پیش بینی

Accurate prediction of the carbonation depth of concrete is very important to protect against harmful consequences such as cracking and corrosion. Nevertheless, due to the complexities of the process and the multitude of available variables, identifying the parameters that are most important in modeling the carbonate depth of concrete is considered a big challenge. This paper deals with the development of a new feature selection method called MOEA/D-ANN. The purpose of this method is to identify the most important variables that help to achieve the highest forecasting accuracy. This proposed method combines the separation-based multi-objective optimization evolutionary algorithm with artificial neural networks to effectively solve the feature selection problem by using the power of optimization methods and machine learning. To evaluate the performance of the introduced method, the algorithm (RReliefF), which is a feature ranking algorithm, has also been used. ANN method has been used to predict concrete carbonate depth and combined MOEA/D-ANN and RReliefF methods have been used to find the influencing variables. The obtained results have shown that the model created using the MOEA/D-ANN approach, by combining the variables determined by it, has a significant reduction in the percentage of errors and an increase in accuracy. In addition, this model reaches the significant value of the coefficient of determination R2 = 0.99, which emphasizes its exceptional accuracy in predicting the depth of concrete carbonate and confirming the accurate selection of influential variables.

Predicting the number of vehicles is crucial in intelligent transportation systems and is a key component of traffic management. Effective vehicle management significantly improves the efficiency of urban road networks and reduces congestion. This study utilizes vehicle entry data for Tehran's traffic cordons from 2017 to 2021 and employs three machine learning methods (Random Forest, XGBoost, and K-Nearest Neighbors) to predict the demand for incoming vehicles in each traffic cordon (Traffic Plan and Air Pollution Control Plan) on an hourly basis. In addition to conventional variables such as weather data and time, travel demand management policies are also used as predictor variables. Sensitivity analysis is conducted to evaluate the impact of different policies on predicting traffic volume. The results indicate that the XGBoost model and the Random Forest model, with a mean absolute percentage error (MAPE) of 8.2% and 11.16%, respectively, for traffic and air pollution cordons, perform better compared to the K-Nearest Neighbors model. Sensitivity analysis of variables related to travel demand management policies shows that the policies of "online schooling" and "tolls for entering the traffic and air pollution cordons" have the greatest impact, while the policy of "inter-provincial travel restrictions" has the least impact on improving prediction accuracy.

The purpose of this article is to predict the delays of passenger trains in the railway areas of the Islamic Republic of Iran using historical data of passenger trains and weather data with machine learning methods. Forecasting delays in railway areas with weather conditions in that area in the winter season can be effective for decision-making and preventive measures. The data used in this study includes passenger train delay data from 2017 to 2022 and weather data from synoptic stations from 1396 to 1400. which contains 46596 records. Independent variables include year, month, day of the month, day of the week, axis of movement, type of train, railway area, maximum wind speed, minimum horizontal visibility, minimum temperature, maximum temperature, number of frost reports on the ground surface and precipitation. It rains and snows 24 hours a day. The proposed method for solving the existing problem based on CRISP-DM is a superior methodology in the field of implementing machine learning and data mining techniques in research and executive fields. Predictive modeling has been carried out in the form of classification. In order to predict the classification of the delay dependent variable, they are divided into two classes, on time and with delay. Supervised learning methods of the classification type have been used to predict the influence of weather factors on the occurrence of delays in railway areas. To evaluate the prediction results, cross-validation has been used to check the validity of the model. The results show that the influence of weather factors in the winter season during the 5-year period in the year-by-year surveys had a positive, negative or neutral effect on the occurrence of delays in railway areas. At the end of the article, preventive measures are presented to adapt the railway industry to climate threats in the future.

As the purpose of monitoring the project is to make accurate decisions that can have significant effects on the project’s success, predicting the project’s characteristics becomes more important. According to experts, schedule delays are a frequent issue in many construction projects. This research aims to propose a model that can address project scheduling problems. For this purpose, this study proposes new applications of recurrent neural network architectures based on short-term long-term memory (LSTM) prediction models. Subsequently, the prediction results of the presented models are compared and verified with the historical data of a real project. The data used in this study has been obtained from the South Extension Project of Tehran Metro Line 6. The project started in October 2016 and ended in July 2018, lasting for a total of 21 months. In this study, the training dataset consisted of the initial 14 months' data, which accounted for 83 percent of the total data. We used the construction project progress as a forecasting variable. To evaluate the performance of LSTM models, we used the mean square error (MSE) metric as the evaluation criterion. The results show that the model accurately forecasts the project’s future progress based on its past progress.

In road pavement design, soil resilient modulus is one of the factors that play a very important role in determining pavement thickness. In the past, determining the Resilient Modulus of soil directly from laboratory results has not always been practical due to its high costs, both in terms of equipment and labor. Therefore, it is possible to predict and determine this parameter based on past field data using artificial intelligence. Our goal in this paper is to develop a model for predicting the resilient modulus of stabilized clay soils using artificial neural networks. In this study, four different soil samples stabilized with additives, such as lime, fly ash, and cement kiln dust, were examined using the pavement design appendix of the AASHTO 2002 specification. By comparing the results to the laboratory data based on the statistical indicators such as regression coefficient (0.99), root mean square error (less than 6 percent), we found that the artificial neural network was highly accurate in predicting the resilient modulus..

Conducting evaluation studies on the bridges used on the road surface is one of the most important time-consuming and costly processes, especially considering the high number of bridges in Iran, i.e., more than 35 thousand in the whole country and 8658 bridges in Zanjan province. On the other hand, the time and cost of these studies can cause delays in carrying out studies for all bridges and cause irreparable damages due to a lack of proper management of bridge repair and maintenance. Taguchi's test design method is one of the methods that predict the desired combination with the help of statistical and mathematical models, by defining its orthogonal arrays, instead of performing all possible evaluation options, by performing a limited number of evaluations. In this research, based on the Taguchi method, instead of examining 8658 bridges with 13 different criteria, only 27 combinations of the physical characteristics of bridges and atmospheric, climatic and traffic conditions affecting concrete road bridges in 5 main axes of Zanjan province were determined the deterioration indices of bridges with these combinations were calculated.It showed that the combination of bridges with 2-3 times of snow along the axis, 91-100 days of frost during the year, 26-30% of heavy vehicles passing over the bridge and a length of 7.1-12 meters has the highest structure failure index with an estimated average of 76.2725, which will lead to the highest failure risk. This means that this combination has created the highest risk of damage. Also, the most important factor in the failure of bridges is the percentage of passing heavy vehicles compared to the total traffic.

Increasing the level of safety in the road transport sector has always been one of the most important issues in the transportation system. In the national transport industry, the outsourcing industry always has the highest casualties. By identifying the safety indicators and the points of the extra-urban accident and increasing their level of safety, the percentage of losses and losses can be greatly reduced. Research for modeling human performance has led to the creation of two new research fields, neural networks and fuzzy systems. Neural networks are dynamic systems that, by simulating the functioning of the nervous system and the human brain by processing on experimental data, transfer knowledge or law beyond the data to the network structure, and relying on the ability to learn and ability parallel processing is capable of solving complex problems. Fuzzy systems, based on the approximate human decision-making process, are quantitatively and intuitively modeled quantitative, and thus they are trying to deal with uncertainties. The simplicity and comprehensiveness of this method are its advantages. Neuro-fuzzy systems combine two methods of parallel learning and processing of neural networks and approximate fuzzy inference. In this research, a neuro-fuzzy recurrence network is designed to predict the number of accidents. Then, the genetic algorithm is proposed for a new method in the training of this network and compared to them.

This study investigates the rheological and mechanical properties of ultra-high performance fiber reinforced self-compacting concrete (UHPSCC) using garnet and basalt aggregates, microsilica, fly ash, nanosilica, and steel fibers. To reduce construction costs, two artificial neural networks (ANN-GA and RBF-NN) are used to predict UHPSCC properties and compared with laboratory results. The studied rheological properties include slump flow diameter, slump flow time, V-funnel test, and L-box test. The laboratory results show high compressive and tensile strength, and acceptable rheological properties within EFNARC acceptance range. Both neural networks demonstrate acceptable accuracy in predicting rheological properties, with ANN-GA having higher prediction accuracy. Understanding UHPSCC properties is essential for the construction industry, and the use of ANN-GA can save on costs while maintaining accuracy in predicting its properties.

One of the most contagious diseases of recent years is Covid 19 disease (Corona), which has spread from Wuhan, China to the rest of the world since late 2019, causing many crises and a profound impact on the world and our daily lives. In most people infected with the disease, it causes respiratory symptoms, the severity of which depends on the person's immune system. The main objectives of this study are to discover the clusters and predict the high risk areas of Covid 19 disease, compare the efficiency of the two proposed methods and determine the effective parameters by city. In this study, Moran index and hot spot analysis index were used to investigate the distribution pattern of disease incidence rates and clusters, respectively, and Pearson correlation coefficient was used to determine effective disease parameters. In this study, statistical data of Covid 19 disease of East Azerbaijan province in the city along with environmental and topographic, health, economic and urban facilities data in the period from February 22, 2020 to November 20, 2020, were collected weekly. According to the results, the incidence of Covid 19 disease during this period has passed two peaks and according to the maps obtained from the two models, in some weeks the GWR model and in some weeks the MLP model was the superior model; also, for the GWR model, the goodness of fit index value is 0.8985 and the normalized root mean square error is 0.0822 and for the MLP model is 0.8226 and 0.1340, respectively, which shows that the GWR method is more appropriate. Sensitivity analysis of different parameters showed that the parameters of the Covid 19 incidence rate of the previous week and wind speed are more important than other modeled parameters in this issue. In this study, effective parameters were extracted separately for each city and a local model was presented that compared to the general state of the model, the local model had better accuracy than the general model of the MLP method.

Prediction of river inflow along with other parameters such as sediment load, flood magnitude, and so on plays an important role in Water Resources Management planning and reservoir operation program. In this regard, many attempts have been devoted so far by the researchers to predict inflow or flow discharge in the rivers. One of the most important rivers in the Golestan province that highly influences climate changing is Gorganrood river. Assessment of chaotic behavior of time series like inflows of rivers by the entropy measure is an important facility in Water Resources Management projects. In addition, this tool can be employed to extract the number of embedding dimensions to predict time series by models like the ARIMA and ANNs. To this end, this paper employed the capability of Approximate Entropy (ApEn) measure as one of the famous models to capture irregular behavior of a time series. Then, ARIMA and ANNs models are implemented to predict monthly inflows at Gorganrood River as the biggest river in Golestan province. The models are developed by using AQqala and Ghazaghli hydrometric stations gathered data. Final results show that at AQqala and Ghazaghli stations, to have an informative predictor model, the number of embedding dimensions must be set to 12 and 10, respectively. In addition, it is concluded that the developed models are accurate enough to be applied in another period of the times in the studied case. Sensitivity analysis of the ARIMA and ANNs models versus various embedding dimensions proves extracted values of embedding dimensions obtained by the ApEn. In addition, the evaluation of the ApEn curves proves the effect of the constructed dams like Voshmgir, Golestan, and Boustan dams on the environmental process and river behavior. The sensitivity analysis versus embedding dimensions clarifies the effects of these parameters over ARIMA and ANNs models.

The aim of this paper is to predict passenger train delays in Iranian Railways using data mining techniques. The results of this research are used to design train timetables. The data used in this research includes a database of passenger train delays from year 2013 to 2018, including 380,748 records. Independent variables for prediction model include year, month, day, day of the week, departure time, axis, train type, car type, origin and destination of the train and the train owner.  In order to model prediction of train delay, two kind of prediction, named Numerical and Classification are used on entire database. Neural network and C5.0 methods are used for classification prediction. The Twostep clustering method is used to divide the delay field into three labels. Regression, CHAID and neural network methods are used for numerical prediction. To evaluate prediction results, we divide existing data set into two subsets called training set and test set, in which delays from year 2013 to 2016 are the training set and delays of year 2017 are the test set. By evaluating the prediction methods, the results show that in numerical prediction, neural network method and in prediction by classification, C5.0 method has higher accuracy than other methods. Therefore, these two techniques have been used to predict the train delays of year 2018. Numerical prediction is used by grouping some database fields. The results show that the prediction by grouping has higher accuracy than the prediction on the entire database.

With the increase in road transport in Iran, accidental damage has also increased dramatically. If accurate predictions are made using appropriate techniques, the percentage of actual and effective factors to improve the conditions of the accident can be determined. This research has been done using fuzzy logic in MATLAB software, and a detailed analysis of the data has been done and then the results have been obtained. The proposed model consists of three inputs, an inference engine in the fuzzy method and the output. In the first stage, six variables were considered as inputs: longitudinal slope, velocity, shoulder path, subterranean intersection, arc radius, gap gap. These factors are considered with the greatest impact on road accidents. The next stage of the accidental points was considered as the output, and in the third step, for the inference engine, the rules were written descriptively. Finally, the results are compared with the actual statistics. To be This approach will enable prediction of accidents in the coming year and determine the best method for modifying the components to minimize road accidents. The selected method is implemented and evaluated case by case in Birjand axis. . The results suggest that the proposed inference framework will be able to detect accident patterns and predict the severity of road accidents, thereby choosing the best option and priority for repair, repair and maintenance.

Prediction of the road accidents severity based on scientific methods can be considered as an important tool in road safety management and transportation engineering. This paper presents a methodology to identify and predict the severity of accidents on highways. The methodology is based on an experimental investigation carried out on an important corridor and arterial way located in khorasan-Razavi province. The study analyses accidents occurring between 1392 and 1395 and the data concerning the accidents that were acquired from police reports. The geometric data were acquired from field study and the related office. The data, organized and stored in a specific designed Geographic Information System (GIS), were processed using a series of statistical procedures, in particular, the results took out the following two models: Model 1 was produced by Multivariate Analysis (MVA) and the Model 2 was obtained using the Artificial Neural Network (ANN) technique. Comparing the two models, it emerged that Model 2 is better than Model 1 because the total sum of the residual is lower. However, Model 1 is more efficient in estimating the black spots with a large number of accident.

Project management is an organized system and resource management so that the project is completed with a specific vision, specific quality, specific time and specific cost. Project management is the process by which a project must achieve the desired result in the easiest and most cost-effective way during its life cycle. Measuring the performance of the project team and determining the progress of the project and comparing it with the initial plan has always been and will be the concern of project managers and it can be said that project performance control with value management is the most efficient and common way to control project performance It started in the middle of the twentieth century and gradually spread. The purpose of this study is to investigate new approaches in the field of value management gained by reviewing the literature in this field. In most recent researches on the subject of value management, it has been pointed out that it is insufficient to achieve the goals of project managers. Therefore, in recent years, many researchers have tried to improve the method of managing the value gained by combining it with other methods. In construction project management, the management of acquired value is considered as a suitable tool and therefore has been implemented in various construction industries. Acquired value management is based on the belief that it increases the value of the project. Given the dynamic environment in which construction companies must operate, especially in turbulent environments that are a direct result of the recent global recession, it is important to address the executive potential of value management in the construction industry. The difference between traditional value management forecasting approaches and new value management approaches in project management can be a way out of problems and shortcomings in this area.

Numerous people have died and economically damaged due to the road accidents. One of the efficient ways of reducing crashes is to predict them before happening. This paper investigated the power of artificial-neural network (ANN) model to predict crash frequencies of Naein-Ardakan road, located in Yazd, Iran. To date, there seems no research done to compare the effects of ANN training functions on prediction performance. This research aimed to determine the proper ANN training algorithm for crash frequency prediction. In this regard, four different training algorithms were investigated. The results demonstrated the outperformance of ‘trainlm’ algorithm. Additionally, it was found that the average daily traffic per lane and gap lengths is the most influential factors in crash occurrences, respectively. The present study can be applied to more precisely explain the effects of independent variables on crash outcomes. An in-depth explanation of the effectiveness of independent variables can assist road safety experts in making better decisions for reducing accidents.

Predicting the residual load-bearing capacity of damaged concrete-filled steel tube (CFST) columns exposed to fire, based on the effects of eccentricities, is a subject on which relatively little research has been done. This paper aims to present the results of a series of post-fire residual capacity tests for CFST columns with different cross sections (circular and square), under axial load, and different eccentricities in the event of a failure. In this experimental study, the influence of parameters such as cross-sectional shape, load eccentricity, slenderness and fire protective coating on the post-fire residual capacity of CFST sections was investigated. Based on the results of this study, the following conclusions were obtained in the scope of this research work:The results showed that eccentricity could be effective in reducing the residual capacity of the column, but the change in the amount of eccentricity cannot be as effective as reducing the residual capacity of the columns. The studies indicate that the residual capacity is significantly reduced by increasing the slenderness ratio. Therefore, in order to determine the residual capacity of the CFST columns under load eccentricity, a simplified equation for predicting the reduction factor was proposed, a comparison between the predicted and experimental results shows that there is a reasonably good agreement. The tests show that by increasing the temperature over a cross-section of CFST columns, the residual axial load capacity and the axial stiffness of the unprotected columns decreased significantly compared to the unheated columns. Comparison of the axial compressive capacity of CFST columns with square and circular have shown that for columns having the same concrete material, the circular column has slightly better structural post-fire behavior than the square column. To fire-protected sections, the effect of the cross-sectional shape on the residual strength is significant, relative to the unprotected sections is more. In fact, by comparing the temperature distribution on the surface of the circular and square sections, one can find that the maximum temperature distribution at the circular cross sections is less than the square cross sections. Therefore, with less degradation of the properties of the cross-sectional materials, the more residual load-bearing capacity is expected. Finally, based on the experimental results, the ability to predict the residual load-bearing capacity of the concrete-filled hollow tube columns after exposure to the ISO-834 standard fire as per the modified design method in Eurocode 4 for the fire and ambient conditions were evaluated. The investigation’s results showed that the simplified method of Eurocode 4, in the ambient temperature produced safe results for predicting residual resistance of CFST columns after fire exposure, under both concentric and eccentric loading conditions. This approach was considered as a conservative method, with the MPEs for concentric loads, as well as both concentric and eccentric loads as -5.51% and -3.06% lower than the prediction, respectively.

In recent decades, the optimal use of dam reservoirs among water resource management researchers has been of great interest. So, due to the high performance and capabilities of evolutionary algorithms, in this study, using gray wolf optimizer algorithm (GWO) to predict Urmia Shaharchay dam reservoir and present a short-term forecast program for next years. The gray wolf algorithm imitates the hierarchy of leadership and the mechanism of hunting gray wolves in nature. In this algorithm, four types of gray wolves consists of alpha, beta, delta and omega have been used to simulate the hierarchy of leadership. In this study, considering the annual planning and monthly intervals, GWO algorithm was firstly evaluated for prediction storage of Urmia shaharchay reservoir during 2006-202014 years and the results compared with ICA algorithm. The results showed that GWO algorithm, with a high accuracy of 90%, provides better results in finding optimal response, convergence rate and lower computational cost compared to ICA algorithm. The results of this study indicated that GWO algorithm, an appropriate algorithm to solve the optimal operation of dam reservoir system problem.

One of the most important goals of a pavement management system is determination of optimal priorities and time for repairs, through prediction of pavement status. In fact, the purpose of the PMS system is to repair and maintain the early stages of cost savings and savings. . Therefore, in this study, in order to determine the Pavement Condition Index (PCI), two linear regression models and back propagation neural network models were fitted and their power estimates were compared.  In this regard, the damages of three freeways of Karbala, Paul Zal and Tehran - Qom have been studied to identify the appropriate method for predicting pavement status index in order to identify the optimal maintenance time to reduce its costs. . Micropaver software and MATLAB and SPSS software were used for modeling and evaluation of components. This track was sampled in order to capture the failure of sample units at 100 m intervals and parts at 500 m intervals. The variables considered in the model analysis included: segment lifetime at inspection time (month), unit width, average AADT at segment lifetime, average percentage of heavy vehicles at segment lifetime, maximum temperature at segment lifetime in 1396, minimum Temperature is the lifetime of the piece in 1396 and the thickness of the pavement (cm). . The results show that the performance of neural network model based on mean square error index (MSE) as well as R2 index is 0.95 and 0.87, respectively, which is more valid than the multiple linear regression model (0.139). The future is paved. In addition, according to the neural network model, the lifetime of the segment can be most important in neural network construction (0.55) and then maximum temperature (0.122) and percentage of heavy vehicles (0.120) are the next important variables in predicting pavement status of roads.

Forecasting rainfall situation has paramount importance for water resources engineering. In this field, linear time series models are widely used in hydrology. Models of ARMA family have always had weaknesses which can be solved by integration of ARMA linear time series models with nonlinear time series models such as ARCH. In economy, the sequence of error variance in one model of errors’ size in previous time periods is the main assumption for Autoregressive conditional heteroscedastic models (Engle, 1982). At first, models of ARCH family for time series were used in financial and economic problems. In problems related to hydrology, ARCH models have been studied less.