Backpropagation Training Algorithm Research Articles

A Comprehensive Overview on Performance of Cascaded Three Tank Level System using Neural Network Predictive Controller

A Neural Network Predictive Controller (NNPC) is a deep learning-based controller (DLC) that uses artificial neural networks (ANN) to predict the future behavior of a system and accordingly control its outputs. In this paper, an NNPC was used to predict the level of the three cascaded tank and then adjust the inputs as flow rate to maintain the desired level in the tank. A three-tank level system is a system consisting of three interconnected tanks used to store liquids. To achieve the desired level, the NNPC first collects data on system behavior, including inputs and outputs, and uses this data to train the neural network. The trained network was then used to make predictions about the future level of each tank and to generate control signals to adjust the inputs as needed. NNPC also incorporates feedback from the system to continuously refine its predictions and improve its control performance over time. The mean squared error (MSE) of different backpropagation training algorithms available in MATLAB deep learning toolbox were evaluated and presented. Based on the MSE and best validation, Levenberg Marquardt algorithm were used in NNPC controller for further step response tracking. Different performance metrics were evaluated and presented.

Estimation of wheel slip in 2WD mode for an agricultural tractor during plowing operation using an artificial neural network

As artificial neural networks (ANNs) have been shown to be precise and reliable in supporting the field of artificial intelligence technology, agricultural scientists have focused on employing ANN for agricultural applications. The ANN can be an effective alternative for evaluating agricultural operations. The intended aim of this investigation was to employ both ANN and multiple linear regression (MLR) to develop a model for determining the rear wheel slip of an agricultural tractor in two-wheel drive (2WD) mode during plowing operations. The output parameter of the models was tractor rear wheel slip. The training data were collected from filed experiments using chisel, moldboard, and disk plows. The plows were operated under different conditions of soil texture, plowing depth, soil moisture content, and plowing speed. All data were acquired during field experiments in two soil textures (clay and clay loam textures). The training dataset was comprised of 319 data points, while 65 data points were employed to test both ANN and MLR models estimation capability. The ANN model with a backpropagation training algorithm was created using the commercial Qnet2000 software by changing its topology and related parameters. The best ANN model possessed a topology of 7-20-1. The estimated tractor rear wheel slip using the testing dataset displayed strong agreement with measured tractor rear wheel slip with the coefficient of determination (R2) value of 0.9977. The results definitely illustrated that the ANN model was capable of defining the correlation between the inputs and rear wheel slip. The outcomes suggest that the established ANN model is trustworthy in predicting the tractor rear wheel slip for an agricultural tractor in 2WD mode during the tillage process compared to MLR models. This study provides a useful tool for management of tillage implements during field operations.

Machine learning algorithms in wood ash-cement-Nano TiO2-based mortar subjected to elevated temperatures

Mortar is subjected to high temperatures during fire attacks or when it is near heat-radiating equipment like furnaces and reactors. The physical and microstructure of mortar were considerably altered by high temperatures. In this investigation, the effects of elevated temperatures on the flexural and compressive strengths of wood ash (WA) cement mortar modified with green-synthesised Nano titanium oxide (NT) were examined. In order to produce mortar samples, the cement was replaced with 10% WA, and 1–3% NT by weight of binder were added at constant water-binder ratio. The specimens were heated to 105, 200, 400, 600, and 800 °C with an incremental rate of 10 °C per min in the electric furnace for a sustained period of 2 h to measure their strengths. The machine learning algorithm of artificial neural networks with Levenberg-Marquardt backpropagation training techniques of different network architectures was engaged to predict the compressive strength of WA-cement-NT-based mortar produced. The findings showed that higher temperatures reduced compressive strength after 400 °C and flexural strength after 200 °C. The mortar specimen with a 3% NT addition showed the highest residual compressive strength increase, ranging from 18.75 to 27.38%. Compared to compressive strength, flexural strength is more severely affected by high temperatures. The backpropagation training algorithm revealed that each hidden layer displayed its unique strong prediction. However, Levenberg-Marquardt backpropagation training technique of 7–10-10-1 network structures yielded the best performance metrics for training, validation, and testing compared to 7-10-10-10 and 7-10-1 network architectures.

