An Algorithm for Detecting Collision Risk between Trucks and Pedestrians in the Connected Environment

Table 4

Results (data acquisition cycle = 2 Hz).

Classification		Actual class
		Dangerous	Normal
Prediction	Dangerous	6,249	2,588
	Normal	561	15,748

True-positive rate (TPR) = 0.918; false-positive rate (FPR) = 0.859; accuracy = 0.875.