Dimension reduction aided hyperspectral image classification with a small-sized training dataset: Experimental comparisons

Keyphrases

• Dimensionality Reduction 100%
• Training Data 100%
• Support Vector Machine 100%
• Hyperspectral Image Classification 100%
• Small-sized 100%
• Principal Coordinate Analysis (PCoA) 66%
• Hyperspectral 66%
• Limited Training Data 66%
• Feature Extraction 33%
• Machine Learning 33%
• Specific Task 33%
• Computation Time 33%
• Computational Complexity 33%
• Computing Time 33%
• Time Complexity 33%
• Classification Results 33%
• Classification Methods 33%
• Image Data 33%
• Time Application 33%
• Prediction Model 33%
• Training Samples 33%
• Spectral Bands 33%
• Number of Features 33%
• Model Mapping 33%
• Kernel Principal Component Analysis 33%
• Feature Selection 33%
• Labeled Data 33%
• Sensing Technology 33%
• Mutual Information 33%
• Methodological Support 33%
• Feature Band 33%
• Redundant Data 33%
• Learning Communities 33%
• Irrelevant Information 33%
• Minimum Redundancy Maximum Relevance (mRMR) 33%

Computer Science

• Image Classification 100%
• Training Dataset 100%
• Hyperspectral Image 100%
• Support Vector Machine 75%
• Principal Components 75%
• Component Analysis 75%
• Feature Extraction 50%
• Prediction Model 25%
• Redundant Data 25%
• Large Data Set 25%
• Real-Time Application 25%
• Time Complexity 25%
• Feature Selection 25%
• Reduction Algorithm 25%
• Learning Community 25%
• Computational Complexity 25%
• classification result 25%
• Training Data 25%
• Training Sample 25%
• Mutual Information 25%
• Computation Time 25%
• Classification Method 25%
• Machine Learning 25%
• Learning System 25%