MODELLING SATURATION FLOW AT SIGNALIZED INTERSECTIONS IN MIXED TRAFFIC CONDITIONS: ARTIFICIAL NEURAL NETWORK APPROACH
Keywords:
Mixed traffic, traffic composition, Artificial Neural Network, Indian highway, capacity manualAbstract
Saturation flow rate is very important parameter which was used extensively in the design and control of signalized intersections. In the present study saturation flow is estimated with cycle time, approach width, proportion of two wheelers, proportion of three wheelers and proportion of cars using regression analysis and Artificial Neural Networks. A comparison of MLR and ANN prediction of field saturation flow is made, and the study results showed that ANN are highly accurate because of their self-computing and intelligent behaviour. Mean absolute percentage error (MAPE) value is less and Index of Agreement (IA) value is high for best fitted ANN model when compared to those for MLR and INDO HCM models. The developed ANN satisfactorily predicted the saturation flow at signalized intersections in mixed traffic conditions with MAPE of 1.76% and with IA of 0.999.
References
Abyaneh, H.Z. (2014). Evaluation of Multivariate linear regression and artificial neural networks in prediction of water quality parameters. J. Environ. Health Sci. Eng., 12(40):1-8.
Arasan, V.T. and Vedagiri, P. (2006). Estimation of saturation flow of heterogeneous traffic using computer simulation. Proceedings 20th European Conference on Modelling and simulation Wolfgang Borutzky, Alessandra Orsoni, Richard Zobel ECMS.
Anusha, C.S., Verma, A., and Kavitha, G. (2013). Effects of two wheelers on saturation flow at signalized intersections in developing countries. J. Transport. Eng., ASCE.,139: 448-457.
Budi, H.S. and Solihin, Y. (2011). Modification of Saturation flow formula by width of approach. In: 6th international symposium on Highway Capacity on quality of service, stockholm, Sweden June 28th to July 1st 2011, p. 620-629.
Chand, S., Gupta, N.J., and Velmurugan, S. (2016). Development of saturation flow model at signalized intersection for heterogeneous traffic. In: World Conference On Transport Research-WCTR 2016, Shanghai 10-15 July 2016, p. 1,662-1,671.
Dogan, E., Akgungor, A., and Arslan, T. (2016). Estimation of delay and vehicle stops at signalized intersections using Artificial Neural Networks. Eng. Review, 36(2):157-165.
Gowri, A., Mourie, H.S., and Sivanandan, R. (2016). Passenger car unit estimation at signalized intersection for non-lane based mixed traffic using microscopic simulation model. Period. Polytech. Transport. Eng., 45(I):12-20.
Hossain, M. (2001). Estimation of saturation flow at signalized intersections of developing cities: a micro-simulation modelling approach. Transport. Res. Part A., 35:123-141.
Indian Highway Capacity Manual (INDO HCM). (2017). Council of Scientific and Industrail Research (CSIR). New Delhi.
Murat, S.Y. and Baskan, O. (2006). Modelling vehicle delays at signalized junctions: Artificial neural networks approach. J. Sci. Indust. Res., 65:558-564.
Nguyen, H.D. (2016). Saturation flow rate analysis at signalized intersections for mixed traffic conditions in motor cycle dependent cities. Transport. Res. Procedia., 15:694-708.
Naik, B.A.K. and Vinod, A.V. (2018). ANN modeling of the viscosity and effective thermal conductivity of non-newtonian nanofluids. Journal of Testing and Evaluation 47(2):791-808
Potts, I.B., Ringert, J.F., Bauer, K.M., and Zegeer, J.D. (2007). Relationship of lane width to saturation flow rate on urban and suburban signalized intersection approaches. J. Transport. Res. Board., 2027:45-51.
Preethi, P., Varghese, A., and Ashalatha, R. (2016). Modelling delay at signalized intersections under heterogeneous traffic condition. 11th Transportation Planning And Implementation Methodologies For Developing Countries.
Preethi, P. and Ashalatha, R. ( 2018). Modeling saturation flow rate and right turn adjustment factor using area occupancy concept. Case Studies on Transport Policy., 6:63-71.
Shrestha, S. and Anil, M. (2014). Development of saturation flow and delay model at signalized intersection of Kathmandu. In: Proceedings of IOE Graduate conference, 2014.
Saha, A., Chandra, S., and Ghosh, I. (2017). Saturation flow estimation at signalized intersections under mixed traffic conditions. WIT Transactions on the built environment.,176:1,743-3,509.
Saha, A., Chakraborty, S., Chandra, S., and Ghosh, I. (2018). Kringing based saturation flow models for traffic conditions in Indian cities. Transport. Res. Oart A: Policy and Practice., 118:38-51.
Turner, J. and Harahap, G. (1993). Simplified saturation flow data collection Methods. Transport Research Laboratory, conference on the development and planning of urban Transport.
Yugendar, P. and Ravishankar, K.V.R. (2018). Analysis of crowd flow parameters using Artificial Neural Networks. Transport Telecom., 19(4):335-345.
Zhao, L. and Thorpe, C.E. (2000). Stereo-and neural network-based pedestrian Detection. IEEE Trans Intell. Transport. Sys.,1(3):148-154.
