Multilayer Feed-forward Back-propagation Research Articles

Smart solutions for dissolved oxygen control in semi-batch fermenters: A machine learning approach

The monitoring and measurement of dissolved oxygen (DO), plays a significant role in industrial effluent, and disposal of effluents has been a serious challenge to researchers. Aeration is the primary step in effluent treatment. The basic method for determining DO is direct measurement. This study has been carried out in effluent from the paper industry to estimate the performance of dissolved oxygen in a semi-batch lark hygiene fermenter and was oxygenated till saturation at 25 °C under real-time study. This study has been carried out using Multi-Layered Feed Forward Back Propagation Artificial Neural Network (ML-FFBPANN) and the experimental results were optimized with fourteen different machine learning algorithms such as Polak-Ribiere Conjugate Gradient (CGP), Conjugate Gradient with Powell/Beale Restarts (CGB), Bayesian Regularization (BR), Gradient Descent (GD), BFGS Quasi-Newton (BFG), GD with Momentum (GDM), Gaussian Discriminate Analysis(GDA), Fletcher-Powell Conjugate Gradient (CGF), Resilient Backpropagation (RP), Variable Learning Rate Gradient Descent (GDX), One Step Secant (OSS), Regression (R), Levenberg-Marquardt (LM), Scaled Conjugate Gradient(SCG). Parameters Root Mean Squared Error (RMSE) and the correlation coefficient (R-square) were used to evaluate the performance of each model and mathematical modeling for correlation co-efficient of all algorithms are also presented. LM and R are the best algorithms but the ML-FFBPANN-LM algorithm provided the best optimization results of maximum correlation co-efficient. LM algorithm produced a maximum correlation coefficient under training (0.99818), testing (0.99351), valediction (1.0), and an overall correlation coefficient be 0.9568. From the study, it can be concluded that the ML-FFBPANN with LM algorithm can be used in the aeration process in effluent treatment for analysis and prediction of process parameters.

An artificial neural network for predicting air traffic demand based on socio-economic parameters

Over the past five years, emerging economies have consistently progressed toward achieving greater economic independence. The aviation industry has played a significant role in driving this progress. Accurately forecasting the future demand for air travel is crucial for making long-term commitments to these economies. The findings of this study provide valuable insights into the provision of low-cost passenger carrier demand. They can assist low-cost carriers, airports, airport consultants, and government agencies in their strategic planning and development processes. The primary objective of this study is to identify and evaluate artificial intelligence-based solutions, specifically, Artificial Neural Networks (ANN), to determine the most effective model for projecting domestic demand for low-cost carriers. The study analyzes nine variables that impact the accuracy of predicting domestic air passenger demand in emerging countries using a Multilayer Feed-Forward Backpropagation Neural (MFFBPN) network. The performance of the developed ANN model for predicting air passenger demand is assessed through training, validation, and testing using 240 data sets. The evaluation metrics employed, including mean square error (MSE), root mean square error (RMSE), accuracy, precision, sensitivity, and specificity, indicate the effectiveness of the developed ANN model, with results of 0.0019 for MSE, 0.0440 for RMSE, 0.92 for accuracy, 0.92 for precision, 0.93 for sensitivity, and 0.95 for specificity. We show that modeling based on artificial intelligence approaches and ANN is more effective than conventional linear regression models.

Electric Vehicle NiMH Battery State of Charge Estimation Using Artificial Neural Networks of Backpropagation and Radial Basis

The state of charge of a battery depends on many magnitudes, but only voltage and intensity are included in mathematical equations because other variables are complex to integrate into. The contribution of this work was to obtain a model to determine the state of charge with these complex variables. This method was developed considering four models, the multilayer feed-forward backpropagation models of two and three input variables used supervised training, with the variable-learning-rate backpropagation training function, five and seven neurons in the hidden layer, respectively, achieving an optimal training. Meanwhile, the radial basis neural network models of two and three input variables were trained with the hybrid method, the propagation constant with a value of 1 and 80 neurons in the hidden layer. As a result, the radial basis neural network with the variable-learning-rate training function, considering the discharge temperature, was the one with the best performance, with a correlation coefficient of 0.99182 and a confidence interval of 95% (0.98849; 0.99516). It is then concluded that artificial neural networks have high performance when modeling nonlinear systems, whose parameters are difficult to measure with time variation, so estimating them in formulas where they are omitted is no longer necessary, which means an accurate SOC.

