linear regression

Accurate travel time prediction is one of the important issues in the field of traffic and transportation that can significantly affect the daily life of people and organizations. In this research, four different machine learning methods including linear regression, multivariate regression, random forest and deep artificial neural network were trained to predict travel time. The purpose of this research is to predict travel time for use in intelligent traffic systems and to use and compare several new methods, including deep neural network and random forest regression, as well as considering new parameters in the computations such as weather conditions, traffic flow, travel time, and accidents and the traffic locking points compared to other studies are the innovation and comprehensiveness of this study compared to other studies. In the design and implementation of this research, real traffic data taken from Google map was used and analyzed. This data includes information such as traffic conditions, season, time of day, weather conditions, and route characteristics. The results of this research show that the deep neural network (DNN) model with R2 equal to 0.833 has a very good performance among the investigated models. This model explains 0.833% of the variance of the data and the distribution of the residuals in it is relatively central with a mean of zero and a distribution close to normal. The linear regression model with R2 equal to 0.615 has a poorer performance than DNN and explains 0.615% of the data variance. But the random regression model with R2 equal to 0.955 has one of the best performances in competition with DNN and explains 0.955% of the data variance. MSE and RMSE parameters were also used to evaluate the performance of the models, and as a result, a multidimensional comparison was made between the models, and the random forest model resulted in the lowest error values. Since in the collected traffic data, traffic accidents and consequently traffic locking points are also used in the models, and considering that the random forest model is more effectively adapted to the data despite the presence of noise and anomaly, the R2 value of this model is higher than R2 of Deep neural networks, due to the overfitting nature of Deep Learning methods.

Nowadays, traffic congestion is a major problem in metropolises that affect daily life. Imbalance between supply and demand causes conjestion. Demand management is used to balance demand and supply, since has more reasonable cost and less restrictions in comparison with increasing transportation supply. One policy in order to manage the demand and reduce Tehran traffic conjestion is to implement flexible working hours since Mehr 1401. In this study, the effect of flexible working hours on traffic congestion has been investigated by using length of Tehran congested roads. The linear regression has been modeled based on the length of traffic congestion of the third week of Mehr 1398 before the Covid-19 epidemic in comparison with the third week of Mehr 1401. It was expected to face more road congestion due to the traditional education after the virtual education during Covid19 epidemic, user behavior changes, increase in usage of private cars. Nevertheless by implementing flexible working hours, Tehran traffic congestion has been far more suitable except the Limited traffic zone than the urban management's prediction.

Foam concrete pavement can be used as a suitable alternative to other pavements in light urban traffic. In order to develop the use of this type of pavement, recognizing its features is necessary and important. Since the permeability of spongy concrete pavement is the most important functional feature of this type of pavement, further understanding of this feature and how it is affected by the parameters of the mixing design is the aim of this study. For this purpose, suitable combinations of foam concrete samples with granulation and different water-to-cement ratios of 36 samples have been made and tested. The ratio of water to cement for making experimental samples in the range of 0.28 to 0.34 in combination with aggregates with maximum nominal size of 9.5 mm, 12.5 mm and 19.5 mm has been selected. In order to select the appropriate model for predicting permeability changes, a comparison has been made between artificial neural network techniques and linear regression. Using the data obtained from laboratory activities and examining the fit of the models, the optimal model is proposed. Comparison of models showed that linear regression produced closer results in predicting changes in the permeability of sponge concrete. The use of linear regression can reduce the number of test specimens to achieve the optimal mixing design for foam concrete.
.

Climate variations, especially rainfall, have a high effect on the behavior of drivers and their decision. Due to the high effect of weather conditions on driving as well as human fatalities on road accidents, the importance of investigating driver behavior as a result of climate change is highlighted. This paper examines the variation of hourly average speed in the different weather conditions by considering the latter traffic factors influencing the speed. Rasht-Khomam highway is considered as the study area. Rasht as a coastal city has the highest rainfall in all the cities of Iran. The linear regression model has been used in this study to examine the variation of hourly average speed, considering traffic factors and weather conditions as independent variables. The Most important traffic factors that were included in the modeling are flow rate and percentage of heavy vehicles. Also, variables representing weather conditions include rainfall, horizontal vision and daylight. The independent variables were trans-formed into dummy variables to investigate the nonlinear relationship between them and the dependent variable. The results showed that the flow rate of more than 2100 veh/h reduces the speed of the vehicles up to 10.81 km/h, which is 12.72% of permitted speed on this highway. Another interesting finding of this research was that the amount of rainfall in ordered levels has a nonlinear effect on the speed. Heavy rain, moderate rain, and light rain reduce speeds by about 5.3, 4 and 2 km/h, respectively. Daylight was also shown to affect speed. In other words, driving at night can reduce speed up to 3 km/h. Horizontal vision variables were not recognized as significant in the model. This may be due to the drivers being familiar with the area and as a result, this parameter cannot affect their performance.

