Back Propagation Neural Network Technique Research Articles

Standalone Smart Irrigation System: An Analysis of Reliability Incorporating BPNN Technique under Various Failures

Observing the huge requirements of water and energy for traditional irrigation and contracting resources, the utility of a smart irrigation system has become necessary. A system that is capable of saving water depends on renewable energy resources for power requirements and runs automatically. Water-saving automatic irrigation systems powered by renewable energy could be a solution to India's rising demand for energy and water. In the current paper, the author has proposed an analysis of a standalone smart irrigation system for its reliability and functional behaviour under various operational events of failures and repairs. The authors have implemented an intelligent computational method because of the increased degradation in system function due to the complex structure of the proposed irrigation system. The system's mathematical formulation is stated in terms of neural networks, and a back propagation neural network technique is applied for fast and comparatively better outcomes. The author has determined state probabilities and other reliability parameters by means of neural networks in the proposed smart irrigation system. To improve the accuracy and consistency of reliability parameters, a Feed Forward Back Propagation Neural Network (FFBPNN) is applied. FFBPNN's learning mechanism can optimize the values of parameters by modifying neural weights. The MATLAB codes are used by the authors to demonstrate the numerical examples, and iterations are repeated until the precision in error tends to 0.0001. The sensitivity and cost of the system are also analyzed, which can help in managing the real-time operations of the system.

Backpropagation and Radial Basis Function Methods for Predicting Rainfall in Sukabumi City Using Artificial Neural Networks: A Comparative Analysis

The weather has a substantial impact on the ability to live organisms to carry out everyday activities, particularly outside activities. Weather data is helpful in various fields, including marine, aviation, and agriculture. The maritime domain is beneficial for establishing the optimal navigation time for a fisherman, the aviation domain helps reduce climate-related mishaps, and the agriculture sector uses weather information to develop harvest season models for agricultural products. Indonesia is a tropical nation with heavy precipitation. Utilized for various objectives, rainfall forecasting models seek the utmost precision, particularly in specialized areas such as flood control. This study is based on two techniques: the Radial Basis Function Neural Network (RBFNN) and Backpropagation Neural Network (BPNN) techniques using multiple training functions. The RBFNN approach yields less accurate results for predicting precipitation, but the multi-practice BPNN method yields more accurate results.

Landslide Susceptibility Evaluation Using Different Slope Units Based on BP Neural Network.

Landslides are one of the most widespread natural hazards that cause damage to both property and life every year. Therefore, the landslide susceptibility evaluation is necessary for land hazard assessment and mitigation of landslide-related losses. Selecting an appropriate mapping unit is an essential step for landslide susceptibility evaluation. This study tested the back propagation (BP) neural network technique to develop a landslide susceptibility map in Qingchuan County, Sichuan Province, China. It compared the results of applying six different slope unit scales for landslide susceptibility maps obtained using hydrological analysis. We prepared a dataset comprising 973 historical landslide locations and six conditioning factors (elevation, slope degree, aspect, lithology, distance to fault lines, and distance to drainage network) to construct a geospatial database and divided the data into the training and testing datasets. We based on the BP learning algorithm to generate landslide susceptibility maps using the training dataset. We divided Qingchuan County into six different scales of slope unit: 4,401, 13,146, 39,251, 46,504, 56,570, and 69,013, then calculated the receiver operating characteristic (ROC) curve, and used the area under the curve (AUC) for the quantitative evaluation of 6 different slope unit scales of landslide susceptibility maps using the testing dataset. The verification results indicated that the evaluation generated by 56,570 slope units had the highest accuracy with a ROC curve of 0.9424. Overelaborate and rough division of slope units may not get the best evaluation results, and it is necessary to obtain the slope units most consistent with the actual situation through debugging. The results of this study will be useful for the development of landslide hazard mitigation strategies.

An Early Prediction of Tumor in Heart by Cardiac Masses Classification in Echocardiogram Images Using Robust Back Propagation Neural Network Classifier

Identification and classification of intracardiac masses in echocardiogram is one of the significant processes in the diagnosis of cardiovascular disease. A robust back propagation neural network (RBPNN) technique is used to conquer every single conventional-issue utilizing the echocardiogram image analysis for this work, which consists of four phases such as noise removal, automatic segmentation, feature extraction, and intracardiac masses classification. Initially, the noise is diminished from the echocardiogram images utilizing the adaptive vector median filter (AVMF). Then, linear iterative vessel segmentation (LIVS) is applied for automatic segmentation of the masses followed by the extraction of texture features using the multiscale local binary pattern (MS-LBP) approach. Finally, RBPNN is employed to classify the heart mass from the images of echocardiogram with the layered kernel for the system combination. Extensive simulation results obtained using proposed AVMF-MS-LBP based RBPNN approach disclosed the superiority over existing intracardiac mass detection and classification approaches in terms of accuracy of 98.85%.

