Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification
Remote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric clas...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4431 |
| _version_ | 1827688549538856960 |
|---|---|
| author | Abdul Razaque Mohamed Ben Haj Frej Muder Almi’ani Munif Alotaibi Bandar Alotaibi |
| author_facet | Abdul Razaque Mohamed Ben Haj Frej Muder Almi’ani Munif Alotaibi Bandar Alotaibi |
| author_sort | Abdul Razaque |
| collection | DOAJ |
| description | Remote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric classifiers based on traditional statistics have successfully been used in remote sensing classification, but the accuracy is greatly impacted and rather constrained by the statistical distribution of the sensing data. To eliminate those constraints, new variants of support vector machine (SVM) are introduced. In this paper, we propose and implement land use classification based on improved SVM-enabled radial basis function (RBF) and SVM-Linear for image sensing. The proposed variants are applied for the cross-validation to determine how the optimization of parameters can affect the accuracy. The accuracy assessment includes both training and test sets, addressing the problems of overfitting and underfitting. Furthermore, it is not trivial to determine the generalization problem merely based on a training dataset. Thus, the improved SVM-RBF and SVM-Linear also demonstrate the outstanding generalization performance. The proposed SVM-RBF and SVM-Linear variants have been compared with the traditional algorithms (Maximum Likelihood Classifier (MLC) and Minimum Distance Classifier (MDC)), which are highly compatible with remote sensing images. Furthermore, the MLC and MDC are mathematically modeled and characterized with new features. Also, we compared the proposed improved SVM-RBF and SVM-Linear with the current state-of-the-art algorithms. Based on the results, it is confirmed that proposed variants have higher overall accuracy, reliability, and fault-tolerance than traditional as well as latest state-of-the-art algorithms. |
| first_indexed | 2024-03-10T09:59:17Z |
| format | Article |
| id | doaj.art-01cf148cece8478cbed8b1343650efb1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T09:59:17Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-01cf148cece8478cbed8b1343650efb12023-11-22T02:04:14ZengMDPI AGSensors1424-82202021-06-012113443110.3390/s21134431Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image ClassificationAbdul Razaque0Mohamed Ben Haj Frej1Muder Almi’ani2Munif Alotaibi3Bandar Alotaibi4Department of Computer Engineering and Information Security, International Information Technology University, Almaty 050040, KazakhstanDepartment of Computer Science and Engineering, University of Bridgeport, Bridgeport, CT 06604, USAGulf University for Science and Technology, Hawally 32093, KuwaitDepartment of Computer Science, Shaqra University, Shaqra 15526, Saudi ArabiaDepartment of Information Technology, University of Tabuk, Tabuk 47731, Saudi ArabiaRemote sensing technologies have been widely used in the contexts of land cover and land use. The image classification algorithms used in remote sensing are of paramount importance since the reliability of the result from remote sensing depends heavily on the classification accuracy. Parametric classifiers based on traditional statistics have successfully been used in remote sensing classification, but the accuracy is greatly impacted and rather constrained by the statistical distribution of the sensing data. To eliminate those constraints, new variants of support vector machine (SVM) are introduced. In this paper, we propose and implement land use classification based on improved SVM-enabled radial basis function (RBF) and SVM-Linear for image sensing. The proposed variants are applied for the cross-validation to determine how the optimization of parameters can affect the accuracy. The accuracy assessment includes both training and test sets, addressing the problems of overfitting and underfitting. Furthermore, it is not trivial to determine the generalization problem merely based on a training dataset. Thus, the improved SVM-RBF and SVM-Linear also demonstrate the outstanding generalization performance. The proposed SVM-RBF and SVM-Linear variants have been compared with the traditional algorithms (Maximum Likelihood Classifier (MLC) and Minimum Distance Classifier (MDC)), which are highly compatible with remote sensing images. Furthermore, the MLC and MDC are mathematically modeled and characterized with new features. Also, we compared the proposed improved SVM-RBF and SVM-Linear with the current state-of-the-art algorithms. Based on the results, it is confirmed that proposed variants have higher overall accuracy, reliability, and fault-tolerance than traditional as well as latest state-of-the-art algorithms.https://www.mdpi.com/1424-8220/21/13/4431remote sensingsupport vector machineimproved SVM-RBF variantimproved SVM-Linear variantimage classification |
| spellingShingle | Abdul Razaque Mohamed Ben Haj Frej Muder Almi’ani Munif Alotaibi Bandar Alotaibi Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification Sensors remote sensing support vector machine improved SVM-RBF variant improved SVM-Linear variant image classification |
| title | Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification |
| title_full | Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification |
| title_fullStr | Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification |
| title_full_unstemmed | Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification |
| title_short | Improved Support Vector Machine Enabled Radial Basis Function and Linear Variants for Remote Sensing Image Classification |
| title_sort | improved support vector machine enabled radial basis function and linear variants for remote sensing image classification |
| topic | remote sensing support vector machine improved SVM-RBF variant improved SVM-Linear variant image classification |
| url | https://www.mdpi.com/1424-8220/21/13/4431 |
| work_keys_str_mv | AT abdulrazaque improvedsupportvectormachineenabledradialbasisfunctionandlinearvariantsforremotesensingimageclassification AT mohamedbenhajfrej improvedsupportvectormachineenabledradialbasisfunctionandlinearvariantsforremotesensingimageclassification AT muderalmiani improvedsupportvectormachineenabledradialbasisfunctionandlinearvariantsforremotesensingimageclassification AT munifalotaibi improvedsupportvectormachineenabledradialbasisfunctionandlinearvariantsforremotesensingimageclassification AT bandaralotaibi improvedsupportvectormachineenabledradialbasisfunctionandlinearvariantsforremotesensingimageclassification |