Trip generation is the first step in the conventional four-step transportation planning process, which, if incorrectly forecasted, lead to waste of national resources and poor infrastructure performance. This paper aims to identify the influential factors of suburban trip generation with mandatory purposes and compare the linear regression, Tobit and Poisson models using the origin-destination travel data of Khorasan, Fars and Tehran provinces in 2015. Results show better or equal performance of linear regression and Tobit models in all travel purposes. The variable of households with more than two vehicles for educational trip production and car ownership per capita for educational trip attraction are significant. Also, the variables of the share of households with more than 2 vehicles and the number of students per capita in car ownership have the greatest impact on the production and attraction of suburban educational trips. The share of people aged between 32-47 years and the number of employee per capita in car ownership have the greatest impact on the production and attraction of work trips, respectively. The population of a district has been significant with a positive sign in trip production of work and educational trips, but its impact on the educational trips is as twice as the work. The number of employee in car ownership per capita has a positive effect on the attraction and production of work trips, but the effect on the attraction is about 4 times the production. Furthermore, the effect of density related to the trip purpose varies in attraction models, so that the effect of industrial density on work trip is almost twice the effect of educational density on the educational trips, which can indicate a greater propensity of people to conduct suburban work trips compare to educational ones which could be used as a policy implication for future.

of this Research is the study and evaluation of the relationship between vegetation area and water area with the number of birds in Band-e-Alikhan wetland between 2011 and 2015. Due to the importance of Band-e-Alikhan wetland as a seasonal wetland with fresh water, which is located 35 km south of Varamin city, it has been used as a study area. In the present study, first, the necessary pre-processing, ie radiometric corrections, which include atmospheric corrections, banding errors, etc., were performed on Landsat 7 and 8 images, and then the normalized differential plant index maps (NDVI) and water index. Normalized difference (NDWI) was generated using pre-processed images. Then, by examining the histogram of plant and water indicators produced for each year, the appropriate threshold for each index was selected and by limiting the threshold on plant and water indicators produced, vegetation and water area maps were obtained for the year, respectively. . Each year, the maps obtained by the reference data selected manually in this study by satellite imagery were evaluated, the results of which show that the average overall accuracy and capability coefficient of vegetation surface extraction and of water over five years, with89/37% and 81/89%, which demonstrates the successful extraction of these parameters are. By obtaining the effective parameters, ie the level of vegetation and water, between the number of birds and the effective parameters of linear regression, two variables were formed and its coefficients were estimated by the least squares method. The results of studies and evaluations show that the model and regression formed between the number of birds and the parameters of vegetation surface and water area have a coefficient of determination of 0.861 and an adjusted coefficient of determination of 0.582 and indicate the appropriate fit of regression. Then, by the obtained coefficients and regression, the number of birds in 1394 was estimated using the level of vegetation and water area of the same year and was compared with the actual amount of birds in 1394, the results of which showed that the bird population is 93 . 1. It is predicted. The results also show that changes in the environmental conditions of the wetland provide a clear response to changes in bird populations and bird migration.

In this research, the hydraulic characteristics of flow through circular culverts and over broad crested weir are experimentally investigated for 12 models. Stage discharge rating curve was presented for each model. The results show that for a specific head, the discharge of combined structure is greater than the summation of discharge of weir and culvert. Also, the discharge coefficient for the combined structure is varying from 0.25 to 0.73 and for the weir is varying from 0.25 to 0.63 and for the culvert is varying from 0.33 to 0.77. The dimensionless parameter H/D (head to diameter) has the greater influence on discharge coefficient. In addition, regression equations are presented for estimation of discharge coefficient.

In this research, the hydraulic characteristics of flow through circular culverts and over broad crested weir are experimentally investigated for 12 models. Stage discharge rating curve was presented for each model. The results show that for a specific head, the discharge of combined structure is greater than the summation of discharge of weir and culvert. Also, the discharge coefficient for the combined structure is varying from 0.25 to 0.73 and for the weir is varying from 0.25 to 0.63 and for the culvert is varying from 0.33 to 0.77. The dimensionless parameter H/D (head to diameter) has the greater influence on discharge coefficient. In addition, regression equations are presented for estimation of discharge coefficient.