Development of rain attenuation prediction in south west Nigeria on terrestrial link using artificial neural network

The predicted precipitation accuracy in light of the current global climate change is very important. The Back-Propagation Neural Network (BPNN) technique then utilized the Artificial Neural Network (ANN) to correctly forecast rainfall. The study is based on data from three Nigerian terrestrial microwave connections operating at frequencies of 23 and 38 GHz. At 23 GHz, a normal distribution with an average of zero is the best represented fade slope distribution, contrary to the model ITU-R earth to satellite rain fade slope. Based on the data analysis observed at 23 GHz, a novel prediction model is developed. The suggested model is validated using 38 GHz fade slope data and shown to work well with nearly all attenuation levels. A chi-square fitness test is used to further validate the model. The suggested model will be critical in the development of rainfall mitigation methods for tropical terrestrial connections. The findings of the research indicate that BPNN models may be utilized as a prediction algorithm that offers a high predictive accuracy of three types of design: 500, 1000 and 1,500.The experiment examined data on precipitation using the BPNN Architecture's two-hidden layers, from three periods of time [2-50-10-1, 500]. The average square error is used for categorization work performance evaluation. The results of the experiment indicate that the design of the 100-year-old [2-50-20-1, MSE of 0 00096341] is excellent. Moreover, the BPNN algorithm provides an efficient Southwestern Nigeria predictor model.

Analysis and prediction of worldwide novel coronavirus (COVID-19) infections, using neural network-based techniques

The novel coronavirus (COVID-19) outbreak has recently become a major public health concern around the world. It is commonly known that some of the world's most powerful countries, such as Iran and the United States, are suffering more than others from the effects of this horrific pandemic. It has spread throughout communities and has endangered the health of many people. Governments must take the necessary steps to stop the virus from spreading globally. The three most widely used backpropagation neural network (BPNN) techniques, i.e., Levenberg–Marquardt, Bayesian regularization (BR), and scaled conjugate gradient (SCG), are used to either predict the future or evaluate the current status of COVID-19 in this research. This study uses a real-time COVID-19 dataset from the Worldometer website, which contains 204 samples from 30 January to 15 April 2020. The 12 most important parameters are selected for study purposes, including country, total cases (TC), new cases (NC), total deaths (TD), new deaths (ND), total recoveries (TREV), active cases (AC), serious cases (SC), total tests (TT), death rate (DR), recovery rate (RR), and case rate (CR). Finally, countries are classified into three risk levels, i.e., high, medium, and low, based on the above parameters. In addition, some new countries are discovered at these levels.

Damage detection in RC beam utilizing feed-forward backpropagation neural network technique

Damage detection in RC beam utilizing feed-forward backpropagation neural network technique

Optimal Power Management for Seismic Nodes

Estimating the state-of-charge of a lead-acid battery at remote seismic nodes is a key factor in managing the available power. Optimal management enables the continuous acquisition of seismic data of an area. This paper presents the management of lead-acid batteries at remote seismic nodes, using the Neural Network model's historical data to estimate the battery's state-of-charge. Powersim (PSIM) simulation tool was used to implement photovoltaic energy harvesting system with a buck mode converter and maximum power point tracking algorithm to acquire historical data. A backpropagation neural network technique for training the historical dataset of hourly points in 500 days on the Matlab platform is adopted, and a feedforward neural network is employed due to the irregularities of the input data. The neural network model's hidden layer contains the transfer function of the Tansig Function to produce the model output of state-of-charge estimations. Besides, this paper is based on the management of estimating the state-of-charge of the lead-acid battery near-realtime instead of relying on the vendor's lifecycle information. The simulated results show the simplicity and optimal estimations of state-of-charge of the lead-acid battery with RMSE of 0.023%.

