A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data
Table 3
List of experiments conducted in the research.
Experiments
1
-Nearest Neighbors (neighbors = 5)
2
-Nearest Neighbors (neighbors = 10)
3
Naive Bayes (algorithm = Gaussian)
4
Random Forests (trees = 10)
5
Random Forests (trees = 50)
6
Random Forests (trees = 100)
7
Support Vector Machines (kernel = linear)
8
Multilayer Perceptron (hidden units = 100; hidden layers = 1)
9
Multilayer Perceptron (hidden units = 100; hidden layers = 3)
10
Multilayer Perceptron (hidden units = 150; hidden layers = 5)
