Model selection and timing of acquisition date impacts classification accuracy: A case study using hyperspectral imaging to detect white pine blister rust over time

Keyphrases

• Model Selection 100%
• Prediction Accuracy 100%
• Classification Accuracy 100%
• White pine Blister Rust 100%
• Hyperspectral Imaging 100%
• Impact Classification 100%
• Dynamic Data 60%
• Training Data 40%
• Spearman 40%
• Data Training 40%
• Testing Data 40%
• Data Testing 40%
• Real-world Application 20%
• Number of Individuals 20%
• Plant Stress 20%
• Hereafter 20%
• Machine Learning 20%
• Pinus Strobiformis 20%
• Southwestern White pine 20%
• Spearman Rank Correlation 20%
• Support Vector Machine 20%
• Machine Learning Models 20%
• 10-fold Cross Validation 20%
• Rust Disease 20%
• Heterogeneous Ensemble 20%
• Linear Kernel 20%
• Classification Model 20%
• Training Dates 20%
• Dynamic Timing Model 20%
• System Training 20%
• Static Data 20%
• Model Accuracy 20%
• Time Dynamics 20%
• Area under the Receiver Operating Characteristic Curve 20%

Agricultural and Biological Sciences

• Case Study 100%
• Blister Rust 100%
• Pinus 50%
• Pinus strobus 50%
• Plant Stress 50%
• Support Vector Machine 50%
• Rust Diseases 50%

Earth and Planetary Sciences

• Machine Learning 100%
• Hyperspectral Imaging 100%
• Correlation Coefficient 50%
• Support Vector Machine 50%
• Plant Stress 50%