---

Taq-Bostan Boulevard (Shahid Shiroudi) in Kermanshah city, due to the very rich history and culture of this city, has become one of the most important tourist and recreational destinations. However, the lighting conditions in this boulevard are still not ideal in a way that can add more beauty and charm to the urban space. As a result, the intelligent lighting design of Taq-Bostan Boulevard by using neural network algorithms and providing the appropriate algorithm can improve the lighting and visual conditions of this boulevard, and add more attractiveness to the urban space of Kermanshah city. In this article, first of all, the challenges of lighting sidewalks and implementation points in the design of urban street lighting have been examined. Then, considering the two factors of citizens’ satisfaction and visual beauty as outputs, as well as color temperature, illuminance, lamp type and luminance as model inputs, the MLP neural network algorithm was used for Taq-Bostan Boulevard in Kermanshah. is to design a smart and suitable lighting system for it. The proposed design has the most optimal conditions because the MRE and MAE errors obtained from the neural which is very ideal. Therefore, the designed lighting system ,%0.035 network are less than.aims for the psychological comfort and security of the citizens.

---

It has been demonstrated that anxiety is accompanied by significant warm up in the periorbital area. This warm up was attributed to the increased blood circulation in the area around the eyes. The whole pattern makes physiological and evolutionary sense since it represents a mechanism to facilitate rapid eye movements during preparedness for fight. This increased blood flow dissipates convective heat, which can be monitored through thermal imaging. The evolution of these variables along the timeline and across the 2D space can reveal important clues about anxiety. In this work, we use both facial thermal imaging analysis and poly graph examination to evaluate the effectiveness of thermal imaging in situation of anxiety. The system had been evaluated on six subjects and for each of them four times, each time in two minutes. It operates on the raw temperature signal and tries to improve the information content by suppressing the noise level instead of amplifying the signal as a whole. Finally, a pattern recognition method classifies stressful (deceptive) from non-stressful (non-deceptive) subjects based on a comparative measure between the entire baseline signal and a transient response. The successful classification rate with Multi Layer Perceptron is about 74.7% that is a little better than the LDA method.

---

In this research, the data relating to global land/oceans temperature anomalies and annual mean precipitation of Tabriz station were used for the period of 1951-2005. The main methodologies used in this research include the Pearson correlation coefficient method, analysis of trend component of time series, simple linear and polynomial regression (as a semi-linear model) and Artificial Neural Networks methods. The results of applying Pearson analysis indicated a significant negative and an inverse correlation between global land/oceans temperature anomalies and annual precipitation in Tabriz station. This is an indicative of increase in precipitation and occurrence of wet years during the negative global temperature anomalies and, on contrary, precipitation reduction and occurrence of droughts during the positive global temperature anomalies. The analysis of long term trend components of time series showed that the annual mean precipitation of Tabriz has a decreasing trend towards the length of the period, but annual global land/oceans temperature anomalies has an increasing trend towards the length of the period. Also we simulated the relationships between annual precipitation in Tabriz station and global warming using Artificial Neural Networks. Applying of different methods recognized artificial neural network as a better and more accurate simulation model compared to the other models applied in this research, i.e. simple regression model, and semiـ linear polynomial regression with the power of 6 models. Different artificial neural network methods were used to demonstrate this relation, among which the Multi Layer Perceptron (MLP) with three hidden layers analysis with back propagation learning algorithm showed excellent capability in predicting the correlation between the series.

---

In this paper, the Meshless Local Petrov-Galerkin (MLPG) method is used to analyze the fracture of an isotropic FGM plate. The stress intensity factor of Mode I and Mode II are determined under the influence of various non-homogeneity ratios, crack length and material gradation angle. Both the moving least square (MLS) and the direct method have been applied to estimate the shape function and to impose the essential boundary conditions. The enriched weight function method is used to simulate the displacement and stress field around the crack tip. Normalized stress intensity factors (NDSIF) are calculated using the path independent integral, J*, which is formulated for the non-homogeneous material. The Edge-Cracked FGM plate is considered here and analyzed under the uniform load and uniform fixed grip conditions. To validate results, at first, homogeneous and FGM plate with material gradation along crack length was analyzed and compared with exact solution. Results showed good agreement between MLPG and exact solution.

---

In this paper the meshless local Petrov-Galerkin (MLPG) method is implemented to study the vibration of a Functionally Graded Material (FGM) cylindrical shell. Displacement field equations, based on Donnell and first order shear deformation theory, are taken into consideration. Material properties are assumed to be temperature-dependent and graded in the thickness direction according to different volume fraction functions. A FGM cylindrical shell made up of a mixture of ceramic and metal is considered herein. The set of governing equations of motion are numerically solved by the Meshless method in which a new variational trial-functional is constructed to derive the stiffness and mass matrices so the natural frequencies are obtained in various boundary conditions by using discretization procedure and solving the general eigenvalue problem. The influences of some commonly used boundary conditions, variations of volume fractions and effects of shell geometrical parameters are studied. The results show the convergence characteristics and accuracy of the mentioned method.