Trip generation is the first stage of the conventional four-step travel forecasting framework that estimates the number of trips to and from a traffic analysis zone. Using linear regression model is common in this step and generates an acceptable level of performance from the perspective of transport planning, however this model does not incorporate traveler behavior, integer and non-negative nature of trips. To overcome these limitation, several models have been suggested: censored model such as Tobit for deleting negative values; count data models such as negative binomial and Poisson for deleting continuous and negative values; and discrete choice models such as ordered logit and probit for incorporating traveler behavior and preventing continuous and negative values. Given the importance of trip generation stage and lack of sufficient and quantitive attention to various trip production models, this paper develops alternative trip production models. The purpose of this paper is a structural analysis for various trip production models and comparison of their performance in prediction. Four representative models (regression, Tobit, Poisson and ordered logit) are applied to the educational trips in Qazvin city. The modeling unit employed in this study is the household. Sample is included econometric- social attributes 4734 houshols. 85% of the data used for estimation and the rest to validation. The models are assessed by how closely they are able to replicate trips ,made by each household in the estimation and validation dataset. in order to compare the performance of models in prediction, each of the models is developed on estimation dataset, and the models are used to predict the trips made by each household in validation and estimation dataset. Measures assessing how well the predicted number of trips made daily by each houshold by each of the models compared to the observed number of trip made by the houshold are evaluated and compared. The four measure for assessing performance are the mean absolute error, regression of the predicted number of household- trips against the observed number of household trip in term of goodness of fit and coefficient of determination, and compare plot of observed and predicted aggregate trip shares. In order to modeling is used stata software. The result show that, In every four models, number of school students, number of university students, and household car ownership have been statistically significant. The performance of each of the models are different in term of various measures (mean absolute error, regression of the predicted number of household- trips against the observed number of household trip in term of goodness of fit and coefficient of determination, and compare plot of observed and predicted aggregate trip shares).From mean absolute error perspective, ordered Logit and linear regression models have the best performance, but from goodness of fit regression of the predicted number of household- trips against the observed number of household trip, Tobit models have the best performance. Ordered Logit models have the best performance in terms of coefficient of determination of the predicted number of household- trips against the observed number of household trip and comparision of predicted share of every trip rate level with observed share. The performance of each of the models are similar in prediction of validation and estimation dataset.

Tunnels are one of the most important accident-prone zones due to their physical and functional difference from open parts of the road whereas crash-prediction models for road tunnels have rarely been investigated. The main purpose of this study is to identify important parameters that affect the traffic safety in tunnels. In this paper, linear regression, Poisson regression, Negative binominal regression and Zero inflated regressions models are applied in order to obtain crash prediction models for property damage, serious injury and fatal accidents. The results show that the best model for property damage accidents is linear regression output. However, for fatal and injuries accidents, zero inflated regression’s results are more dependable. This paper’s suggested method appears to be useful for many applications such as the estimation of accident reductions due to improvement in existing tunnels and/or to modifications of traffic control systems, as well as for the prediction of accidents when different tunnel design options are compared. According to the final crash prediction models the most important safety characteristics of tunnels are: AADT per lane, tunnel length, heavy vehicles ratio, and number of lanes in tunnel

Construction of residential, commercial, medical, official and other different type of complexes is symbol of land use development. Determination of trip generation rate is vital parameter for Transportation planners for conducting an Impact study. In this research a regression models show different land use trip generation rate based on collected data of users, trip behavior. A literature review expressed the importance of localizing trip generation study. Data collection and analysis methods are demonstrated and shown as standard structure. Finally results of study are compared with other countries and cities for analyzing different trip generation based on travel behavior.

Bus stops are one of the most important infrastructures at bus transportation system that decreases the role near-side bus stop with regard to having it before the intersection and the effect on the traffic stream of Inter section area is very important. The purpose of this article linear Modeling for predicted to place near-side bus stop in intersections with signal control use of Survey five elected stop in Mashhad city. Number of Records has statistics for modeling; record 575 has been with the use of the analysis multiple linear regressions by SPSS 19 software. The results caused by the evaluation of proposed models coefficient of determination above 0. 9 are that this put satp orange of models. Validity proposed models with the use of the data collection of the other stop in Mashhad city which indicates the results satisfaction for predicted place near-side bus stop in intersections with signal control. As regards in our country to examine Micro Models location for the bus stops; not been paid¡ the results can be the existing problems in this section improve to some extent.

Meta-analysis is a statistical systematic literature review which is common approach to summarize and obtain overall estimation of different studies. It has been increasingly used for evaluating the effects of various afety measures. Publication bias is an important error in meta-analysis, being cause of not publishing studies that have generally small size and non-significant impact. Funnel plot is a visual qualitative tool for detecting publication bias in meta-analysis. This paper introduces and explains two statistical tests, rank correlation method and linear regression method, based on funnel plot for detecting statistically significant publication bias in meta-analysis. These two statistical tests can be used as a quantitative tool for detecting publication bias. This is the first time that a quantitative method has been used for publication bias detections in safety metaanalysis.As a case study, the safety effects of urban traffic calming measures have been analyzed using meta-analysis. Safety effects of urban traffic calming have been gathered from 46 related studies and an overall effect for this safety treatment has been obtained. Two aforementioned tests are used to test publication bias. Meta-analysis shows that urban traffic calming measures approximately reduce the number of injury accidents, property damage accidents and total accidents by about 15, 17 and 14 percent, respectively. Statistical tests show that there is no evidence of publication bias in urban traffic calming studies.