---

In the present paper, ANN is used to predict the tidal level fluctuations, which is an important parameter in maritime areas. A time lagged recurrent network (TLRN) was used to train the ANN model. In this kind of networks, the problem is representation of the information in time instead of the information among the input patterns, as in the regular ANN models. Two sets of data were used to test the proposed model. San Francisco Bay tidal levels were used to test the performance of the model as a predictive tool. The second set of data was collected in Gouatr Bay in southeast of Iran. This data set was used to show the ability of the ANN model in predicting and completing of data in a station, which has a short period of records. Different model structures were used and compared with each other. In addition, an ARMA model was used to simulate time series data to compare the results with the ANN forecasts. Results proved that ANN can be used effectively in this field and satisfactory accuracy was found for the two examples. Based on this study, an operational real time environment could be achieved when using a trained forecasting neural network.

---

In this paper the analysis of the pipe networks is formulated as a nonlinear unconstrained optimization problem and solved by a general purpose optimization tool. The formulation is based on the minimization of the total potential energy of the network with respect to the nodal heads. An analogy with the analysis of the skeletal structures is used to derive tire formulation. The proposed formulation owes its significance for use in pipe network optimization algorithms. The ability and versatility of the method to simulate different pipe networks are numerically tested and the accuracy of the results is compared with direct network algorithms.

---

An efficient selection operator for use in genetic search of pipe networks optimal design is introduced in this paper. The proposed selection scheme is the superior member of a family of improved selection operators developed in an attempt to more closely simulate the main features of the natural mating process which is not reflected in existing selection schemes. The mating process occurring in the nature exhibits two distinct features. First, there is a competition between phenotypes looking for the fittest possible mate which usually ends up with choosing a mate with more or less the same fitness. Second, and more importantly, the search for a mate is often confined to a community of phenotypes rather than the whole population. Four different selection operators simulating these features in a random and pre-determined manner are developed and tested. All the selection schemes exhibit good convergence characteristics, in particular the one in which both the size of the sub-community and the pair of the mates in the sub-community are determined randomly. The efficiency of the proposed selection operator is shown by applying the method for the optimal design of three well-known benchmark networks, namely two-loop, Hanoi and New-York networks. The proposed scheme produces results comparable to the best results presented in the literature with much less computational effort

---

Optimization is an important methodology for activities in planning and design. The transportation designers are able to introduce better projects when they can save time and cost of travel for project by optimization methods. Most of the optimization problems in engineering are more complicated than they can be solved by custom optimization methods. The most common and available methods are heuristic methods. In these methods, the answer will be close to the optimum answer but it isn’t the exact one. For achieving more accuracy, more time has been spent. In fact, the accuracy of response will vary based on the time spent. In this research, using the generic algorithms, one of the most effective heuristic algorithms, a method of optimization for urban streets direction will be introduced. Therefore model of decision making in considered one way – two way streets is developed. The efficiency of model in Qazvin network is shown and the results compared whit the current situation as case study. The objective function of the research is to minimize the total travel time for all users, which is one of the most used in urban networks objectives.

---

The safety of buried pipes under repeated load has been a challenging task in geotechnical engineering. In this paper artificial neural network and regression model for predicting the vertical deformation of high-density polyethylene (HDPE), small diameter flexible pipes buried in reinforced trenches, which were subjected to repeated loadings to simulate the heavy vehicle loads, are proposed. The experimental data from tests show that the vertical diametric strain (VDS) of pipe embedded in reinforced sand depends on relative density of sand, number of reinforced layers and height of embedment depth of pipe significantly. Therefore in this investigation, the value of VDS is related to above pointed parameters. A database of 72 experiments from laboratory tests were utilized to train, validate and test the developed neural network and regression model. The results show that the predicted of the vertical diametric strain (VDS) using the trained neural network and regression model are in good agreement with the experimental results but the predictions obtained from the neural network are better than regression model as the maximum percentage of error for training data is less than 1.56% and 27.4%, for neural network and regression model, respectively. Also the additional set of 24 data was used for validation of the model as 90% of predicted results have less than 7% and 21.5% error for neural network and regression model, respectively. A parametric study has been conducted using the trained neural network to study the important parameters on the vertical diametric strain.

---

This paper presents a hybrid approach to developing a short-term traffic flow prediction model. In this

approach a primary model is synthesized based on Neural Networks and then the model structure is optimized through

Genetic Algorithm. The proposed approach is applied to a rural highway, Ghazvin-Rasht Road in Iran. The obtained

results are acceptable and indicate that the proposed approach can improve model accuracy while reducing model

structure complexity. Minimum achieved prediction r2 is 0.73 and number of connection links at least reduced 20%

as a result of optimization.

