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

Table 5

Results (data acquisition cycle = 10 Hz).

Classification		Actual class
		Dangerous	Normal
Prediction	Dangerous	35,967	14,661
	Normal	724	85,901

True-positive rate (TPR) = 0.980; false-positive rate (FPR) = 0.854; accuracy = 0.888.