Name
Title | ||
|---|---|---|
Sensitivity of Support Vector Machines to Random Feature Selection in Classification of Hyperspectral Data |
Abstract | ||
|---|---|---|
The accuracy of supervised land cover classifications depends on factors such as the chosen classification algorithm, adequate training data, the input data characteristics, and the selection of features. Hyperspectral imaging provides more detailed spectral and spatial information on the land cover than other remote sensing resources. Over the past ten years, traditional and formerly widely accepted statistical classification methods have been superseded by more recent machine learning algorithms, e.g., support vector machines (SVMs), or by multiple classifier systems (MCS). This can be explained by limitations of statistical approaches with regard to high-dimensional data, multimodal classes, and often limited availability of training data. In the presented study, MCSs based on SVM and random feature selection (RFS) are applied to explore the potential of a synergetic use of the two concepts. We investigated how the number of selected features and the size of the MCS influence classification accuracy using two hyperspectral data sets, from different environmental settings. In addition, experiments were conducted with a varying number of training samples. Accuracies are compared with regular SVM and random forests. Experimental results clearly demonstrate that the generation of an SVM-based classifier system with RFS significantly improves overall classification accuracy as well as producer's and user's accuracies. In addition, the ensemble strategy results in smoother, i.e., more realistic, classification maps than those from stand-alone SVM. Findings from the experiments were successfully transferred onto an additional hyperspectral data set. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/TGRS.2010.2041784 | Geoscience and Remote Sensing, IEEE Transactions |
Keywords | Field | DocType |
feature extraction,geophysical image processing,image classification,learning (artificial intelligence),remote sensing,spectral analysis,support vector machines,terrain mapping,high-dimensional data,hyperspectral data classification,hyperspectral imaging,input data characteristics,machine learning algorithm,multimodal class,random feature selection,random forest,remote sensing,spatial information,spectral information,supervised land cover classification,support vector machine,Classifier ensembles,hyperspectral data,multiple classifier systems (MCSs),random feature selection (RFS),support vector machines (SVMs) | Data set,Pattern recognition,Feature selection,Computer science,Support vector machine,Hyperspectral imaging,Feature extraction,Artificial intelligence,Contextual image classification,Random forest,Statistical classification,Machine learning | Journal |
Volume | Issue | ISSN |
48 | 7 | 0196-2892 |
Citations | PageRank | References |
15 | 0.69 | 28 |
Authors | ||
6 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Björn Waske | 1 | 435 | 24.75 |
| Sebastian van der Linden | 2 | 84 | 10.59 |
| JÓn Atli Benediktsson | 3 | 635 | 28.85 |
| Andreas Rabe | 4 | 56 | 5.09 |
| Patrick Hostert | 5 | 241 | 24.33 |
| van der Linden, S. | 6 | 15 | 0.69 |