Premium
A computational intelligence‐based approach for short‐term traffic flow prediction
Author(s) -
Zargari Shahriar Afandizadeh,
Siabil Salar Zabihi,
Alavi Amir Hossein,
Gandomi Amir Hossein
Publication year - 2012
Publication title -
expert systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.365
H-Index - 38
eISSN - 1468-0394
pISSN - 0266-4720
DOI - 10.1111/j.1468-0394.2010.00567.x
Subject(s) - computer science , traffic flow (computer networking) , term (time) , multilayer perceptron , fuzzy logic , computational intelligence , genetic programming , artificial intelligence , simple (philosophy) , data mining , perceptron , machine learning , artificial neural network , philosophy , physics , computer security , epistemology , quantum mechanics
This paper proposes alternative approaches for the prediction of short‐term traffic flow using three branches of computational intelligence techniques, namely linear genetic programming (LGP), multilayer perceptron (MLP) and fuzzy logic (FL). Different LGP, MLP and FL models are developed for estimating the 5‐ and 30‐min traffic flow rates. New LGP‐ and MLP‐based prediction equations are derived for the traffic flow rates in the 5‐ and 30‐min time intervals. The models are established upon extensive databases of the traffic flow records obtained from Iran's Rasht‐Qazvin highway. The results indicate that the proposed models are effectively capable of predicting the target values. The LGP‐based models are found to be simple, straightforward and more practical for predictive purposes compared with the other derived models.