---

Detection of tool wear and breakage during machining operations is one of the major problems in control and optimization of the automatic machining process. In this study, the relationship between tool wear with vibration in the two directions, one in the machining direction and the other perpendicular to machining direction was investigated during face milling. For this purpose, a series of experiment were conducted in a vertical milling machine. An indexable sandvik insert and ck45 work piece were used in the experiments. Tool wear was measured by a microscope. It was observed that there was an increase in vibration amplitude with increasing tool wear. In this study adaptive neuro - fuzzy inference systems (ANFIS) and multi-layer perceptron neural network (MLPNN) were implemented for classification of tool wear. In this study for the first time, five different states of tool wear was used for accurate tool wear classification. Also to accuracy and speed of the network Principle Component Analysis (PCA) was implemented. Using PCA, the input matrix size was reduced to an acceptable order causing more efficient networks. ANFIS and MLP were trained using feature vectors extracted from the spectrum frequency and time signals. The results showed that for 86 final measurements, the ANFIS and MLP networks were successful in classifying different tool wear state correctly for 91 and 82 percent, respectively. ANFIS due to its high efficiency in diagnosing tool wear and breakage can be proposed as proper technique for intelligent fault classification.

---

In this study first the meshless local Petrov-Galerkin (MLPG) method by Radial Basis Function (RBF) has been explained entirely. In this way the governing channel flow expression that is based on the Laplace equation is expanded. In MLPG method, the problem domain is represented by a set of arbitrarily distributed nodes and Quadrature radial basis function is used for field function approximation and local integration is used to calculate the integrals. In the following, MLPG method is verified by exact solution in a numerical example. The Results show that MLPG method presented high accuracy and capability for solving the governing equation of the problem. Finally the velocity field is approximated in middle of nodes by RBF (MatLab code was adopted) in the uniform flow in a sloped channel problem. The MLPG results are compared with the isogeometric analysis (IA) method in the tutorial numerical example of Fluid flow modeling in channel, the velocity contours is detected, and their accuracy is demonstrated by means of several examples. The results showed good conformity compared to available analytical solution. The obtain results explain that Application of meshless method in Fluid flow modeling in channel show the applicability and efficiency of the meshless local Petrov-Galerkin method by Radial Basis Function method.

---

The formation of chitosan nanoparticles (CSNPs) with a high stability still remains a main challenge in terms of applying the produced particles in the field of nutraceutical and drug delivery systems. Giving that there are many variables parameters which could affect the size, morphology, and other properties of fabricated CSNPs during ionic gelation process along with using sodium tripolyphosphate (STPP) as the most common cross-linking agent. In this study, after the production of CSNPs under the influence of various independent variables such as chitosan (CS) concentration, STPP concentration, and CS to STPP ratio, in the next step, the physical, rheological, turbidity, and colorimetric properties of the produced nanoparticles were measured. Finally, two artificial neural networks (ANNs) – multilayer perceptron (MLP) and radial basis function (RBF) – with a single hidden layer and different threshold functions, learning algorithms, etc. were employed to predict the CSNPs properties. The results revealed that MLP for the physical, viscosity, b^*, and chroma properties and RBF for other properties – with a Levenberg-Marquardt (LM) learning algorithm of 1000 epochs – well predict them with a very high determination coefficients (R²) and low mean square error (MSE). R² for nanoparticle size, poly dispersity index (PDI), zeta potential, viscosity, and electrical conductivity of CSNPs suspensions were determined 0.9881, 0.9534, 0.9431, 0.9212, and 0.9636, respectively. However, RBF with a single hidden layer comprising a set of 3 inputs, 4 neurons in hidden layer, and 3 outputs with the SigmoidAxon- SigmoidAxon transfer function presented the best results for predicting the L^*, ΔE, and WI properties of CSNPs suspensions. In addition, R² for L^*, ΔE, and WI of CSNPs were calculated 0.9586, 0.9775, and 0.9457, respectively. Also, the flow behavior index of CSNPs suspensions was determined less than 1, which indicates the pseudoplastic behavior of the samples.

---

Abstract This paper presents a neuro-based approach for annual gasoline demand forecast in Iran by taking into account several socio-economic indicators. To analyze the influence of economic and social indicators on the gasoline demand, gross domestic product (GDP), population and the total number of vehicles are selected. This approach is structured as a hierarchical artificial neural network (ANN) based on supervised multi-layer perceptron (MLP), trained with back-propagation (BP) algorithm. This hierarchical ANN is designed properly. The input variables are GDP, population, total number of vehicles and the gasoline demand in the last one year. The output variable is the gasoline demand. The paper proposes a hierarchical network by which the inputs to the ending level are obtained as outputs of the starting levels. Actual Iranian data between 1967 and 2008 were used to test the hierarchical ANN hence; it illustrated the capability of the approach. Comparison of the model predictions with validation data shows validity of the model. Furthermore, the demand for the period between 2011 and 2030 is estimated. It is noticeable that if there will not be any price shock or efficiency improvement in the transportation sector, the gasoline consumption may achieve a threatening level of about 54 billion liters by 2030 in Iran.

---

Three independent models were constructed for the prediction of yields of winter wheat. The models were designed to enable the prediction of yield at three dates: 15th April, 31st May, and 30th June. The models were built using artificial neural networks with MLP (multilayer perceptron) topology, based on meteorological data (air temperature and precipitation) and information on applications of mineral fertilizer. Data were collected in the 2008–2015 from 301 crop fields in the Wielkopolska region of Poland. The evaluation of the quality of predictions made using the neural models was verified by determination of prediction errors using the RAE, RMS, MAE and MAPE measures. An important feature of the constructed predictive models is the ability to make a forecast in the current agricultural year based on up-to-date weather and fertilization information. The lowest MAPE error values were obtained for the neural model WW30_06 (30th June) based on an MLP network with the structure 19:19-15-13-1:1, the error was 8.85%. Sensitivity analysis revealed which factors had the greatest impact on winter wheat yield. The highest rank (1) was obtained by all networks for the same independent variable, namely, the mean air temperature in the period from 1st September to 31st December of the previous year (T9-12_LY).