An Informative and Comprehensive Behavioral Characteristics Analysis Methodology of Android Application for Data Security in Brain-Machine Interfacing

Table 4

Performance of static behavioral characteristic combination.

Behavioral characteristic set	Algorithm	TP	FP	Precision	Recall	F-Measure	ROC area
Platform-defined	SVM	0.887	0.123	0.892	0.887	0.886	0.88
	KNN	0.94	0.06	0.94	0.94	0.94	0.975
	Random forest	0.942	0.058	0.942	0.942	0.942	0.981
App-specific	SVM	0.898	0.102	0.899	0.898	0.898	0.895
	KNN	0.961	0.039	0.961	0.961	0.961	0.981
	Random forest	0.961	0.039	0.961	0.961	0.961	0.99
All	SVM	0.905	0.095	0.909	0.905	0.904	0.899
	KNN	0.962	0.038	0.962	0.962	0.962	0.981
	Random forest	0.971	0.029	0.971	0.97	0.971	0.992