Ogunwolu, L., Adedokun, O., Orimoloye, O., Oke, S. (2011). A neuro-fuzzy approach to vehicular traffic flow prediction for a metropolis in a developing country. Journal of Industrial Engineering, International, 7(13), 52-66.
L Ogunwolu; O Adedokun; O Orimoloye; S.A Oke. "A neuro-fuzzy approach to vehicular traffic flow prediction for a metropolis in a developing country". Journal of Industrial Engineering, International, 7, 13, 2011, 52-66.
Ogunwolu, L., Adedokun, O., Orimoloye, O., Oke, S. (2011). 'A neuro-fuzzy approach to vehicular traffic flow prediction for a metropolis in a developing country', Journal of Industrial Engineering, International, 7(13), pp. 52-66.
Ogunwolu, L., Adedokun, O., Orimoloye, O., Oke, S. A neuro-fuzzy approach to vehicular traffic flow prediction for a metropolis in a developing country. Journal of Industrial Engineering, International, 2011; 7(13): 52-66.
A neuro-fuzzy approach to vehicular traffic flow prediction for a metropolis in a developing country
1Senior Lecturer, Dep. of Systems Engineering, University of Lagos, Lagos, Nigeria
2Former Student, Dep. of Mechanical Engineering, University of Lagos, Lagos, Nigeria
3Lecturer, Dep. of Mechanical Engineering, University of Lagos, Lagos, Nigeria
Abstract
Short-term prediction of traffic flow is central to alleviating congestion and controlling the negative impacts of environmental pollution resulting from vehicle emissions on both inter- and intra-urban highways. The strong need to monitor and control congestion time and costs for metropolis in developing countries has therefore motivated the current study. This paper establishes the application of neuro-fuzzy to predict traffic volume of vehicles on a busy traffic corridor. Using a case drawn from metropolitan Lagos, Nigeria, a traffic prediction system is designed such that the predicted values (output) can be accessed by the public through mobile phones. The best route to a particular route will also be advised by the system. In addition, the expected fuel consumption and travel time will be included in the output. Input data is pre-processed based on acquired real time traffic data, the network is trained and the fuzzifier module categorized the numerical output of the model. The advisory module of the traffic prediction model then computes the expected travel time and the fuel consumption cost. The results obtained established the non-linear nature of traffic flow along the routes and indicates that predicting the traffic situation is non-algorithmic. The travel time along the routes is averaged at 23.5 minutes, while the fuel cost is estimated at an average of $2.03. Thus, proper control of traffic time and cost could be obtained if monitoring is aided with neuro-fuzzy as a tool.
Top