Derivation of level of service by artificial neural networks at horizontal curves: a case study in Egypt

Abstract

Purpose Multi-lane highways represent the majority of the total length of highway network at many countries. The geometric design of such facilities and the traffic volume which includes heavy vehicles percentage (HV) are considered the most important factors affecting the level of service (LOS), especially on the horizontal curves. Methods This paper aims to explore the relationship between the road geometric characteristics including horizontal curve properties and traffic volume including average annual daily traffic (AADT) and HV in one hand and LOS in the other hand by two methods. First is generalized linear modeling (GLM) procedure and second is the artificial neural networks (ANNs) procedure. In this research, the traffic and road geometric data are collected on 78 horizontal curves that are distributed on four multi-lane highways in Egypt. Two of them are located in desert area and the others in agricultural area.

Utjecaj stanja višetračnih kolnika na promet osobnih vozila

“…Finally, many models are excluded due to poor significance with V 85 C or multicollinearity with predictor variables. VIF values for IRI and PCI are the same as 1.562 that are safe against multicollinearity (do not exceed 2.5), Allison [16]. The investigation of the 2-Lanes and 3-Lanes models shows that the negative coefficient sign for the IRI means that V 85 C decreases with an increase of the IRI.…”

“…The experience in this field is analysed according to Semeida [16] who established in his studies that the multi-layer perceptron (MLP) neural network models give the best performance compared to other models. In addition, this network is usually preferred in engineering applications because many learning algorithms could be used in the MLP.…”

Impact of Horizontal Curves and Percentage of Heavy Vehicles on Right Lane Capacity at Multi-lane Highways

“…Semeida [15] explored the impact of roadway and traffic characteristics on the level of service (LOS) at 78 curved sections that are located on the major Egyptian highways, where the most effective factors on the LOS are found to be: the average annual daily traffic (AADT), HV, and R.…”

“…Plentiful attempts are made to attain the best percentage among the training and testing sections that grant the superior model efficiency [15]. The statistical parameters of the superior attempt for training, testing, and both of the groups are produced in Table 4.…”

Bus service quality prediction and attribute ranking: a neural network approach

“…As mentioned earlier, ANNs are of several types such as RBF network, FBNN, RNN, Self-organizing Map etc. Among them FBNN and a variant of RBF network are used to carry out the research, since the level of service (LOS) of buses is related to determine classifications of SQ (Garrido et al 2014;Semeida 2015).…”