Infinite Latent Feature Selection Technique for Hyperspectral Image Classification
The classification process is one of the most crucial processes in hyperspectral imaging. One of the limitations in classification process using machine learning technique is its complexities, where hyperspectral image format has a thousand band that can be used as a feature for learning purpose. Th...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Indonesian Institute of Sciences
2019-08-01
|
| Series: | Jurnal Elektronika dan Telekomunikasi |
| Subjects: | |
| Online Access: | https://www.jurnalet.com/jet/article/view/260 |
| _version_ | 1819210908090499072 |
|---|---|
| author | Tajul Miftahushudur Chaeriah Bin Ali Wael Teguh Praludi |
| author_facet | Tajul Miftahushudur Chaeriah Bin Ali Wael Teguh Praludi |
| author_sort | Tajul Miftahushudur |
| collection | DOAJ |
| description | The classification process is one of the most crucial processes in hyperspectral imaging. One of the limitations in classification process using machine learning technique is its complexities, where hyperspectral image format has a thousand band that can be used as a feature for learning purpose. This paper presents a comparison between two feature selection technique based on probability approach that not only can tackle the problem, but also improve accuracy. Infinite Latent Feature Selection (ILFS) and Relief Techniques are implemented in a hyperspectral image to select the most important feature or band before applied in Support Vector Machine (SVM). The result showed ILFS technique can improve classification accuracy better than Relief (92.21% vs. 88.10%). However, Relief can extract less feature to reach its best accuracy with only 6 features compared with ILFS with 9. |
| first_indexed | 2024-12-23T06:18:39Z |
| format | Article |
| id | doaj.art-e55f8d33e2ed4943811e38a8acc8f19a |
| institution | Directory Open Access Journal |
| issn | 1411-8289 2527-9955 |
| language | English |
| last_indexed | 2024-12-23T06:18:39Z |
| publishDate | 2019-08-01 |
| publisher | Indonesian Institute of Sciences |
| record_format | Article |
| series | Jurnal Elektronika dan Telekomunikasi |
| spelling | doaj.art-e55f8d33e2ed4943811e38a8acc8f19a2022-12-21T17:57:15ZengIndonesian Institute of SciencesJurnal Elektronika dan Telekomunikasi1411-82892527-99552019-08-01191323710.14203/jet.v19.32-37157Infinite Latent Feature Selection Technique for Hyperspectral Image ClassificationTajul Miftahushudur0Chaeriah Bin Ali Wael1Teguh Praludi2Indonesian Institute of Sciences, IndonesiaIndonesian Institute of SciencesIndonesian Institute of SciencesThe classification process is one of the most crucial processes in hyperspectral imaging. One of the limitations in classification process using machine learning technique is its complexities, where hyperspectral image format has a thousand band that can be used as a feature for learning purpose. This paper presents a comparison between two feature selection technique based on probability approach that not only can tackle the problem, but also improve accuracy. Infinite Latent Feature Selection (ILFS) and Relief Techniques are implemented in a hyperspectral image to select the most important feature or band before applied in Support Vector Machine (SVM). The result showed ILFS technique can improve classification accuracy better than Relief (92.21% vs. 88.10%). However, Relief can extract less feature to reach its best accuracy with only 6 features compared with ILFS with 9.https://www.jurnalet.com/jet/article/view/260classificationfeature selectionhyperspectralInfinite Latent Feature SelectionSVM |
| spellingShingle | Tajul Miftahushudur Chaeriah Bin Ali Wael Teguh Praludi Infinite Latent Feature Selection Technique for Hyperspectral Image Classification Jurnal Elektronika dan Telekomunikasi classification feature selection hyperspectral Infinite Latent Feature Selection SVM |
| title | Infinite Latent Feature Selection Technique for Hyperspectral Image Classification |
| title_full | Infinite Latent Feature Selection Technique for Hyperspectral Image Classification |
| title_fullStr | Infinite Latent Feature Selection Technique for Hyperspectral Image Classification |
| title_full_unstemmed | Infinite Latent Feature Selection Technique for Hyperspectral Image Classification |
| title_short | Infinite Latent Feature Selection Technique for Hyperspectral Image Classification |
| title_sort | infinite latent feature selection technique for hyperspectral image classification |
| topic | classification feature selection hyperspectral Infinite Latent Feature Selection SVM |
| url | https://www.jurnalet.com/jet/article/view/260 |
| work_keys_str_mv | AT tajulmiftahushudur infinitelatentfeatureselectiontechniqueforhyperspectralimageclassification AT chaeriahbinaliwael infinitelatentfeatureselectiontechniqueforhyperspectralimageclassification AT teguhpraludi infinitelatentfeatureselectiontechniqueforhyperspectralimageclassification |