Issa et al. [14] developed ANN model for predicting V85 fortwo-lane rural highways in Oklahoma. Data from 121 sites,distributed throughout Oklahoma, were used in this study.The input parameters were average daily traffic (ADT), inter-national roughness index (IRI), present serviceability index(PSI), and surface width. Results from that project indicatedthat the developed ANN model might have suffered from overfitting. Nonetheless, the previous model developed by the Uni-versity of Oklahoma was an important first step towards real-izing the objective of developing ANN-based models for thesetting of V85 for two-lane rural highways in Oklahoma.McFadden et al. [15] used models. Data from 100 sites infive states including New York, Pennsylvania, Oregon,Washington, and Texas (approximately two thirds of the data)were used for network training. The remaining 38 sites wereused for model testing.The models were also compared to regression models esti-mated by Krammes et al. [16] using the same data. It was con-cluded that ANNs offer predictive powers comparable withthose of regression and ANNs are able to overcome many ofthe assumptions and limitations inherent to linear regression.In Egypt, there are few studies on operating speed and roadfactors due to lack of road geometric and speed data. The mostimportant research in this direction is published by Hashim [1].The analysis in this paper uses 20 sites from two-lanerural roads that connect Shebin El-Kom, the capital city ofMinoufiya Governorate, with the adjacent cities. Three sepa-rate analyses are carried out. The first analysis investigatesthe relationship between 85th percentile speed and headwayto define a headway value corresponding to free moving vehi-cles. The second analysis examines the suitability of the postedspeed limits on the roads under study. The third and last anal-ysis inspects the conformity of the study sites’ speed data withnormal distributions. It was found that the 85th percentilespeed took a constant value at headway equal to 5 s or more.Also, a significant proportion of drivers exceed the postedspeed limit as well as the current speed limit may not be appro-priate. Finally spot speed data follow a normal distribution.MethodologyThe methodology of operating speed prediction in the presentresearch is pided into three main steps: (1) data collection, (2)linear regression models, and (3) ANN models.Data collectionThe present research focuses on the rural multi-lane highwaysin Egypt. The analysis uses 41 sites (sections) from two catego-ries of multi-lane highways. These categories are as follows:1. Agricultural highways category  Cairo–Alexandria Agricultural highway (CAA)  Tanta–Damietta Agricultural highway (TDA)2. Desert highways category  Cairo–Alexandria Desert highway (CAD)  Cairo–Ismailia Desert highway (CID)Each section length is 100 m. These roads have a postedspeed limit ranging from 100 to 40 km/h. The chosen sitesare located on straight sections with level terrain to avoidthe effect of the longitudinal gradient, and to be far from theinfluence of horizontal curves.Free-flow speeds are collected for passenger cars only. Spotspeed data are collected using radar gun (version LASER 500with±1 km/h accuracy) that is placed at midpoint of each sec-tion so as to be invisible to drivers [17]. Vehicles traveling infree-flow conditions are considered to have time headways ofat least 5 s. The number of speeds collected at each site rangefrom 100 to 160, which led to a total of 5330 spot speeds.Speeds are carried out in working days, during daylight hours.During all data collection periods, the weather is clear andthe pavement is dry and in a good condition.The road geometric data are collected directly from siteinvestigation which included lane width, right shoulder width,number of lanes in one direction, median width, pavementwidth, and existing of side access along section. All the previ-ous variables, their symbols, and statistical analysis are pro-vided in Table 1.The research uses a total number of eight variables whichare pided into dependent and independent variables.  Dependent variable– V85 = 1 variable (see Table 1).  Independent variables (7 variables)– Road geometric = 6 variables (see Table 1).– Posted speed limit = 1 variable (see Table 1).Linear regression modelsThe collected data are used to investigate the relationships be-tween operating speed (V85) as dependent variable and road-way factors and posted speed limit as independent variables.Simple linear regression was used to check the correlation coef-ficient between dependent variable and the independent vari-ables. The independent variables that have relatively high R2values were introduced into the multiple linear regression mod-els. The form of multiple linear regression models is shown inthe following equation:Y ¼ bo þXibiXi ð1Þwhere Y= V85; Xi = explanatory variables; bo = regressionconstant; and bi= regression coefficient.Then, stepwise regression analysis was used to select themost statistically significant independent variables with V85in one model. Stepwise regression starts with no model terms.At each step, it adds the most statistically significant term (theone with highest F statistic or lowest P-value) until the addi-tion of the next variable makes no significant difference. 路几何线形和交通速度英文文献和中文翻译(2):http://www.youerw.com/fanyi/lunwen_57273.html