Sharif Digital Repository

In this study the ability of artificial neural network (ANN) in forecasting the daily NASDAQ stock exchange rate was investigated. Several feed forward ANNs that were trained by the back propagation algorithm have been assessed. The methodology used in this study considered the short-term historical stock prices as well as the day of week as inputs. Daily stock exchange rates of NASDAQ from January 28, 2015 to 18 June, 2015 are used to develop a robust model. First 70 days (January 28 to March 7) are selected as training dataset and the last 29 days are used for testing the model prediction ability. Networks for NASDAQ index prediction for two type of input dataset (four prior days and nine... 

Artificial neural networks with multilayer feed forward topology and back propagation algorithm containing two hidden layers are implemented to predict the effect of chemical composition and tensile properties on the both impact toughness and hardness of microalloyed API X70 line pipe steels. The chemical compositions in the forms of "carbon equivalent based on the International Institute of Welding equation (CEIIW)", "carbon equivalent based on the Ito-Bessyo equation (CEPcm)", "the sum of niobium, vanadium and titanium concentrations (VTiNb)", "the sum of niobium and vanadium concentrations (NbV)" and "the sum of chromium, molybdenum, nickel and copper concentrations (CrMoNiCu)", as well... 

This study is focused on simulating and optimizing design and configuration of anaerobic baffled reactor (ABR) by means of artificial neural network (ANN). This approach is aimed to assess an efficient ABR performance in various operational conditions treating municipal wastewater. For this purpose, to analyze comprehensively on a base of experimental data, the system is operated in two pilots of 48 liters net volume made of 8 compartments. In 7 months, more than 130 sets of data are obtained to be introduced to MATLAB neural network. These include removal efficiency of chemical oxidation demand (COD) and volatile fatty acids (VFAs) parameters. The finest correlative architecture obtained... 

Pressure filters are popular in small municipal water treatment plants. One of the principles for designing and using the various units of water treatment plants is the ability of assigning and predicting the performance of those units under different and various conditions that could be verified by making pilot scale tests and could be modeled by means of available programs and software such as artificial neural network. The goals of this study that was conducted to predict pressure filter efficiency are: (1) evaluations of pressure filter efficiency for turbidity removal under different conditions such as turbidity of raw water, filtration rate and filter pressure changes; (2) statistical... 

Production of highly viscous tar sand bitumen using Steam Assisted Gravity Drainage (SAGD) with a pair of horizontal wells has advantages over conventional steam flooding. This paper explores the use of Artificial Neural Networks (ANNs) as an alternative to the traditional SAGD simulation approach. Feed forward, multi-layered neural network meta-models are trained through the Back-Error-Propagation (BEP) learning algorithm to provide a versatile SAGD forecasting and analysis framework. The constructed neural network architectures are capable of estimating the recovery factors of the SAGD production as an enhanced oil recovery method satisfactorily. Rigorous studies regarding the hybrid... 

The reinforcement of concrete columns with fabric reinforced cementitious matrix (FRCM) is one of the most challenging issues in the construction of concrete structures, as there is still an absence of a promising model to assess their performance. This is because the behavior of such elements is complex and accompanied by a high margin of uncertainty. To address this issue, this study compiles a large dataset of the performance of FRCM-reinforced concrete columns under monotonic load. The obtained dataset is then used to train an artificial neural network (ANN) as a promising method for predicting the compressive strength of concrete columns with acceptable accuracy. Afterward, using a... 

One of the most important requirements for the operation and planning activities of an electrical utility is the prediction of load for the next hour to several days out, known as short term load forecasting (STLF). This paper presents STLF of Iran national power system (INPS) using artificial neural network (ANN). The developed program is based on a four-layered perceptron ANN building block. The optimum inputs were selected for the ANN considering historical data of the INPS. Instead of conventional back propagation (BP) methods, Levenberg-Marquardt BP (LMBP) method has been used for the ANN training to increase the speed of convergence. A data analyzer and a temperature forecaster are... 

In the present study, bainite fraction results of continuous cooling of high strength low alloy steels have been modeled by artificial neural networks. The artificial neural network models were constructed by 16 input parameters including chemical compositions (C, Mn, Nb, Mo, Ti, N, Cu, P, S, Si, Al, V), Nb in solution, austenitizing temperature, initial austenite grain size and cooling rate over the temperature range of the occurrence of phase transformations. The value for the output layer was the bainite fraction. According to the input parameters in feed-forward back-propagation algorithm, the constructed networks were trained, validated and tested. To make a decision on the completion... 

Surface electromyogram (sEMG) signals are extensively used for rehabilitation and control purposes. However due to their intrinsic complexities and intense sensor crosstalk, feature classification and pattern recognition of sEMG signals especially for motion analysis are quite challenging. This study proposes a versatile sEMG Artificial Neural Network based regression approach to evaluate a simple elbow motion with respect to a reference frame. The proposed approach attempts to appropriately interpolate intermediate position angles in an attempt to evaluate and substantiate a continuous motion of the forearm. Results show that based on the proposed algorithm, with a correlation of about 91%... 

The present study investigated a counter-flow cooling tower performance by integrating the Artificial Neural Networks and Intelligent Optimisation Algorithms (ANN-IOAs). For this purpose, two scenarios were evaluated. In the first scenario, inlet air wet-bulb temperature (T aw), inlet air dry bulb temperature (T ad), water to the air mass flow rate ratio (mw /ma), and rotor speed (υ) were the input parameters for the ANNs, while the output temperature (T wo) was the ANNs output. In the second scenario, the same input parameters applied for the first scenario were used as input variables and the tower efficiency (ε) was considered as an output parameter. The well-known IOAs methods, namely,... 