Experimental Study for Thermophysical Properties of ZrO2/Ethylene Glycol Nanofluid: Developing an ANFIS Modeling and Proposing New Correlations

Nanofluids are potential coolants for heat transfer applications because of their excellent thermal characteristics. Experimentally the thermophysical properties of ZrO2/ethylene glycol nanofluids are determined at 0.2%, 0.4%, 0.6%, 0.8%, and 1.0% vol. concentrations. A two-step method is used to prepare the stable nanofluids. The ZrO2/EG nanofluids properties were estimated over temperature ranging from 20 °C to 60 °C. From the experimental data, a multi-layer perceptron feed-forward back propagation artificial neural network was developed. Additionally, new correlations were proposed for all the thermophysical properties. The experimental analysis showed that thermal conductivity is enhanced by 19.6% at 60 °C and viscosity is enhanced by 86.62% at 20 °C at 1.0% vol. of nanofluid, density is enhanced by 4.9%, and specific heat is decreased by 4.2% at 1.0% vol. of nanofluid and at 60 °C, over base fluid data. The proposed ANN model succeeded in predicting the target property with minimum RMSE. The results of the developed artificial neural network and its correlation analysis perfectly agree with the experimental data.

Artificial neural network model for strength predictions of CFST columns strengthened with CFRP

This paper presents an optimised Artificial Neural Network (ANN) model for predicting the ultimate axial strengths of concentrically loaded Concrete-Filled Steel Tubular (CFST) short and slender columns strengthened with Carbon Fibre-Reinforced Polymer (CFRP). Since experimental data on CFRP strengthened CFST columns is limited, an accurate Finite Element (FE) model is developed and used to provide additional numerical data. A multi-layered feed-forward back-propagation network is proposed, optimised, and trained using the results of 76 experimental tests and 450 generated FE models. The accuracy of the ANN model is assessed through comparing its computed results with experimental data. A reliability analysis is performed using Monte Carlo Simulation (MCS) to evaluate the safety of the solutions computed by the ANN model. ANN-based equations and Graphical User Interface (GUI) are developed based on the trained ANN model for the determination of the ultimate axial strengths of CFST columns. The results show that the developed ANN model is capable of accurately predicting the ultimate axial strengths of CFRP strengthened CFST columns with a high degree of accuracy.

Welding sequence optimization to reduce welding distortion based on coupled artificial neural network and swarm intelligence algorithm

This study aims to develop a welding sequence optimization (WSO) framework based on coupled artificial neural network (ANN) and swarm intelligence algorithm for minimizing welding distortion of thin-walled squared Al–Mg–Si alloy tube components. This framework is mainly composed of two critical computer programs. Firstly, a multilayer feedforward backpropagation neural network (BPNN) system was established to rapidly estimate residual distortion for an arbitrary welding sequence so that welding sequence can be optimized for achieving desired welding quality. For this purpose, a series of nonlinear thermo-elastic–plastic finite element (FE) simulations were conducted and verified with experiments to generate the input database of the neural network. Subsequently, a reliable BPNN model was successfully created and trained within an acceptable error. Secondly, a novel swarm intelligence algorithm, namely, bees algorithm (BA) was proposed to solve the complicated WSO problems. In this optimization process, the trained BPNN model was implanted into this proposed BA for computing the fitness value of arbitrary welding sequences. Moreover, welding experiments were also performed to confirm the performance of the proposed optimization method. Comparing the results from experimental measurements, FE simulations, and proposed WSO framework, it is demonstrated that this proposed BPNN-and-BA-based WSO framework can be successfully applied in practical engineering to obtain an optimal welding sequence for minimizing final welding distortion.

Artificial neural networks (ANNs) for modeling efficient factors in predicting pap smear screening behavior change stage.