---

This paper presents the application of an iterative penalty method for the design of water distribution pipe networks. The optimal design of pipe networks is first recasted into an unconstrained minimization problem via the use of the penalty method, which is then solved by a global mathematical optimization tool. The difficulty of using a trial and error procedure to select the proper value of the penalty parameter is overcome by an iterative use of the penalty parameter. The proposed method reduces the original problem with a priori unknown penalty parameter to a series of similar optimization problems with known and increasing value of the penalty parameters. An iterative use of the penalty parameter is then implemented and its effect on the final solution is investigated. Two different methods of fitting, namely least squares and cubic splines, are used to continuously approximate the discrete pipe cost function and are tested by numerical examples. The method is applied to some benchmark examples and the results are compared with other global optimization approaches. The proposed method is shown to be comparable to existing global optimization methods.

---

Landslides are major natural hazards which not only result in the loss of human life but also cause economic burden on the society. Therefore, it is essential to develop suitable models to evaluate the susceptibility of slope failures and their zonations. This paper scientifically assesses various methods of landslide susceptibility zonation in GIS environment. A comparative study of Weights of Evidence (WOE), Analytical Hierarchy Process (AHP), Artificial Neural Network (ANN), and Generalized Linear Regression (GLR) procedures for landslide susceptibility zonation is presented. Controlling factors such as lithology, landuse, slope angle, slope aspect, curvature, distance to fault, and distance to drainage were considered as explanatory variables. Data of 151 sample points of observed landslides in Mazandaran Province, Iran, were used to train and test the approaches. Small scale maps (1:1,000,000) were used in this study. The estimated accuracy ranges from 80 to 88 percent. It is then inferred that the application of WOE in rating maps’ categories and ANN to weight effective factors result in the maximum accuracy.

---

The congestion pricing has been discussed as a practical tool for traffic management on urban transport networks. The traffic congestion is defined as an external diseconomy on the network in transport economics. It has been proposed that the congestion pricing would be used to reduce the traffic on the network. This paper investigates the cordon-based second-best congestion-pricing problems on road networks, including optimal selection of both toll levels and toll locations. A road network is viewed as a directed graph and the cutest concept in graph theory is used to describe the mathematical properties of a toll cordon by examining the incidence matrix of the network. Maximization of social welfare is sought subject to the elastic-demand traffic equilibrium constraint. A mathematical programming model with mixed (integer and continuous) variables is formulated and solved by use of two genetic algorithms for simultaneous determination of the toll levels and cordon location on the networks. The model and algorithm are demonstrated in the road network of Mashhad CBD.

---

In spite of significant advances in highways safety, a lot of crashes in high severities still occur in highways. Investigation of influential factors on crashes enables engineers to carry out calculations in order to reduce crash severity. Therefore, this paper deals with the models to illustrate the simultaneous influence of human factors, road, vehicle, weather conditions and traffic features including traffic volume and flow speed on the crash severity in urban highways. This study uses a series of artificial neural networks to model and estimate crash severity and to identify significant crash-related factors in urban highways. Applying artificial neural networks in engineering science has been proved in recent years. It is capable to predict and present desired results in spite of limited data sets, which is the remarkable feature of the artificial neural networks models. Obtained results illustrate that the variables such as highway width, head-on collision, type of vehicle at fault, ignoring lateral clearance, following distance, inability to control the vehicle, violating the permissible velocity and deviation to left by drivers are most significant factors that increase crash severity in urban highways.

---

In this paper, a new approach was presented for bus network design which took the effects of three out of four stages of the bus planning process into account. The presented model consisted of three majors steps 1- Network Design Procedure (NDP), 2- Frequency Determination and Assignment Procedure (FDAP), and 3- Network Evaluation Procedure (NEP). Genetic Algorithm (GA) was utilized to solve this problem since it was capable of solving large and complex problems. Optimization of bus assignment at depots is another important issue in bus system planning process which was considered in the presented model. In fact, the present model was tested on Mandl’s bus network which was a benchmark in Swiss network and was initially employed by Mandl and later by Baaj, Mahmassani, Kidwai, Chakroborty and Zhao. Several comparisons indicated that the model presented in this paper was superior to the previous models. Meanwhile, none of the previous approaches optimized depots assignment. Afterwards, sensitivity analysis on GA parameters was done and calculation times were presented. Subsequently the proposed model was evaluated thus, Mashhad bus network was designed using the methodology of the presented model.

