A Prediction Method of Electromagnetic Environment Effects for UAV LiDAR Detection System

Table 3

Parameter optimization table.

Model	Parameter
ADB	AdaBoostClassifier (n_estimators = 100, learning_rate = 0.8, algorithm = SAMME.R)
SVC	SVC (kernel = rbf, gamma = 0.2, decision_function_shape = ovo, C = 1)
RF	RandomForestClassifier (criterion = “gini,” max_depth = 12, max_leaf_nodes = 20)
DT	DecisionTreeClassifier (min_samples_split = 10, max_depth = 20, splitter = random)
XGB	XGBClassifier (eta = 0.1, objective = multi:softmax, num_class = 4)
GDBT	GradientBoostingClassifier (n_estimators = 90, learning_rate = 0.3, loss = deviance)
KNN	KNeighborsClassifier (n_neighbors = 85, Algorithm = auto)