Background and objectivesCervical cancer is ranked as the third most prevalent cancer that affects women all over the world and Pap smear seems to be the single most critical intervention to prevent cervical cancer. In the present study, the effects of demographic factors (age, education level, job, income level, marriage age, pregnancy, child number, breastfeeding, and menopause), insurance type, disease history and screening (sono and mammography, breast problem) and cancer information on Pap smear screening and behavior stage of change were investigated and modeled using an artificial neural network model (ANN).Materials and methodsData were collected from a descriptive-analytical cross-sectional study. This research was conducted on 1898 female employees of governmental agencies of Birjand, a city located in the east of Iran. The questionnaire consisted of four parts (socioeconomic, reproductive characteristics, information about cervical cancer screening, and stage of change for cervical cancer screening). Multilayer feed-forward back-propagation neural networks were used to detect the patterns between variables using a neural network with 14 inputs and one output. To find out the neural network with the minimum sum of squared errors, we evaluated the performance of all neural networks using varying algorithms and numbers of neurons in the hidden layer. For this purpose, the data collected from 1898 women were analyzed using SPSS-22 software.ResultsIn the optimal ANN model, the variables of marriage age, age, breastfeeding, and the number of children were identified as the most significant factors with 18.3, 16.3, 7.3, and 7.3 percent, respectively, whereas the history of cancer, job, pregnancy, and menopause had importance of lower than 5 percent.ConclusionOur findings showed that among many associated variables, the marriage age, age, breastfeeding, and the number of children were the most important predictors for the behavioral stage of change. Thus, it seems, focusing on these factors may lead to the adoption of effective programs and policies to improve cervical cancer screening practices in women.

Applying artificial neural-network model to predict psychiatric symptoms.

IntroductionMental disorders result in mental disabilities and discomfort in the affected person as they affect both thinking and behavior. Therefore, more vulnerable people must first be identified to improve the psychological level of society.AimThis study aims to determine the importance of gender, employment, education, place of residence, and age in predicting mental disorders using artificial neural network modeling.MethodsThe pattern held between variables in this study will be identified using multilayer feed-forward back-propagation neural networks with five inputs and 10 outputs. To determine the neural network with the least sum of square errors, we evaluated the performance of all neural networks with varying algorithms and different numbers of neurons in the hidden layer. Data were analyzed for 380 people aged 10–82 years using the SPSS software.ResultsThe optimal neural network model was effective in predicting mental disorders. In this model, the variables of the place of residence, education, age, gender, and employment were important in fitting the optimal model with 34.08, 20.11, 18.93, 14.55, and 12.33%, respectively. The accuracy rate for the neural network model was 99.2%.ConclusionTo achieve further results in improving mental health problems, it is better to focus more on employed, rural, and younger people with a non-tertiary education level.

Forecasting of Electrical Energy Consumption in Slovakia

Prediction of electricity energy consumption plays a crucial role in the electric power industry. Accurate forecasting is essential for electricity supply policies. A characteristic feature of electrical energy is the need to ensure a constant balance between consumption and electricity production, whereas electricity cannot be stored in significant quantities, nor is it easy to transport. Electricity consumption generally has a stochastic behavior that makes it hard to predict. The main goal of this study is to propose the forecasting models to predict the maximum hourly electricity consumption per day that is more accurate than the official load prediction of the Slovak Distribution Company. Different models are proposed and compared. The first model group is based on the transverse set of Grey models and Nonlinear Grey Bernoulli models and the second approach is based on a multi-layer feed-forward back-propagation network. Moreover, a new potential hybrid model combining these different approaches is used to forecast the maximum hourly electricity consumption per day. Various performance metrics are adopted to evaluate the performance and effectiveness of models. All the proposed models achieved more accurate predictions than the official load prediction, while the hybrid model offered the best results according to performance metrics and supported the legitimacy of this research.

Artificial neural networks for developing early warning system for banking system: Indian context

This study attempts to develop an early warning system for the Indian banking sector using artificial neural networks (ANNs) by considering important economic variables based on detailed literature review. It takes into account an Elman recurrent neural network and a multilayered feedforward backpropagation network (MLFN). The ANNs are evaluated based on their accuracy and calibration using quadratic probability score (QPS) and global squared bias (GSB) for both within the sample and out of the sample. The scores depict results with Elman recurrent network outperforming the MLFN. The uniqueness of this study lies in using and identifying pertinent macroeconomic variables to anticipate the banking sector fragility for the Indian economy using sequential feature selection algorithms. The ANN models are found to be appropriate and useful for policy planners to foresee the possibility of the occurrence of banking fragility and take proactive corrective measures to minimise and safeguard the economy from adverse implications of banking crisis.

