Comparison of general kernel, multiple kernel, infinite ensemble and semi-supervised support vector machines for landslide susceptibility prediction
Comparison of general kernel, multiple kernel, infinite ensemble and semi-supervised support vector machines for landslide susceptibility prediction
Zhice Fang,Yi Wang,2 Autori,Ling Peng
2022 · DOI: 10.1007/s00477-022-02208-z
25 citazioni
TLDR
The experimental results show that the Laplacian-SVM has the highest prediction performance (AUC = 0.8815) among SVM-based methods, indicating that RBF kernel is more suitable for solving susceptibility prediction problems.