Evaluation of the PSO Metaheuristic Algorithm in Different Types of Sleep Apnea Diagnosis Using RR Intervals

Sleep apnea is one of the most common sleep disorders that facilitating and accelerating its diagnosis will have positive results on its future trend. This study aimed to diagnosis the sleep apnea types using the optimized neural network. This descriptive-analytical study was done on 50 cases of patients referred to the sleep clinic of Imam Khomeini Hospital in Tehran, including 11 normal, 13 mild, 17 moderate and 9 severe cases. At the first, the data were pre-processed in three stages, then The Electrocardiogram (ECG) signal was decomposed to 8 levels using wavelet transform convert and 6 nonlinear features for the coefficients of this level and 10 features were calculated for RR Intervals. For apnea categorizing classes, the multilayer perceptron neural network was used with the backpropagation algorithm. For optimizing Multi-layered Perceptron (MLP) weights, the Particle Swarm Optimization (PSO) evolutionary optimization algorithm was used. The simulation results show that the accuracy criterion in the MLP network is allied with the Backpropagation (BP) training algorithm for different types of apnea. By optimizing the weights in the MLP network structure, the accuracy criterion for modes normal, obstructive, central, mixed was obtained %96.86, %97.48, %96.23, and %96.44, respectively. These values indicate the strength of the evolutionary algorithm in improving the evaluation criteria and network accuracy. Due to the growth of knowledge and the complexity of medical decisions in the diagnosis of the disease, the use of artificial neural network algorithms can be useful to support this decision.

Bacterial Foraging Algorithm for a Neural Network Learning Improvement in an Automatic Generation Controller

The frequency diversion in hybrid power systems is a major challenge due to the unpredictable power generation of renewable energies. An automatic generation controller (AGC) system is utilised in a hybrid power system to correct the frequency when the power generation of renewable energies and consumers’ load demand are changing rapidly. While a neural network (NN) model based on a back-propagation (BP) training algorithm is commonly used to design AGCs, it requires a complicated training methodology and a longer processing time. In this paper, a bacterial foraging algorithm (BF) was employed to enhance the learning of the NN model for AGCs based on adequately identifying the initial weights of the model. Hence, the training error of the NN model was addressed quickly when it was compared with the traditional NN model, resulting in an accurate signal prediction. To assess the proposed AGC, a power system with a photovoltaic (PV) generation test model was designed using MATLAB/Simulink. The outcomes of this research demonstrate that the AGC of the BF-NN-based model was effective in correcting the frequency of the hybrid power system and minimising its overshoot under various conditions. The BP-NN was compared to a PID, showing that the former achieved the lowest standard transit time of 5.20 s under the mismatching power conditions of load disturbance and PV power generation fluctuation.

Modeling of methylene blue removal on Fe3O4 modified activated carbon with artificial neural network (ANN)

In this study, AC/Fe3O4 adsorbent was first synthesized by modifying activated carbon with Fe3O4. The structure of the adsorbent was then characterized using analysis techniques specific surface area (BET), Scanning Electron Microscopy with Energy Dispersive X-ray Spectroscopy (SEM-EDX), and Fourier Transform Infrared Spectroscopy (FTIR). Equilibrium, thermodynamic and kinetic studies were carried out on the removal of methylene blue (MB) dyestuff from aqueous solutions AC/Fe3O4 adsorbent. The Langmuir maximum adsorption capacity of AC/Fe3O4 was 312.8 mg g−1, and the best fitness was observed with the pseudo-second-order kinetics model, with an endothermic adsorption process. In the final stage of the study, the adsorption process of MB on AC/Fe3O4 was modeled using artificial neural network modeling (ANN). Considering the smallest mean square error (MSE), The backpropagation neural network was configured as a three-layer ANN with a tangent sigmoid transfer function (Tansig) at the hidden layer with 10 neurons, linear transfer function (Purelin) the at output layer and Levenberg-Marquardt backpropagation training algorithm (LMA). Input parameters included initial solution pH (2.0–9.0), amount (0.05–0.5 g L−1), temperature (298–318 K), contact time (5–180 min), and concentration (50–500 mg L−1). The effect of each parameter on the removal and adsorption percentages was evaluated. The performance of the ANN model was adjusted by changing parameters such as the number of neurons in the middle layer, the number of inputs, and the learning coefficient. The mean absolute percentage error (MAPE) was used to evaluate the model’s accuracy for the removal and adsorption percentage output parameters. The absolute fraction of variance (R 2) values were 99.83, 99.36, and 98.26% for the dyestuff training, validation, and test sets, respectively.

Hadamard product-based in-memory computing design for floating point neural network training

Deep neural networks (DNNs) are one of the key fields of machine learning. It requires considerable computational resources for cognitive tasks. As a novel technology to perform computing inside/near memory units, in-memory computing (IMC) significantly improves computing efficiency by reducing the need for repetitive data transfer between the processing and memory units. However, prior IMC designs mainly focus on the acceleration for DNN inference. DNN training with the IMC hardware has rarely been proposed. The challenges lie in the requirement of DNN training for high precision (e.g. floating point (FP)) and various operations of tensors (e.g. inner and outer products). These challenges call for the IMC design with new features. This paper proposes a novel Hadamard product-based IMC design for FP DNN training. Our design consists of multiple compartments, which are the basic units for the matrix element-wise processing. We also develop BFloat16 post-processing circuits and fused adder trees, laying the foundation for IMC FP processing. Based on the proposed circuit scheme, we reformulate the back-propagation training algorithm for the convenience and efficiency of the IMC execution. The proposed design is implemented with commercial 28 nm technology process design kits and benchmarked with widely used neural networks. We model the influence of the circuit structural design parameters and provide an analysis framework for design space exploration. Our simulation validates that MobileNet training with the proposed IMC scheme saves in energy and in time versus the same task with NVIDIA GTX 3060 GPU. The proposed IMC design has a data density of 769.2 Kb mm−2 with the FP processing circuits included, showing a 3.5 × improvement than the prior FP IMC designs.

Character level vehicle license detection using multi layered feed forward back propagation neural network

Real-world traffic situations, including smart traffic monitoring, automated parking systems, and car services are increasingly using vehicle license detection systems (VLDS). Vehicle license plate identification is still a challenge with current approaches, particularly in more complicated settings. The use of machine learning and deep learning algorithms, which display improved classification accuracy and resilience, has been a significant recent breakthrough. Deep learning-based license plate identification using neural networks is proposed in this article. The number plate is detected using a multi layered feed forward back propagation neural network (MLFFBPNN). In this method, there are 3 layers namely input, hidden, and output layers has been utilized. Each layer has been related with interconnection weights. In feed forward of information, initially a set of randomly chosen weights are feed to the input data and an output has been determined. Back propagation training algorithm is utilized to train the network. Then character level identification is performed. The suggested proposed method is compared to the region-based convolutional neural network (RCNN) method in terms of accuracy and computational efficiency. The proposed method produced the character level recognition accuracy of 89%. It is improved by 4% when compared with the RCNN recognition method.

BatTS: a hybrid method for optimizing deep feedforward neural network.

Deep feedforward neural networks (DFNNs) have attained remarkable success in almost every computational task. However, the selection of DFNN architecture is still based on handcraft or hit-and-trial methods. Therefore, an essential factor regarding DFNN is about designing its architecture. Unfortunately, creating architecture for DFNN is a very laborious and time-consuming task for performing state-of-art work. This article proposes a new hybrid methodology (BatTS) to optimize the DFNN architecture based on its performance. BatTS is a result of integrating the Bat algorithm, Tabu search (TS), and Gradient descent with a momentum backpropagation training algorithm (GDM). The main features of the BatTS are the following: a dynamic process of finding new architecture based on Bat, the skill to escape from local minima, and fast convergence in evaluating new architectures based on the Tabu search feature. The performance of BatTS is compared with the Tabu search based approach and random trials. The process goes through an empirical evaluation of four different benchmark datasets and shows that the proposed hybrid methodology has improved performance over existing techniques which are mainly random trials.

Development of an artificial neural network model for criticizing the burr formation during flat bottom drilling of CuZn38As brass alloy considering cutting tool geometry

The approved laws and regulations on restricting the use of Lead in the products’ chemical composition, have made the industries to come up with development of low-lead brass alloys as an innovative solution during the last years. These alloys are the most predominantly utilized materials in pumping, drinking water industry. However, as alternatives for the conventional brass alloys, they contain lower machinability. Most of the components need to be aesthetic and compact. Therefore, the designed components have complex geometries. Flat bottom drilling is one of the new processes which is generally taken advantage in machining of these components. In this study, artificial neural networks (ANN) modelling, have been deployed to investigate the effects of the cutting tool geometries including axial rake, radial rake angles and edge radius as well as plunging angle to the work material focusing on the burr formation. A multilayer feed-forward ANN using error back-propagation training algorithm has been employed for this purpose. The results revealed possible reduction of burr formation on both the entry and exit sides of the low-lead brass alloy.

Machine Learning Model for Estimation of Local Scour Depth around Cylindrical Bridge Piers

Scour around bridge piers is a well-known threat to bridge stability worldwide. It can cause losses in lives and the economy, especially during floods. Therefore, an artificial intelligence approach called artificial neural network (ANN) was used to predict the scour depth around bridge piers. The ANN model was trained with laboratory data, including pier width, flow velocity, particle diameter, sediment critical velocity, flow depth, and scour depth. The data was divided into 70% for training, 15 for validation, and 15% for testing. Besides, the ANN model was trained using various training algrthins and a single hidden layer with 20 neurons in the hidden layer. The results showed that the ANN model with Bayesian regularization backpropagation training algorithm provides a better predicted scour depth with a correlation coefficient (R) equal to 0. 9692 and 0.926 for training and test stages, respectively. Besides, it showed a low mean squared error (MSE), which was 0.0034 for training and 0.0066 for the test. These results were slightly better than the ANN with Levenberg-Marquardt backpropagation with R training equals 0.9552 (MSE training = 0.0047), and R test equals 0.838 (MSE test = 0.007).On the other hand, the ANN model with a scaled conjugate gradient backpropagation training algorithm showed worse predictions (R training = 0.7407 and R test = 0.6409). Besides, the ANN model shows better outcomes than the linear regression model. Finally, the sensitivity analysis has shown that the pier width is the most crucial parameter for estimating scour depth using the ANN model.

Modelling Moisture Ratio of Dehydrating Yam Slices Using the Levenberg-Marquardt Back-propagation Artificial Neural Network Technique

This study predicts the moisture ratio history data of dehydrating yam slices from partial data using Artificial Neural Network (ANN) techniques. The moisture ratio history data at 65 oC, 75 oC, 85 oC, and 95 oC were recorded for the dehydration of 1.5 mm, 3.0 mm, and 4.5 mm thick yam slices in a Refractance Window Dryer. The Artificial Neural Network within MATLAB software (v. 8.5), using the Levenberg-Marquardt back-propagation algorithm, was trained with some of the data. After training, the Neural Network software predicted the moisture ratio of the primary variables not used in training. The predicted and experimental values were compared. The results showed that, the Artificial Neural Network (ANN) model using the Levenberg-Marquardt back-propagation training algorithm could accurately predict the experimental results not used in training., the predicted and observed data values fitted each other with correlation coefficient (R2) values of 0.97, 0.99 and 0.99, respectively, for the three-process condition considered. The high R2 establishes a strong correlation between the experimental and predicted values. This work is essential as it establishes that Artificial Neural Network (ANN) techniques, using the Levenberg-Marquardt back-propagation training algorithm, can predict food samples moisture ratios of in a drying process when data is incomplete.

Artificial Neural Network Modeling on PM10, PM2.5, and NO2 Concentrations between Two Megacities without a Lockdown in Korea, for the COVID-19 Pandemic Period of 2020

The mutual relationship among daily averaged PM10, PM2.5, and NO2 concentrations in two megacities (Seoul and Busan) connected by the busiest highway in Korea was investigated using an artificial neural network model (ANN)-sigmoid function, for a novel coronavirus (COVID-19) pandemic period from 1 January to 31 December 2020. Daily and weekly mean concentrations of NO2 in 2020 under neither locked down cities, nor limitation of the activities of vehicles and people by the Korean Government have decreased by about 15%, and 12% in Seoul, and Busan cities, than the ones in 2019, respectively. PM 10 (PM2.5) concentration has also decreased by 15% (10%), and 12% (10%) in Seoul, and Busan, with a similar decline of NO2, causing an improvement in air quality in each city. Multilayer perception (MLP), which has a back-propagation training algorithm for a feed-forward artificial neural network technique with a sigmoid activation function was adopted to predict daily averaged PM10, PM2.5, and NO2 concentrations in two cities with their interplay. Root mean square error (RMSE) with the coefficient of determination (R2) evaluates the performance of the model between the predicted and measured values of daily mean PM10, PM2.5, and NO2, in Seoul were 2.251 with 0.882 (1.909 with 0.896; 1.913 with 0.892), 0.717 with 0.925 (0.955 with 0.930; 0.955 with 0.922), and 3.502 with 0.729 (2.808 with 0.746; 3.481 with 0.734), in 2 (5; 7) nodes in a single hidden layer. Similarly, they in Busan were 2.155 with 0.853 (1.519 with 0.896; 1.649 with 0.869), 0.692 with 0.914 (0.891 with 0.910; 1.211 with 0.883), and 2.747 with 0.667 (2.277 with 0.669; 2.137 with 0.689), respectively. The closeness of the predicted values to the observed ones shows a very high Pearson r correlation coefficient of over 0.932, except for 0.818 of NO2 in Busan. Modeling performance using IBM SPSS-v27 software on daily averaged PM10, PM2.5, and NO2 concentrations in each city were compared by scatter plots and their daily distributions between predicted and observed values.

Using Artificial Neural Network Application in Modeling the Mechanical Properties of Loading Position and Storage Duration of Pear Fruit

In the study, rupture energy values of Deveci and Abate Fetel pear fruits were predicted using artificial neural network (ANN). This research aimed to develop a simple, accurate, rapid, and economic model for harvest/post-harvest loss of efficiently predicting rupture energy values of Deveci and Abate Fetel pear fruits. The breaking energy of the pears was examined in terms of storage time and loading position. The experiments were carried out in two stages, with samples kept in cold storage immediately after harvest and 30 days later. Rupture energy values were estimated using four different single and multi-layer ANN models. Four different model results obtained using Levenberg–Marquardt, Scaled Conjugate Gradient, and resilient backpropagation training algorithms were compared with the calculated values. Statistical parameters such as R2, RMSE, MAE, and MSE were used to evaluate the performance of the methods. The best-performing model was obtained in network structure 5-1 that used three inputs: the highest R2 value (0.90) and the lowest square of the root error (0.018), and the MAE (0.093).

Modeling arbiter-PUF in NodeMCU ESP8266 using artificial neural network

<p>A hardware fingerprinting primitive known as physical unclonable function (PUF) has a huge potential for secret-key cryptography and identification/authentication applications. The hardware fingerprint is manifested by the random and unique binary strings extracted from the integrated circuit (IC) which exist due to inherent process variations during its fabrication. PUF technology has a huge potential to be used for device identification and authentication in resource-constrained internet of things (IoT) applications such as wireless sensor networks (WSN). A secret computational model of PUF is suggested to be stored in the verifier’s database as an alternative to challenge and response pairs (CRPs) to reduce area consumption. Therefore, in this paper, the design steps to build a PUF model in NodeMCU ESP8266 using an artificial neural network (ANN) are presented. Arbiter-PUF is used in our study and NodeMCU ESP8266 is chosen because it is suitable to be used as a sensor node or sink in WSN applications. ANN with a resilient back-propagation training algorithm is used as it can model the non-linearity with high accuracy. The results show that ANN can model the arbiter-PUF with approximately 99.5% prediction accuracy and the PUF model only consumes 309,889 bytes of memory space.</p>

Optimization of MLP neural network for modeling flow boiling performance of Al2O3/water nanofluids in a horizontal tube

In this paper, a multilayer perceptron (MLP) artificial neural network (ANN) with a back-propagation (BP) training algorithm is applied for modeling thermophysical properties and subcooled flow boiling performance of Al2O3/water nanofluid in a horizontal tube. The influence of nanofluid concentration, heat flux, and flow rate on different thermophysical parameters, including thermal conductivity, thermal conductivity enhancement, viscosity, viscosity enhancement, and heat transfer coefficient, are investigated. Specifically, flow boiling of Al2O3/water nanofluid in a horizontal tube is modeled with the MLP neural network optimized by three novel swarm-based optimization algorithms: namely, Equilibrium Optimizer (EO), Marine Predators Algorithm (MPA), and Slime Mould Algorithm (SMA). To evaluate the effectiveness of different models, the MSE (Mean-Square Error) of the ANN model with varying optimization algorithms is calculated and compared. Additionally, the optimal network and regression values for each parameter are determined. The results show that the applied neural network and optimization algorithms could model the thermal conductivity, thermal conductivity enhancement, and viscosity better than the viscosity enhancement and heat transfer coefficient. The MSE of the best network for the thermal conductivity is 2.693 × 10−7, while the MSE of the best network for the viscosity enhancement is 0.0598. Also, the EO algorithm achieves the best optimization for the first three outputs, thermal conductivity, thermal conductivity enhancement, and viscosity. In comparison, the MPA algorithm extracts the optimal network for the other two outputs, viscosity enhancement, and heat transfer coefficient.

Flood Forecasting Using Artificial Neural Network

The process of assessing the timing, amount, and period of flood events based on observed features of a river basin is known as flood forecasting. Floods cause lots of damage to properties and create a risk to human life. Flood forecasting is critical for developing appropriate flood risk management strategies, reducing flood hazards, evacuating people from flood-prone areas. The main objective of this study is to apply artificial neural networks for forecasting of river flow in the Deo River, located in Gujarat. Rainfall and discharge are the parameters considered for model development. The developed model is validated to test the accuracy of the model. Trained and validated models are evaluated using performance indices. Six alternative flood prediction models have been developed using ANN. These models are developed based on various training algorithms. A single layer feed forward back-propagation neural network with six different training algorithms (Scaled conjugate gradient, Levenberg Marquardt, Resilient back-propagation, Conjugate gradient, and Cascade forward back propagation, Bayesian regularization) was developed, with 70% of the data used for training and 30% for validation. The created models’ performance is assessed using statistical performance parameters. The best performance was obtained with an ANN model developed using the Cascade forward back-propagation training algorithm, which had a coefficient of correlation (r) of 0.83, a coefficient of determination (R2) of 0.70, and a root mean squared error (RMSE) of 5.58 for training and a coefficient of correlation (r) of 0.89, a coefficient of determination (R2) of 0.70, and a root mean squared error (RMSE) of 7.27 for validation. The forecast inflow is very close to the observed values. This study shows that ANN can be used to successfully predict floods, and the model developed can be used by flood control departments across the country for flood forecasting.