Prediction of ground subsidence due to underground mining through time using multilayer feed-forward artificial neural networks and back-propagation algorithm – case study at Mong Duong underground coal mine (Vietnam)

The paper is devoted to studying the possibility of using artificial neural networks (ANN) to estimate ground subsidence caused by underground mining. The experiments showed that the most suitable network structure is a network with three layers of perceptrons and four neurons in the hidden layer with the back propagation algorithm (BP) as a training algorithm. The subsidence observation data in the Mong Duong underground coal mine and other parameters, including: (1) the distance from the centre of the stope to the ground monitoring points; (2) the volume of mined-out space; (3) the positions of the ground points in the direction of the main cross-section of the trough; and (4) the time (presented by cycle number), were used as the input data for the ANN. The findings showed that the selected model was suitable for predicting subsidence along the main profile within the subsidence trough. The prediction accuracy depended on the number of cycles used for the network training as well as the time interval between the predicted cycle and the last cycle in the training dataset. When the number of monitoring cycles used for the network training was greater than eight, the largest values of RMS and MAE were less than 10 % compared to the actual maximum subsidence value for each cycle. If the network training was less than eight cycles, the results of prediction did not meet the accuracy requirements.

Using artificial neural network and non‐destructive test for crack detection in concrete surrounding the embedded steel reinforcement

AbstractBond between steel and concrete is one of the key aspects of structural design and its performance evaluation. In the past much research work has been focused on understanding bond deterioration owing to corrosion of reinforcement, however, there exists no nondestructive method to access the bond condition. In this regard, the presented experimental research work details the development of a nondestructive testing method to estimate the crack condition of concrete surrounding the steel reinforced by using ultrasonic pulse velocity test. In addition, a multilayer feedforward back propagation perceptron artificial neural network (ANN) is developed in order to avoid simplification assumptions for developing models to predict the cracking, owing to the nonlinear complex stress distribution at the steel‐concrete interface. The ANN is used to predict the crack width and to conduct sensitivity analysis of the various factors influencing the bond deterioration. A high accuracy level is achieved between the predicted and the experimental values with R2 of 0.97 and the most influential parameter is highlighted.

Prediction of Infection and Death Ratio of COVID-19 Virus in Turkey by Using Artificial Neural Network (ANN)

Background: For the first time in December 2019, as reported in the Wuhan city of China, COVID-19 deadly virus spread rapidly around the world and the first cases were seen in Turkey on March 11, 2020. On the same day, a pandemic was declared by the World Health Organization due to the rapid spread of the disease throughout the world. Methods: In this study, a multilayered perception feed-forward back propagation neural network has been designed for predicting the spread and mortality rate of the COVID-19 virus in Turkey. COVID-19 data from six different countries were used in the design of the artificial neural network, which has 15 neurons in its hidden layer. 70% of these optimized data were used for training, 20% for validation, and 10% for testing. Results: The simulation results showed that the COVID-19 virus in Turkey, between day 20 and 37, was the fastest to rise. The number of cases for the 20th day was predicted to be 13.845. Conclusion: As for the death rate, it was predicted that a rapid rise would start on the 20th day and a slowdown around the 43rd day and progress towards the zero case point. The death rate for the 20th day was predicted to be 170 and for the 43rd day it was 1,960s.

