The Use of a Machine Learning Method to Predict the Real-Time Link Travel Time of Open-Pit Trucks

Table 4

Description of the variables used in the prediction.

Variables	Type	Role	Description
Truck Id	Numeric	Feature	The serial number of truck.
Truck type	Categorical	Feature	The type of the truck (i.e., BELAZ-L, BELAZ-M, and MT86).
Truck status	Categorical	Feature	The status of the truck (i.e., running, waiting, and stop).
-axis start	Numeric	Feature	The coordinate of the truck at the starting position.
-axis start	Numeric	Feature	The coordinate of the truck at the starting position.
-axis arrival	Numeric	Feature	The coordinate of the truck at the ending position.
-axis arrival	Numeric	Feature	The coordinate of the truck at the ending position.
Load status	Categorical	Feature	The load status of the truck (i.e., empty and coal).
Start node	Categorical	Feature	The node code of the starting position of the road.
Arrival node	Categorical	Feature	The node code of the ending position of the road.
Pressure	Numeric	Feature	A fundamental atmospheric quantity.
Wind speed	Numeric	Feature	A fundamental atmospheric quantity.
Temperature	Numeric	Feature	A fundamental atmospheric quantity.
Relative humidity	Numeric	Feature	A fundamental atmospheric quantity.
Precipitation	Numeric	Feature	A fundamental atmospheric quantity.
Rain	Categorical	Feature	A fundamental atmospheric quantity (i.e., yes and no).
Travel time	Date time	Target	The travel time of the truck on each link.