The Development of PSO-ANN and BOA-ANN Models for Predicting Matric Suction in Expansive Clay Soil

Disasters have different shapes, and one of them is sudden landslides, which can put the safety of highway users at risk and result in crucial economic damage. Along with the risk of human losses, each day a highway malfunctions causes high expenses to citizens, and repairing a failed highway is a time- and cost-consuming process. Therefore, correct highway functioning can be categorized as a high-priority reliability factor for cities. By detecting the failure factors of highway embankment slopes, monitoring them in real-time, and predicting them, managers can make preventive, preservative, and corrective operations that would lead to continuing the function of intracity and intercity highways. Expansive clay soil causes many infrastructure problems throughout the United States, and much of Mississippi’s highway embankments and fill slopes are constructed of this clay soil, also known as High-Volume Change Clay Soil (HVCCS). Landslides on highway embankments are caused by recurrent volume changes due to seasonal moisture variations (wet-dry cycles), and the moisture content of the HVCCS impacts soil shear strength in a vadose zone. Soil Matric Suction (SMS) is another indication of soil shear strength, an essential element to consider. Machine learning develops high-accuracy models for predicting the SMS. The current work aims to develop hybrid intelligent models for predicting the SMS of HVCCS (known as Yazoo clay) based on field instrumentation data. To achieve this goal, six Highway Slopes (HWS) in Jackson Metroplex, Mississippi, were extensively instrumented to track changes over time, and the field data was analyzed and generated to be used in the proposed models. The Artificial Neural Network (ANN) with a Bayesian Regularization Backpropagation (BR-BP) training algorithm was used, and two intelligent systems, Particle Swarm Optimization (PSO) and Butterfly Optimization Algorithm (BOA) were developed to optimize the ANN-BR algorithm for predicting the HWS’ SMS by utilizing 13,690 data points for each variable. Several performance indices, such as coefficient of determination (R2), Mean Square Error (MSE), Variance Account For (VAF), and Regression Error Characteristic (REC), were also computed to analyze the models’ accuracy in prediction outcomes. Based on the analysis results, the PSO-ANN outperformed the BOA-ANN, and both had far better performance than ANN-BR. Moreover, the rainfall had the highest impact on SMS among all other variables and it should be carefully monitored for landslide prediction HWS. The proposed hybrid models can be used for SMS prediction for similar slopes.

Application of artificial neural networks for external network equivalent modeling

In this paper an artificial neural network (ANN) based methodology is proposed for determining an external network equivalent. The modified Newton-Raphson method with constant interchange of total active power between internal and external system is used for solving the load flow problem. A multilayer perceptron (MLP) with backpropagation training algorithm is applied for external network determination. The proposed methodology was tested with the IEEE 24-bus test network and simulation results show a very good performance of the ANN for external network modeling.

Comparison of MLP and RBF neural networks for bearing remaining useful life prediction based on acoustic emission

In this research, the efficiency of multilayer perceptron (MLP) and radial basis function (RBF) neural networks in estimating the remaining useful life (RUL) of angular contact ball bearing based on acoustic emission signals are investigated. To capture the bearing acoustic emission signals, an appropriate laboratory setup is used. Acoustic emission signal processing is carried out in the time and frequency domain and 102 different features are extracted. Prognostic feature selection have been used to reduce the dimension of the extracted features. Applications of the different training algorithms in MLP neural network are compared for bearing RUL prediction. The results indicate that acoustic emission is a good method for bearing RUL prediction. Mobility, Square-mean-root, and Count are the best time domain features based on the used feature selection method. Also, the Frequency center, Signal power, and F60 are the best frequency domain features. It was shown that between different backpropagation training algorithms for MLP neural net, Levenberg Marquardt has the lowest SSE error of 7.86 for the prediction of bearing remaining useful life based on frequency domain features. Moreover, comparison of RBF and MLP neural networks shows that RBF neural networks presents the best performance with SSE error of 2.85.