Gasification of food waste in supercritical water: An innovative synthesis gas composition prediction model based on Artificial Neural Networks

The present study intends to develop multi-layered feed-forward back-propagation algorithm based artificial neural network (FFBPNN) models to predict the synthesis gas (SG) compositions (H2, CH4, CO & CO2) and yields (mol/kg) for supercritical water gasification (SCWG) of food wastes. Such models are trained with Levenberg-Marquardt (L-M) algorithm, minimized using gradient descent approach and tested with real-time experimental datasets obtained from literature. Moreover, to determine an optimal form of the neural network for a typical non-catalytic SCWG process, a trial and error approach involving multiple combinations of transfer functions and neurons in the network layers is performed. The predicted values of SG compositions yield delivered by the FFBPNN models are in line with the experimental datasets converging to a mean squared error (MSE) value below 0.300 range and coefficient of determination (R2) above 98%. Best prediction accuracy is achieved for CO yield prediction characterized by a least MSE of 0.022 and highest train-test R2 of 0.9942–0.9939. The performance of the developed FFBPNN models can be arranged on the basis of MSE as (ann7)CO < (ann6)CH₄ < (ann5)H₂ < (ann8)CO₂ and on the basis of testing R2 as (ann7)CO > (ann6)CH₄ > (ann5)H₂ > (ann8)CO₂.

Retraction Note To: Artificial neural network to predict the effect of heat treatments on Vickers microhardness of low-carbon Nb microalloyed steels

In the present study, an artificial neural networks-based model (ANNs) was developed to predict the Vickers microhardness of low-carbon Nb microalloyed steels. Fourteen parameters affecting the Vickers microhardness were considered as inputs, including the austenitizing temperature, cooling rate, initial austenite grain size, different chemical compositions and Nb in solution. The network was then trained to predict the Vickers microhardness amounts as outputs. A Multilayer feed-forward back-propagation network was developed and trained using experimental data form literatures. Five low-carbon Nb microalloyed steels and one low-carbon steel without Nb were investigated. The effects of austenitizing temperature (900–1,100°C) and subsequent cooling rate (0.15–227°C/s) and initial austenite grain size (5–130 μm) on the Vickers microhardness of steels were modeled by ANNs as well. The predicted values are in very good agreement with the measured ones, indicating that the developed model is very accurate and has the great ability for predicting the Vickers microhardness.

A novel comparative analysis between the experimental and numeric methods on viscosity of zirconium oxide nanofluid: Developing optimal artificial neural network and new mathematical model

In this study, the viscosity of five different ZrO2/Water nanofluids of 0.0125%, 0.025%, 0.05%, 0.1% and 0.2% prepared by the two-step method were experimentally investigated. Using the experimental data obtained, a multi-layer perceptron feed-forward back-propagation artificial neural network and a new mathematical correlation have been developed in order to predict the viscosity of ZrO2/Water nanofluid. Experimental results revealed that viscosity decreases with increasing temperature and increases with increasing concentration. The outputs obtained from the developed artificial neural network and the new correlation were compared with the experimental results and analyzed. The results show that the developed artificial neural network can predict the viscosity of ZrO2/Water nanofluid with an average error rate of −0.11%. The new mathematical model developed has been able to calculate the viscosity of ZrO2/Water nanofluid with an error rate of −0.74%.

Wear volume prediction of AISI H13 die steel using response surface methodology and artificial neural network

Resistance to wear of hot die steel is dependent on its mechanical properties governed by the microstructure. The required properties for given application of hot die steel can be obtained with control the microstructure by heat treatment parameters. In the present paper impact of different heat treatment parameters like austenitizing temperature, tempering time, tempering temperature is studied using response surface methodology (RSM) and artificial neural network (ANN) to predict sliding wear of H13 hot die steel. After heat treating samples at austenitizing temperature of 1020°C, 1040°C and 1060°C; tempering temperature 540°C, 560°C and 580°C; tempering time 1hour, 2hours and 3hours, experimentation on pin-on-disc tribo-tester is done to measure the sliding wear of H13 die steel. Box-Behnken design is used to develop a regression model and analysis of variance technique is used to verify the adequacy of developed model in case of RSM. Whereas, multi-layer feed-forward backpropagation architecture with input layer, single hidden layer and an output layer is used in ANN. It was found that ANN proves to be a better tool to predict sliding wear with more accuracy. Correlation coefficient R2 of the artificial neural network model is 0.986 compared to R2 of 0.957 for RSM. However, impact of input parameter interactions can only be analysed using response surface method. In addition, sensitivity analysis is done to determine the heat treatment parameter exerting most influence on the wear resistance of H13 hot die steel and it showed that tempering time has maximum influence on wear volume, followed by tempering temperature and austenitizing temperature. The prediction models will help to estimate the variation in die lifetime by finding the amount of wear that will occur during use of hot die steel, if the heat treatment parameters are varied to achieve different properties.

Remote Sensing of Time-Varying Tidal Flat Topography, Jiangsu Coast, China, Based on the Waterline Method and an Artificial Neural Network Model

Measurement of beach heights in the intertidal zone has great importance for dynamic geomorphology research, coastal zone management, and the protection of ecological resources. Based on satellite images, the waterline method based on satellite images is one of the most effective methods for constructing digital elevation models (DEMs) for large-scale tidal flats. However, for fast-changing areas, such as Tiaozini in the Jiangsu coast, timely and detailed topographical data are difficult to obtain due to the insufficient images over a short period of time. In this study, as a supplement to the waterline method, an artificial neural network (ANN) model with the multi-layer feed-forward back propagation algorithm was developed to simulate the topography of variable Tiaozini tidal flats. The “7-15-15-1” double hidden layers with optimized training structures were confirmed via continuous training and comparisons. The input parameters included spectral bands (HJ-1 images B1~B4), geographical coordinates (X, Y), and the distance (D) to waterlines, and the output parameter was the elevation. The model training data were the HJ-1 image for 21 March 2014, and the corresponding topographic data obtained from the waterline method. Then, this ANN model was used to simulate synchronous DEMs corresponding to remote sensing images on 11 February 2012, and 11 July 2013, under low tide conditions. The height accuracy (root mean square error) of the two DEMs was about 0.3–0.4 m based on three transects of the in-situ measured data, and the horizontal accuracy was 30 m—the same as the spatial resolution of the HJ-1 image. Although its vertical accuracy is not very high, this ANN model can quickly provide the basic geomorphological framework for tidal flats based on only one image. This model, therefore, provides an effective way to monitor rapidly changing tidal flats.

Design and Implementation of Intelligent Hybrid Neuro Controller for Automatic Voltage Regulator

In this paper, we presented a hybrid controller by combining the advantages of both PID and Neuro controllers for automatic voltage regulator (AVR) system. A Neuro controller is designed using multilayer feedforward neural network and Levenberg-Marquardt backpropagation algorithm is used for training the network. Also, hybrid controller is achieved by blending the characteristics of classical PID and proposed Neuro controller using a switching mechanism based on the error. The proposed PID, Neuro and Hybrid controllers are simulated in MATLAB environment and their transient response parameters are compared. The simulation results clearly indicated the improvement in the transient output of the automatic voltage regulator system with proposed hybrid controller even in the presence of uncertainties in the system.

Critical evaluation and comparison of psychoacoustics, acoustics and vibration features for gear fault correlation and classification

Gear fault diagnosis has gained importance in the last few decades with the focus of fault diagnosis function for maintenance purpose. This paper investigates the ability of various vibration, acoustics and psychoacoustic features to correlate and classify faults in the gearbox. This study is motivated by the process of gearbox fault diagnosis at the end of the assembly line inspection of gearbox. It is observed that during the end of assembly line inspection, the gearbox is operated on a test bench and operator takes a decision about the presence of fault by listening to the sound emitted by the gearbox. This decision is based on an operator’s judgement and past experience which involves subjectivity. Efforts are made to address this issue of end of the line inspection, by applying a scientific, objective psychoacoustic based technique which works on similar principles of listening. Experiments are performed in a laboratory by simulating four types of gear faults and vibration and acoustic signals are acquired to extract statistical features of vibration and acoustic signal along with psychoacoustic features. It is observed that different features respond to faults in different ways and changes in feature values are also dependent on loading condition. Therefore, correlating these features with faults is not simple and need intelligent techniques for correlating faults to features. This correlation of faults to features is attempted with different techniques like ANN and discriminant classifier. It is found that the psychoacoustic features have better ability to classify faults compared to acoustics and vibration statistical features which are found to be 93.02% using quadratic discriminant classifier and 95.93% using multilayer feed-forward back-propagation neural network. It is shown that the psychoacoustic based fault identification technique can be applied for the end of the assembly line inspection of gearbox.