiers with different training sample sizes for the same remote sensing images, particularly the Sentinel-2 Multispectral Imager (MSI). In this study, we examined and compared the performances of the RF, kNN, and SVM classifiers for land use/cover classification using Sentinel-2 image data. An area of 30 × 30 km² within the Red River Delta of Vietnam with six land use/cover types was classified using 14 different training sample sizes, including balanced and imbalanced, from 50 to over 1250 pixels/class. All classification results showed a high overall accuracy (OA) ranging from 90% to 95%. Among the three classifiers and 14 sub-datasets, SVM produced the highest OA with the least sensitivity to the training sample sizes, followed consecutively by RF and kNN. In relation to the sample size, all three classifiers showed a similar and high OA (over 93.85%) when the training sample size was large enough, i.e., greater than 750 pixels/class or representing an area of approximately 0.25% of the total study area. The high accuracy was achieved with both imbalanced and balanced datasets.
  • Publisher: Switzerland: MDPI AG
  • Language: English
  • Identifier: ISSN: 1424-8220
    EISSN: 1424-8220
    DOI: 10.3390/s18010018
    PMID: 29271909
  • Source: Geneva Foundation Free Medical Journals at publisher websites
    ROAD
    PubMed Central
    ProQuest Central
    DOAJ Directory of Open Access Journals
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait