A number of common laboratory rock mechanics tests are carried out in all geotechnical projects such as dams, to determine parameters such as porosity, density, water absorption, sonic velocity, Brazilian tensile strength, uniaxial compressive strength, and triaxial compressive strength. In this paper, data obtained from two dams in Asmari Formation including Khersan 1 and Karun 4 - both located in Chahar-MahalVaBakhtiari Province, Iran- have been subjected to a series of statistical analyses. Then, using Multivariate Linear Regression (MLR) and ARTIFICIAL NEURAL NETWORKS values of UCS, E, C, andj were predicted using the input parametersincludingdepth, compressionultrasonic velocity, porosity, density, and Brazilian tensile strength. The designed (ANN) in this research was a feedforwardbackpropagation network which is powerful tool to solve prediction problems.Designed network had two hidden layer (hidden layer 1: 18 neurons and hidden layer 2: 20 neurons). Via comparing designed MLR and (ANN) models, it was revealed that (ANN)s (R2 UCS=0.91, R2 E=0.87, R2 C=0.78, R2 phi =0.61) are more efficient than MLR models (R2 UCS=0.69, R2 E=0.69, R2 C=0.66, and R2 phi=0.50) in predicting strength and shear parameters of the intact rock. Also, to enhance the credibility of this study, some extra tests were carried out to evaluate the efficiency of network designed for prediction of strength parameters. The results obtained from this network were as: R2 UCS=0.85, R2 E=0.81.

Flood energy attenuation in vegetated rivers is a critical factor in flood management and riverine ecosystem stability. This study develops an ARTIFICIAL NEURAL Network ((ANN)) model to predict flood energy reduction using a dataset of 760 rivers in Iran. The dataset was divided into 70% for training and 30% for testing. A multi-layer perceptron (MLP) (ANN) was implemented in Python to establish the relationship between key hydraulic and vegetation parameters and energy dissipation. The input variables included the Froude number (Fr), vegetation density and thickness (Dv), and relative backwater rise (Δr), while the output parameter was energy reduction (ΔE). The model’s performance was evaluated using statistical metrics, achieving a high correlation (R² = 0. 92) and a low mean absolute error (MAE = 0. 025 and RMSE = 0. 012), demonstrating the (ANN)’s strong predictive capability. Results indicate that vegetation characteristics significantly influence energy dissipation, with denser and thicker vegetation leading to greater flood energy reduction. Sensitivity analysis further highlighted the dominant role of Δr in determining energy loss. The (ANN) model outperformed traditional empirical methods in accuracy, proving its reliability for practical applications in flood risk assessment. These findings suggest that (ANN)-based modeling can be a valuable tool for hydrologists and engineers in optimizing river management strategies. Future research should focus on expanding the dataset and integrating additional hydraulic parameters to further refine prediction accuracy.

The present research studies on the prediction of Tehran Exchange Price Index (TEPIX) using ARTIFICIAL NEURAL NETWORKS and represents some evidences on chaotic behavior of Tehran Exchange Price Index. TEPIX data form 1990-2003 was used in this research. Two sets of data were selected for NEURAL network input. Different lags of index and macroeconomic factors as independent variables. Index value in the next week was the network output. The NEURAL NETWORKS used in this research were multilayer perception (MLP). That trained with back propagation algorithm, and contained three-layer feed forward NEURAL NETWORKS (Input, Hidden and Output layer) and four-layer (Input layer, hidden double layer and Output layer) with different number of neurons in input and hidden layers. Functions used in the middle layer are nonlinear tan sigmoid and linear in the output layer, the training command is also applied for network training. Furthermore, the linear ARIMA model is used to predict the price index for the next week. The research results shows that the NEURAL NETWORKS have better performance for the prediction of price index rather than linear ARIMA model. The acceptable MSE for network error in test and estimations data indicates that there are chaotic movements in the behavior of price index. The calculated R2 test indicates some evidences opposite to the Efficient Market Hypothesis (EMH) and random walk.      

This study aimed to investigate the effects of inputs such as pesticides, fertilizers, seeds, labor and machine use on wheat yield. The data used in the study were obtained from 177 wheat producers in Diyarbakir Province through a questionnaire, and ARTIFICIAL NEURAL NETWORKS ((ANN)) were used in the analysis of the data. According to the results, the average wheat yield is 5482.03 kg ha-1, and 294.75 kg of seeds, 550.73 kg of fertilizer, 3.59 hours of machinery, 5.37 hours of labor and 2662.43 cc of pesticides were used per hectare for wheat production. According to the results of the (ANN) analysis, the relative importance of inputs affecting wheat yield was quantified, with the use of pesticides and fertilizer having the most significant impacts. Specifically, the sensitivity coefficients for pesticide use and fertilizer use were found to be 0.23 and 0.14, respectively. These coefficients represent the relative change in wheat yield per unit change in the input parameters.

There is a complex relationship between the properties of Poly (Lactic-Co-Glycolic Acid) (PLGA) and its Nanoparticle (NP) synthesis parameters that affect its performance as a drug delivery system. In the current study because of the complexity of the data, ARTIFICIAL NEURAL NETWORKS were used to predict the impact of input variables on the performance, including NP size, Encapsulation Efficiency (E.E.%), and Drug Loading (D.L.%). In the current study, over 180 data gathered from literarture via data minig method. The effective parameters can be classified into two main groups: intrinsic polymer properties and parameters associated with the synthesis process. The individual effects of each of these parameters, their combination as third set, and finally target parameters have also been added to them as 4th set are thoroughly examined. The results revealed that considering all parameters as 4th set provides higher accuracy (R2 = 0.93) in NP size prediction. At the same time, E.E. % and D.L. % are primarily influenced by synthesis parameters (R2 = 0.96) and polymer intrinsic properties (R2 = 0.92), respectively. Sensitivity analysis for the effect of each parameter has revealed that presence of PEG in the formulation, NPs size, and synthesis method are the most effective parameters in prediction of NPs size,  E.E. % and D.L. %, respectively.

This paper presents the application of multivariate time series model (ARDL) to investigate factors affecting bread waste and to explore the relationships among shortrun, longrun and error correction coefficient and the independent variables over the period 1978-2006. Results reveal that Gross National Product and urbanization have positive effects on bread waste in the long term, while the bread price and Gini coefficient have negative effects on bread waste in short term. To predict the amount of bread waste, ARTIFICIAL NEURAL network ((ANN)) and ARDL model were applied. Comparison of the two models indicated that the (ANN)-ARDL multi-layer perceptron model (3 layers) with a hyperbolic tangent transfer function for the hidden layer and a delta-bar-delta learning algorithm, is the best model for forecasting the amount of bread waste. This amount will exceed 3.181 million tons in 2011. This implies that considering the wheat price in 2006, USD 1145 million will be removed from the national economic cycle.

Nowadays Volunteered Geographic Information (VGI) is an important source of geographic information. Unlike formal data, precision and accuracy of VGI is not known at the time of data gathering. Thus, several methods have been developed to evaluate the VGI quality. One of these methods is assessing the VGI quality by evaluating the reliability (trustworthiness) of VGI participants. In this study, using background information of VGI participants and ARTIFICIAL NEURAL NETWORKS ((ANN)), user’s reliability in producing spatial information is estimated. To collect user’s background information, a mobile application was designed under the Android operating system. In this program, the map of Tehran was used and changes were applied to some of its parts. When using this program, the users must answer questions such as gender, age, education, familiarity with GPS or GIS, etc. Then users should answer the questions about the changes made to the map. All of the answers are compared with the correct ones. Then the percentage of user’s correct answers is calculated. Each user should answer the questions of at least three regions. Finally, this information was collected for 1102 regions. The data was used to train the (ANN) as well as validating. (ANN) which is a feed forward back propagation multilayer perceptron network was trained by various number of neurons and hidden layers. The best network with mean squared error value 0. 19988 was selected. Using the trained (ANN), it is possible that in a VGI system, a new user enters his/her background information and the percentage of predicted correct user’s responses is estimated. This percentage may be assumed as one of the criteria of user's reliability in VGI

During the past few years, modeling in agriculture has attracted considerable attention. New modeling methods including NEURAL NETWORKS are employed in various industries, and it is necessary that their use in agriculture be also considered. This research addressed the trend of energy use in broiler farms in Alborz Province and sought to model the trend of energy consumption and production in these farms. For this purpose, 45 questionnaires were distributed among broiler producers of the province. The reported levels of energy consumption and production were 218.40 and 30.13 GJ per thousand broilers, respectively. The largest share of the energy consumed, 40%, 25%, 23% and 9%, was related to gas-oil, feed, natural gas, and electricity inputs. Indices of ratio, productivity, special energy, and net energy gain were reported to be 0.15, 0.01 kg per MJ, 76.28 MJ per kg and 188268 MJ per thousand broilers, respectively. Modeling of energy inputs and the index of energy ratio as the inputs and outputs, respectively, of various ARTIFICIAL NEURAL NETWORKS indicated that the network having two hidden layers with 12 and 9 neurons in the first and second hidden layers, respectively, was the most suitable network for modeling. Results of evaluation of NETWORKS suggested that the values for the R2 and MAPE indices for the 12-9 neuron network were 0.98 and 3.078, respectively, which showed that about 98 percent of the actual data could be estimated with the help of this ARTIFICIAL NEURAL network.

Lozenge rug chaleshtor is in terms of artistic and aesthetic aspects, it is considered one of the consumer and capital goods that have international fame. From the past until now, this native art has been traditionally produced with the same design, pattern, and colour without paying attention to the tastes of its audience, which can be one of the reasons for the failure of this original art in the global rug markets shortly. Therefore, knowledge and awareness of consumers' taste, which is considered as one of the steps before production, and using modern science, can help to produce according to the taste of the audience and, accordingly, to be more successful in terms of sales and providing high export statistics. To achieve this, in this article, sub-branches of ARTIFICIAL intelligence were used to achieve the taste of Lozenge rug chaleshtor audiences. Three algorithms more related to the subject, 1. ARTIFICIAL NEURAL NETWORKS, 2. decision tree learning and 3. support vector machine are compared and finally, the most suitable algorithm for this subject is the ARTIFICIAL NEURAL NETWORKSs for receiving the taste of the audience of the Lozenge rug chaleshtor and providing suitable patterns in the field of design., role, colour, dimensions, texture and price according to the audience's taste, and it was tried to answer the question of whether that ARTIFICIAL NEURAL NETWORKSs can introduce the principles of the audience's taste of lozenge rug chaleshtor. in structural fields. For this purpose, primary data in the field of design and role, colour, raw materials, texture, dyeing, dimensions and price were collected through the contact questionnaire and then, using an ARTIFICIAL NEURAL NETWORKSs, an algorithm was designed, the results showed that traditional lozenge designs with half motifs curved and quiet, with bright, limited, soft colours, natural dyeing, dimensions under 6 meters and preferably square with a price per meter of up to 10 million tomans is the final taste of the audience of this type of rugs.