Multimodal Classification Technique for Fall Detection of Alzheimer’s Patients by Integration of a Novel Piezoelectric Crystal Accelerometer and Aluminum Gyroscope with Vision Data

Table 2

Parameter setting for ML models.

ML model	Parameters
Logistic regression	Penalty = l2
	Intercept_scal = 1
	Max_iteration = 100
Decision tree	Criterion = Gini
	Min_samples_split = 2
	Min_samples_leaf = 1
K-nearest neighbors	Neigh = 3
	Leaf_size = 30
	Metric = Minkowski
SVM	C = 1.0 kernel = rbf
	Deg-3
	Gamma = auto
	Tolerance = 0.001
Random forest	Estimators = 50
	Min_samples_split = 2
	Min_samples_leaf = 1
	Bootstrap = true