Support Vector Machine

Summary

This tool is an implementation of the LIBSVM (Chang et al.,2011) for support vector regression (SVR). LiDAR360 supports forest metrics estimation using two SVR types (epsilon-SVR and nu-SVR) and four kernel types (linear, polynomial, radial basis function and sigmoidal).

Support Vector Regression

Usage

Navigate to ALS Forest > Regression Analysis > Support Vector Machine.

Support Vector Regression

Settings

  • Import Training Data: Refer to Sample Data and Independent Variables.
  • Independent Variables: Refer to Sample Data and Independent Variables.
  • Kernel Type: Users can select the type of kernel function here including RBF function, Linear, Polynomial, and Sigmoid.
    • RBF Function (default): , where γ > 0.
    • Linear: .
    • Polynomial: , where γ > 0.
    • Sigmoid: .
  • SVM Type: Two types of SVM method are provided.
    • EPSILON_SVR (default): EPSILON SVR(ϵSVR ).
    • NU_SVR: NU SVR(νSVR).
  • Degree (default value is "3"): Kernel function parameter.
  • Gamma (default value is "0.1"): Kernel function parameter.
  • Accuracy Assessment: Based on the K-Fold cross validation model, a sample would be partitioned into k subsets according to input K-Fold value (no less than 2). Take one of subsets as a validation dataset and the remaining subsets as training datasets to form a model, then run this model and test the fitting of validation set to training sets. Repeat this process until every subset is treated as a validation set at least once and select out the model with the least MSE (mean square error) as the optimal model.
  • Save Regression Model: Tick the checkbox to save the SVM model (Support Vector Machine.model) under the output path.
  • Save Regression Dataset: Tick the checkbox to save the training dataset (Support Vector Machine.csv) in .csv format under the output path.
  • Output Path: Choose an output directory. A support vector machine regression model report (Support Vector Machine.html), recording the model's parameters and accuracy (R-square, RMSE), would be generated under this directory. A prediction result file (Support Vector Machine.tif), based on the support vector machine regression model and input variables from a .tif or .csv file, would also be generated under this output directory.
Support Vector Regression

Note: The dimension of imported sample/training data must be within the scope of independent variables, which may be adjusted accordingly. The model/result is based on the passed-in variables.

    @inproceedings{
        author={Chang C C and Lin C J},
        title={LIBSVM: A Library for Support Vector Machines},
        booktitle={ACM,2(3):1-27},
        year={2011}
    }

results matching ""

    No results matching ""