Over the years, accurate prediction of dew-point pressure of gas condensate has been a vital importance in reservoir evaluation. Although various scientists and researchers have proposed correlations for this purpose since 1942, but most of these models fail to provide the desired accuracy in prediction of dew-point pressure. Therefore, further improvement is still needed. The objective of this study is to present an improved artificial neural network (ANN) method to predict dew-point pressures in gas condensate reservoirs. The model was developed and tested using a total set of 562 experimental data point from different gas condensate fluids covering a wide range of variables. After a... 

This paper presents artificial neural network (ANN) meta-models for expensive continuous simulation optimization (SO) with stochastic constraints. These meta-models are used within a sequential experimental design to approximate the objective function and the stochastic constraints. To capture the non-linear nature of the ANN, the SO problem is iteratively approximated via non-linear programming problems whose (near) optimal solutions obtain estimates of the global optima. Following the optimization step, a cutting plane-relaxation scheme is invoked to drop uninformative estimates of the global optima from the experimental design. This approximation is iterated until a terminating condition... 

A precise model of the behavior of complex systems such as solar chimney power plants (SCPP) would be much beneficial. Also, such a model would be quite contributing to the control of solar chimney operation. In this paper, the identification and modeling of SCPP utilizing ANN and Adaptive Neuro Fuzzy Inference System (ANFIS) are discussed. The modeling is based on the data of three working days which were taken of a built pilot in University of Zanjan, Iran. The input parameters are time, radiation and ambient temperature, while the output is the air velocity at the inlet of the chimney. The results of ANN model and ANFIS model were compared; it was found that ANFIS model exhibited better... 

An Artificial Neural Network (ANN) model has been designed for predicting the effects of alloying elements (Fe, Si, Al, Mn) on the recrystallization behavior and microstructural changes of 70/30 brass. The model introduced here considers the content of alloying elements, temperature, and time of recrystallization as inputs while percent of recrystallization is presented as output. It is shown that the designed model is able to predict the effect of alloying elements well. It is also shown that all alloying elements strongly affect the recrytallization kinetics, and all slow down the recrystallization process. The effect of alloying elements on the activation energy for recrystallization has... 

Facial expression imitation with applications in the design of human robot interaction (HRI) systems is an active area of research. In this study, we propose an approach for real-time imitation of human facial expression by a humanoid social robot 'Alice'. Artificial neural network (ANN) and Kinect sensor are used for recognition and classifying of the facial expressions like happiness, sadness, fear, anger and surprise; with the Alice humanoid robot imitating the comprehended expressions. Results and experiments demonstrate the effectiveness of the approach. © 2016 IEEE  

In this study, the artificial neural network (ANN) and the Taguchi method are employed to optimize the radial force and strain inhomogeneity in radial forging process. The finite element analysis of the process verified by the microhardness test (to confirm the predicted strain distribution) and the experimental forging load published by the previous researcher are used to predict the strain distribution in the final product and the radial force. At first, a combination of process parameters are selected by orthogonal array for numerical experimenting by Taguchi method and then simulated by FEM. Then the optimum conditions are predicted via the Taguchi method. After that, by using the FEM... 

Lack of robust techniques for optimization of hybrid separation systems is obvious in the literature. A novel hybrid approach for modeling and optimization of a hybrid process consisting of fixed-bed adsorption column (FBAC) and dead-end filtration (DEF) for the removal of methylene blue from water was presented. Artificial neural network (ANN), response surface methodology (RSM) and genetic algorithm (GA) were used for this purpose. ANN was employed to successfully approximate the breakthrough curves. Central composite design was used to investigate the impact of the operating variables, i.e. feed flowrate, initial concentration, adsorption bed length, and filter type on the removal rate as... 

In this study, new method for NAA purposes at 30 kW Isfahan MNSR is suggested. An algorithm based on ANN is proposed to quantitatively predict the unknown elements with no need standard sample. A three-layer feed-forward ANN with back-propagation algorithm has been used to determine concentration of selenium and fluorine in Multiple Sclerosis patients and healthy people blood samples. Predicted concentration of elements show good agreement between new method and experiment results. The correlation coefficient between the experimentally determined and predicted values are 0.99104 and 0.99364, respectively. This method is a rapid and precise approach for elemental analysis. © 2022, Akadémiai... 

This study focuses on the spectrochemical estimation of pH and titratable acidity (TA) of apples of Fuji variety at different stages of ripening. A novel approach is proposed for near-infrared (NIR) spectral analysis using hybrid machine learning methods that combine artificial neural networks (ANN) and metaheuristic algorithms. One hundred twenty samples were collected at three ripening stages and spectral data within two bands of NIR were extracted from each sample to predict the acidity properties. Alternatively, the 4 most effective wavelengths were also selected using a hybrid of ANN and the cultural algorithm. The experimental results prove that the models using spectral bands and the... 

Biosensors could be used as digital devices to measure the sample infield. Consequently, computational programming along with experimental achievements are required. In this study, a novel biosensor/artificial neural network (ANN) integrated system was developed. Poly (3,4-ethylenedioxy-thiophene)(PEDOT), graphene oxide nano-sheets (GONs) and laccase (Lac) were used to construct a biosensor. The simple and one-pot process was accomplished by electropolymerizing 3,4-ethylenedioxy-thiophene (EDOT) along with GONs and Lac as dopants on glassy carbon electrode. Scanning electron microscopy (SEM) and electrochemical characterization were conducted to confirm successful enzyme entrapment. The...