Development of rain attenuation prediction in south west Nigeria on terrestrial link using artificial neural Network

The predicted precipitation accuracy in light of the current global climate change is very important. The Back-Propagation Neural Network (BPNN) technique then utilized the Artificial Neural Network (ANN) to correctly forecast rainfall. The study is based on data from three Nigerian terrestrial microwave connections operating at frequencies of 23 and 38 GHz. At 23 GHz, a normal distribution with an average of zero is the best represented fade slope distribution, contrary to the model ITU-R earth to satellite rain fade slope. Based on the data analysis observed at 23 GHz, a novel prediction model is developed. The suggested model is validated using 38 GHz fade slope data and shown to work well with nearly all attenuation levels. A chi-square fitness test is used to further validate the model. The suggested model will be critical in the development of rainfall mitigation methods for tropical terrestrial connections. The findings of the research indicate that BPNN models may be utilized as a prediction algorithm that offers a high predictive accuracy of three types of design: 500, 1000 and 1,500. The experiment examined data on precipitation using the BPNN Architecture's two-hidden layers, from three periods of time [2-50-10-1, 500]. The average square error is used for categorization work performance evaluation. The results of the experiment indicate that the design of the 100-year-old [2-50-20-1, MSE of 0 00096341] is excellent. Moreover, the BPNN algorithm provides an efficient Southwestern Nigeria predictor model.

Solar PV’s Micro Crack and Hotspots Detection Technique Using NN and SVM

For lifelong and reliable operation, advanced solar photovoltaic (PV) equipment is designed to minimize the faults. Irrespectively, the panel degradation makes the fault inevitable. Thus, the quick detection and classification of panel degradation is pivotal. Among various problems that promote panel degradation, hot spots and micro-cracks are the prominent reliability problems which affect the PV performance. When these types of faults occur in a solar cell, the panel gets heated up and it reduces the power generation hence its efficiency considerably. In this study, the effect of the hotspot is studied and a comparative fault detection method is proposed to detect different PV modules affected by micro-cracks and hotspots. The classification process is accomplished by utilizing Feed Forward Back Propagation Neural Network technique and Support Vector Machine (SVM) techniques. The investigation of both the techniques permits a complete analysis of choosing an effective technique in terms of accuracy outcome. Six input parameters like percentage of power loss (PPL), Open-circuit voltage (VOC), Short circuit current (ISC), Irradiance (IRR), Panel temperature and Internal impedance (Z) are accounted to detect the faults. Experimental investigation and simulations using MATLAB are carried out to detect five categories of faulty and healthy panels. Both methods exhibited a promising result with an average accuracy of 87% for feed-forward back propagation neural network and 99% SVM technique which exposes the potential of this proposed technique.

Model updating of a bridge structure using vibration test data based on GMPSO and BPNN: case study

Model updating issues with high-dimensional and strong-nonlinear optimization processes are still unsolved by most optimization methods. In this study, a hybrid methodology that combines the Gaussian-white-noise-mutation particle swarm optimization (GMPSO), back-propagation neural network (BPNN) and Latin hypercube sampling (LHS) technique is proposed. In this approach, as a meta-heuristic algorithm with the least modification to the standard PSO, GMPSO simultaneously offers convenient programming and good performance in optimization. The BPNN with LHS establishes the meta-models for FEM to accelerate efficiency during the updating process. A case study of the model updating of an actual bridge with no distribution but bounded parameters was carried out using this methodology with two different objective functions. One considers only the frequencies of the main girder and the other considers both the frequencies and vertical displacements of typical points. The updating results show that the methodology is a sound approach to solve an actual complex bridge structure and offers good agreement in the frequencies and mode shapes of the updated model and test data. Based on the shape comparison of the main girder at the finished state with different objective functions, it is emphasized that both the dynamic and static responses should be taken into consideration during the model updating process.

Active Charge Balancing Strategy Using the State of Charge Estimation Technique for a PV-Battery Hybrid System

Charging a group of series-connected batteries of a PV-battery hybrid system exhibits an imbalance issue. Such imbalance has severe consequences on the battery activation function and the maintenance cost of the entire system. Therefore, this paper proposes an active battery balancing technique for a PV-battery integrated system to improve its performance and lifespan. Battery state of charge (SOC) estimation based on the backpropagation neural network (BPNN) technique is utilized to check the charge condition of the storage system. The developed battery management system (BMS) receives the SOC estimation of the individual batteries and issues control signal to the DC/DC Buck-boost converter to balance the charge status of the connected group of batteries. Simulation and experimental results using MATLAB-ATMega2560 interfacing system reveal the effectiveness of the proposed approach.