---

Since the 1990’s, network reliability has been considered as a new index for evaluating transportation networks under uncertainty. A large number of studies have been revealed in the literature in this field, which are mostly dedicated to developing relevant measures that can be utilized for the evaluation of vulnerable networks under different sources of uncertainty, such as daily traffic flow fluctuations, natural disasters, weather conditions, and so fourth. This paper addresses the resource allocation problem in vulnerable transportation networks, in which multiple performance reliability measures should be met at their desired levels, while the overall cost of upgrading links’ performances should be minimized simultaneously. For this purpose, a new approach has been considered to formulate the two well-known performance measures, connectivity and capacity reliability, along with their application in a bi-objective nonlinear mixed integer goal programming model. In order to take into account the uncertain conditions of supply, links’ capacities have been assumed to be random variables and follow normal distribution functions. A computationally efficient method has been developed that allows calculating the network-wise performance indices simply by means of a set of functions of links’ performance reliabilities. Using this approach, as the performance reliability of links are themselves functions of the random links’ capacities, they can be simply calculated through numerical integration. To achieve desirable levels for both connectivity reliability and capacity reliability (as network-wise performance reliability measures) two distinct objectives have been considered. One of the objectives seeks to maximize each of the measures regardless of what is happening to the other objective function which minimizes the budget. Since optimization models with two conflicting objectives cannot be solved directly, the well-known goal attainment multi-objective decision-making (MODM) approach has been adapted to formulate the model as a single objective model. Then the resultant single objective model has been solved through the generalized gradient method, which is a straightforward solution algorithm coded in existing commercial software such as MATLAB programming software. To show the applicability of the proposed model, numerical results are provided for a simple network. Also, to show the sensitiveness of the model to decision maker’s direction weights, the results of sensitivity analysis are presented..

---

Due to its critical impact and significant destructive nature during and after seismic events, soil liquefaction and liquefactioninduced

lateral ground spreading have been increasingly important topics in the geotechnical earthquake engineering field

during the past four decades. The aim of this research is to develop an empirical model for the assessment of liquefaction-induced

lateral ground spreading. This study includes three main stages: compilation of liquefaction-induced lateral ground spreading

data from available earthquake case histories (the total number of 525 data points), detecting importance level of seismological,

topographical and geotechnical parameters for the resulted deformations, and proposing an empirical relation to predict

horizontal ground displacement in both ground slope and free face conditions. The statistical parameters and parametric study

presented for this model indicate the superiority of the current relation over the already introduced relations and its applicability

for engineers.

---

The main aim of this paper is to find the optimum shape of arch dams subjected to multiple natural frequency constraints by using an efficient methodology. The optimization is carried out by charged system search algorithm and its enhanced version. Computing the natural frequencies by Finite Element Analysis (FEA) during the optimization process is time consuming. In order to reduce the computational burden, Back Propagation (BP) neural network is trained and utilized to predict the arch dam natural frequencies. It is demonstrated that the optimum design obtained by the Enhanced Charged System Search using the BP network is the best compared with the results of other algorithms. The numerical results show the computational advantageous of the proposed methodology.

---

Concrete filled steel tube is constructed using various tube shapes to obtain most efficient properties of concrete core and steel tube. The compressive strength of concrete is considerably increased by the lateral confined steel tube in circular concrete filled steel tube (CCFT). The aim of this study was to present an integrated approach for predicting the steel-confined compressive strength of concrete in CCFT columns under axial loading based on large number of experimental data using artificial neural networks. Neural networks process information in a similar way the human brain does. Neural networks learn by example. The main parameters investigated in this study include the compressive strength of unconfined concrete (f'c), outer diameter (D) and length (L) of column, wall thickness (t) and tensile yield stress (fy) of steel tube. Subsequently, using the reliable network, empirical equations are developed for the confinement effect. The results of proposed model are compared with recently existing model on the basis of the experimental results. The findings demonstrate the precision and applicability of the empirical approach to determine capacity of CCFT columns.

---

This paper investigates the frequency response method for waterhammer phenomenon in piping networks. The unsteady flow governing equations are solved in time domain using the method of characteristics. They are also solved in frequency domain using the transfer matrix method. For the pipe network under consideration, critical transient excitation scenarios are identified. For each scenario, the frequency responses of the system as well as the time history of the transient pressures at the network nodes are calculated. The model is applied against a real pipe network and the results of the transfer matrix method are compared with those of the method of characteristics. It is concluded that the frequency response method not only presents a very fast algorithm for analyzing pipe systems but also, has an acceptable accuracy compared to the method of characteristics. The frequency response method requires linearization in some terms of the governing equations. Instead of that, it needs no computational discretization and interpolation necessary in time-space domains when using the method of characteristics.

---

One of the frequent aspects of lawlessness at signalized intersections is red light violation (RLV). In addition to adverse effects on intersection safety, RLV can cause delay in the startup of the vehicles in the competing phase, defined as the green flow in this study. In this research a video camera was used to collect the required data from intersections in order to investigate the adverse effect of RLV in the city of Esfahan, Iran. Then, by assigning a cellular network to the conflict points of the vehicles path in successive phases the vehicles arrival times to these cells were measured and the imposed delays to the green flow were measured. The results of this study showed that the behavior of drivers in the green flow, the time passed into red interval, and the presence of an all-red interval are the prominent factors affecting the delay caused by RLV. Furthermore, in the absence of an all-red intervals a delay in the range of 1 to 4.5 seconds was inflicted on the subsequent competing green phase. Results of the study also showed that the amount of delay increased substantially when a RL violator was not permitted to precede through the intersection by the green flow vehicles.