Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level

Sikdar M. M. Rasel; Hsing-Chung Chang; Israt Jahan Diti; Tim Glasby

doi:10.1109/IGARSS.2019.8897942

Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level

Sikdar M. M. Rasel, Hsing-Chung Chang, Israt Jahan Diti, Tim Glasby

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

2 Citations (Scopus)

Abstract

Ground truth data collection for species-level mapping is made challenging by limited access and hazardous conditions in some wetland ecosystems. Support Vector Machine (SVM), and the relationship between kernel smoothness parameter of SVM and spectral separability are investigated with a limited number of sample. The overall accuracy (OA) for 8 classes was around 56.25% (kappa = 0.50) for MLC, 78.12 % (kappa=0.75) for SVM (radial basis function) and 78.90% (kappa=0.76) for SVM (polynomial). When the polynomial kernel increased from 2 to 4, producer accuracy (%) increased from 81.25% to 87.50% and 53.22% to 66.67 % for Mangrove (Avicennia marina) and Swamp She-oak (Casuarina glauca) tree species respectively. This accuracy is acceptable as 15% of the required sample provided 79% overall accuracy from SVM and is comparable to other previous studies.

Original language	English
Title of host publication	IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium
Subtitle of host publication	proceedings
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	2674-2677
Number of pages	4
ISBN (Electronic)	9781538691540, 9781538691533
ISBN (Print)	9781538691557
DOIs	https://doi.org/10.1109/IGARSS.2019.8897942
Publication status	Published - 2019
Event	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 - Yokohama, Japan Duration: 28 Jul 2019 → 2 Aug 2019

Publication series

Name
ISSN (Print)	2153-6996
ISSN (Electronic)	2153-7003

Conference

Conference	39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019
Country/Territory	Japan
City	Yokohama
Period	28/07/19 → 2/08/19

Access to Document

10.1109/IGARSS.2019.8897942

Cite this

Rasel, S. M. M., Chang, H.-C., Diti, I. J., & Glasby, T. (2019). Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level. In IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium: proceedings (pp. 2674-2677). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/IGARSS.2019.8897942

Rasel, Sikdar M. M. ; Chang, Hsing-Chung ; Diti, Israt Jahan et al. / Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level. IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium: proceedings. Piscataway, NJ : Institute of Electrical and Electronics Engineers (IEEE), 2019. pp. 2674-2677

@inproceedings{83049918c92f45d3984f9d46fffeb227,

title = "Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level",

abstract = "Ground truth data collection for species-level mapping is made challenging by limited access and hazardous conditions in some wetland ecosystems. Support Vector Machine (SVM), and the relationship between kernel smoothness parameter of SVM and spectral separability are investigated with a limited number of sample. The overall accuracy (OA) for 8 classes was around 56.25\% (kappa = 0.50) for MLC, 78.12 \% (kappa=0.75) for SVM (radial basis function) and 78.90\% (kappa=0.76) for SVM (polynomial). When the polynomial kernel increased from 2 to 4, producer accuracy (\%) increased from 81.25\% to 87.50\% and 53.22\% to 66.67 \% for Mangrove (Avicennia marina) and Swamp She-oak (Casuarina glauca) tree species respectively. This accuracy is acceptable as 15\% of the required sample provided 79\% overall accuracy from SVM and is comparable to other previous studies.",

author = "Rasel, \{Sikdar M. M.\} and Hsing-Chung Chang and Diti, \{Israt Jahan\} and Tim Glasby",

year = "2019",

doi = "10.1109/IGARSS.2019.8897942",

language = "English",

isbn = "9781538691557",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

pages = "2674--2677",

booktitle = "IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium",

address = "United States",

note = "39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

}

Rasel, SMM, Chang, H-C, Diti, IJ & Glasby, T 2019, Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level. in IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium: proceedings. Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 2674-2677, 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019, Yokohama, Japan, 28/07/19. https://doi.org/10.1109/IGARSS.2019.8897942

Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level. / Rasel, Sikdar M. M.; Chang, Hsing-Chung; Diti, Israt Jahan et al.
IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium: proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2019. p. 2674-2677.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level

AU - Rasel, Sikdar M. M.

AU - Chang, Hsing-Chung

AU - Diti, Israt Jahan

AU - Glasby, Tim

PY - 2019

Y1 - 2019

N2 - Ground truth data collection for species-level mapping is made challenging by limited access and hazardous conditions in some wetland ecosystems. Support Vector Machine (SVM), and the relationship between kernel smoothness parameter of SVM and spectral separability are investigated with a limited number of sample. The overall accuracy (OA) for 8 classes was around 56.25% (kappa = 0.50) for MLC, 78.12 % (kappa=0.75) for SVM (radial basis function) and 78.90% (kappa=0.76) for SVM (polynomial). When the polynomial kernel increased from 2 to 4, producer accuracy (%) increased from 81.25% to 87.50% and 53.22% to 66.67 % for Mangrove (Avicennia marina) and Swamp She-oak (Casuarina glauca) tree species respectively. This accuracy is acceptable as 15% of the required sample provided 79% overall accuracy from SVM and is comparable to other previous studies.

AB - Ground truth data collection for species-level mapping is made challenging by limited access and hazardous conditions in some wetland ecosystems. Support Vector Machine (SVM), and the relationship between kernel smoothness parameter of SVM and spectral separability are investigated with a limited number of sample. The overall accuracy (OA) for 8 classes was around 56.25% (kappa = 0.50) for MLC, 78.12 % (kappa=0.75) for SVM (radial basis function) and 78.90% (kappa=0.76) for SVM (polynomial). When the polynomial kernel increased from 2 to 4, producer accuracy (%) increased from 81.25% to 87.50% and 53.22% to 66.67 % for Mangrove (Avicennia marina) and Swamp She-oak (Casuarina glauca) tree species respectively. This accuracy is acceptable as 15% of the required sample provided 79% overall accuracy from SVM and is comparable to other previous studies.

UR - https://www.scopus.com/pages/publications/85077722538

U2 - 10.1109/IGARSS.2019.8897942

DO - 10.1109/IGARSS.2019.8897942

M3 - Conference proceeding contribution

AN - SCOPUS:85077722538

SN - 9781538691557

SP - 2674

EP - 2677

BT - IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Rasel SMM, Chang HC, Diti IJ, Glasby T. Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level. In IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium: proceedings. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2019. p. 2674-2677 doi: 10.1109/IGARSS.2019.8897942

Support Vector Machine (SVM) classifier with small training samples for mapping saltmash wetland at species level

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this