A Review of Traffic Congestion Prediction Using Artificial Intelligence

Table 1

Traffic congestion prediction studies in probabilistic reasoning.

Methodology	Road type	Data source	Input parameters	Target domain	No. of congestion state levels	Reference
Hierarchical fuzzy rule-based system	Highway corridor	Sensor	Occupancy	Speed	2	Zhang et al. [30]
			Speed	Speed	4	Lopez-garcia et al. [37]
Evolutionary fuzzy rule learning			Traffic flow	Traffic density		Onieva et al. [28]
Mamdani-type fuzzy logic inference	Highway, trunk road, branch road	—	Speed	Congestion Index		Cao and Wang [3]
			Density			Wang et al. [58]
Fuzzy inference	Highway corridor	Camera	Travel time
			Traffic flow
			Speed
Fuzzy comprehensive evaluation	Highway corridor	Probe	Traffic volume	Saturation	5	Kong et al. [4]
			Speed	Density speed		Yang et al. [5]
Hidden Markov model	Highway network	Sensor	Emission matrix	Traffic pattern selection	—	Zaki et al. [32]
			Emission matrix	Traffic pattern determination	—	Zaki et al. [25]
			Transition matrix
	Main road	Probe	Observation probability	Mapping GPS data	—	Sun et al. [45]
			Transition probability
Gaussian distribution	Highway corridor	Sensor	Traffic volume	Optimal feature selection	—	Yang [29]
Bayesian network	Build-up area	Simulation	Road and bus increment	Congestion probability	—	Yi Liu et al. [59]
	Bridge	Sensor	Intensity			Asencio-Cortés et al. [54]
			Occupation
			Average speed
			Average distance
	Highway network	Sensor	Network direction	Congestion probability		Kim and Wang [34]
			Day and time weather
			Incidents
			Traffic flow
			Occupancy
			Speed
			Level of service
			Congestion state
Extended Kalman filter	Highway	Camera	Travel time	Data fusion	—	Adetiloye and Awasthi [7]

The table accumulates the data source, scope of the study area, input and resulting parameters, and how many cognitive traffic states were considered in the studies.2 = free/congested, 4 = free/light/medium/severe, 5 = very free/free/light/medium/severe