Driver’s Face Pose Estimation Using Fine-Grained Wi-Fi Signals for Next-Generation Internet of Vehicles

Table 4

Overall generalization performance.

Experiment	Average accuracy (%)
	SVM		KNN		KSVM
	Original	LOPO-CV	Original	LOPO-CV	Original	LOPO-CV
Scenario-I	86.8	83.7	87.2	80.2	91.1	86.4
Scenario-II	87.1	84.9	87.9	81.7	91.8	88.2