Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data
Land cover classification is an essential process in many remote sensing applications. Classification based on supervised methods have been preferred by many due to its practicality, accuracy and objectivity compared to unsupervised methods. Nevertheless, the performance of different supervised meth...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Science and Information (SAI) Organization Limited
2018
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/3552/ http://eprints.uthm.edu.my/3552/1/AJ%202018%20%28700%29%20Comparative%20analysis%20of%20support%20vector%20machine%2C%20maximum%20likelihood%20and%20neural%20network%20classification%20on%20multispectral%20remote%20sensing%20data.pdf |
| _version_ | 1848888051069091840 |
|---|---|
| author | Ahmad, Asmala Mohd Hashim, Ummi Kalsom Mohd, Othman Abdullah, Mohd Mawardy Sakidin, Hamzah Rasib, Abd Wahid Sufahani, Suliadi Firdaus |
| author_facet | Ahmad, Asmala Mohd Hashim, Ummi Kalsom Mohd, Othman Abdullah, Mohd Mawardy Sakidin, Hamzah Rasib, Abd Wahid Sufahani, Suliadi Firdaus |
| author_sort | Ahmad, Asmala |
| building | UTHM Institutional Repository |
| collection | Online Access |
| description | Land cover classification is an essential process in many remote sensing applications. Classification based on supervised methods have been preferred by many due to its practicality, accuracy and objectivity compared to unsupervised methods. Nevertheless, the performance of different supervised methods particularly for classifying land covers in Tropical regions such as Malaysia has not been evaluated thoroughly. The study reported in this paper aims to detect land cover changes using multispectral remote sensing data. The data come from Landsat satellite covering part of Klang District, located in Selangor, Malaysia. Landsat bands 1, 2, 3, 4, 5 and 7 are used as the input for three supervised classification methods namely support vector machines (SVM), maximum likelihood (ML) and neural network (NN). The accuracy of the generated classifications is then assessed by means of classification accuracy. Land cover change analysis is also carried out to identify the most reliable method to detect land changes in which showing SVM gives a more stable and realistic outcomes compared to ML and NN. |
| first_indexed | 2025-11-15T20:04:08Z |
| format | Article |
| id | uthm-3552 |
| institution | Universiti Tun Hussein Onn Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:04:08Z |
| publishDate | 2018 |
| publisher | The Science and Information (SAI) Organization Limited |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | uthm-35522021-11-18T07:07:19Z http://eprints.uthm.edu.my/3552/ Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data Ahmad, Asmala Mohd Hashim, Ummi Kalsom Mohd, Othman Abdullah, Mohd Mawardy Sakidin, Hamzah Rasib, Abd Wahid Sufahani, Suliadi Firdaus QA75 Electronic computers. Computer science TP200-248 Chemicals: Manufacture, use, etc. Land cover classification is an essential process in many remote sensing applications. Classification based on supervised methods have been preferred by many due to its practicality, accuracy and objectivity compared to unsupervised methods. Nevertheless, the performance of different supervised methods particularly for classifying land covers in Tropical regions such as Malaysia has not been evaluated thoroughly. The study reported in this paper aims to detect land cover changes using multispectral remote sensing data. The data come from Landsat satellite covering part of Klang District, located in Selangor, Malaysia. Landsat bands 1, 2, 3, 4, 5 and 7 are used as the input for three supervised classification methods namely support vector machines (SVM), maximum likelihood (ML) and neural network (NN). The accuracy of the generated classifications is then assessed by means of classification accuracy. Land cover change analysis is also carried out to identify the most reliable method to detect land changes in which showing SVM gives a more stable and realistic outcomes compared to ML and NN. The Science and Information (SAI) Organization Limited 2018 Article PeerReviewed text en http://eprints.uthm.edu.my/3552/1/AJ%202018%20%28700%29%20Comparative%20analysis%20of%20support%20vector%20machine%2C%20maximum%20likelihood%20and%20neural%20network%20classification%20on%20multispectral%20remote%20sensing%20data.pdf Ahmad, Asmala and Mohd Hashim, Ummi Kalsom and Mohd, Othman and Abdullah, Mohd Mawardy and Sakidin, Hamzah and Rasib, Abd Wahid and Sufahani, Suliadi Firdaus (2018) Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data. International Journal of Advanced Computer Science and Applications, 9 (9). pp. 529-537. ISSN 2156-5570 |
| spellingShingle | QA75 Electronic computers. Computer science TP200-248 Chemicals: Manufacture, use, etc. Ahmad, Asmala Mohd Hashim, Ummi Kalsom Mohd, Othman Abdullah, Mohd Mawardy Sakidin, Hamzah Rasib, Abd Wahid Sufahani, Suliadi Firdaus Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data |
| title | Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data |
| title_full | Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data |
| title_fullStr | Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data |
| title_full_unstemmed | Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data |
| title_short | Comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data |
| title_sort | comparative analysis of support vector machine, maximum likelihood and neural network classification on multispectral remote sensing data |
| topic | QA75 Electronic computers. Computer science TP200-248 Chemicals: Manufacture, use, etc. |
| url | http://eprints.uthm.edu.my/3552/ http://eprints.uthm.edu.my/3552/1/AJ%202018%20%28700%29%20Comparative%20analysis%20of%20support%20vector%20machine%2C%20maximum%20likelihood%20and%20neural%20network%20classification%20on%20multispectral%20remote%20sensing%20data.pdf |