Forecasting of Dissolved Oxygen in Shatt Al-Arab River Based on parameters of water quality Using Artificial Neural Networks

The quality of water is considered as a vital quality factor that affects the life quality in different areas. Thus, its assessment and forecasting became an essential subject matter for several researches. Analytically, the common adopted feed forward error back propagation neural network technique is used to developed two types of ANN models. The first model is applied having experimental data that gotten from the Department of Environment, Basrah-Iraq, during year 2009-2014 and the data set for the current year (2019), while the second model is applied according to the data for the current year (2019) only. The parameters of input of the neural network are pH value (pH), electrical conductivity (EC), Total Dissolved Solid (TDS), Calcium (Ca), Magnesium (Mg), nitrate nitrogen (NO3), phosphorous (PO4 −3) and Sulfate (SO4 −2), the output parameter of the neural network is dissolved oxygen (DO). Through comparing the outcomes of ANN models depending on high value of regressions coefficient (R2) and lower value of mean square error (MSE). For the first model R = 0.96143 and MSE=0.00125 for testing. The second model is R=0.99225 and MSE=0.00532. The results show the proposed ANN prediction model has a great potential significance for the assessment and forecasting the dissolved oxygen.

Modelling of Machining Characteristics During Green Machining of Biomaterials

Titanium and its alloys are gaining much attention in the biomedical field. Their biocompatibility makes them first choice for implants. However, machining of titanium is still a challenge owing to its unique properties. Beside this, industries are also looking for a solution to the economical and ecological machining of titanium and its alloys. Current research discusses a probable solution to it. This paper presents the modelling of machining characteristics during the green machining of titanium alloy. In this work, experimentation is performed with varying cutting speed, feed, and depth of cut following response surface methodology (RSM) approach. After that, the experimental results are analyzed and employed to develop an interactive model using back-propagation neural network (BPNN) technique. It is witnessed that the developed BPNN model is of higher accuracy than RSM model. Cutting inserts are further examined to gain a deeper insight into the process. Confirmation runs are also performed for adequacy check of the developed models.

Feedforward Artificial Neural Network-Based Model for Predicting the Removal of Phenolic Compounds from Water by Using Deep Eutectic Solvent-Functionalized CNTs.

In the recent decade, deep eutectic solvents (DESs) have occupied a strategic place in green chemistry research. This paper discusses the application of DESs as functionalization agents for multi-walled carbon nanotubes (CNTs) to produce novel adsorbents for the removal of 2,4-dichlorophenol (2,4-DCP) from aqueous solution. Also, it focuses on the application of the feedforward backpropagation neural network (FBPNN) technique to predict the adsorption capacity of DES-functionalized CNTs. The optimum adsorption conditions that are required for the maximum removal of 2,4-DCP were determined by studying the impact of the operational parameters (i.e., the solution pH, adsorbent dosage, and contact time) on the adsorption capacity of the produced adsorbents. Two kinetic models were applied to describe the adsorption rate and mechanism. Based on the correlation coefficient (R2) value, the adsorption kinetic data were well defined by the pseudo second-order model. The precision and efficiency of the FBPNN model was approved by calculating four statistical indicators, with the smallest value of the mean square error being 5.01 × 10−5. Moreover, further accuracy checking was implemented through the sensitivity study of the experimental parameters. The competence of the model for prediction of 2,4-DCP removal was confirmed with an R2 of 0.99.

Information Entropy Embedded Back Propagation Neural Network Approach for Debris Flows Hazard Assessment

The purpose of the study is to propose a new method to assess debris flow hazard by embedding Shannon’s information entropy in back propagation neural network. The procedure was divided into two parts. One was to establish a mathematical model for debris-flow hazard assessment based on Shannon’s information entropy forming input and output data sets of back propagation neural network. The other was to establish a back propagation neural network technique for characterizing debris flow dynamic hazard. The proposed method was employed to assess debris flow hazard of Shenxi gully basin, Sichuan province, China. The result shows that the assessed result of proposed method is highly consistent with the result of field surveys. The proposed method can reflect the interaction, nonlinearity and dynamic process of background variable factors and can be used to debris flow hazard assessment, risk management and mitigation of debris flows.

Predicting Mouse Cursor Target using Backpropagation Neural Network

Many solutions were proposed in the past decades to assist the people with disability in the movement to interact with personal computers. Various results were proposed to simulate the mouse cursor movement and click operations through facial expressions captured by the camera. Tracking and converting accurately the facial expression of the user to the mouse operation is still acknowledged as a research challenge and opportunity. The proposed system introduces a prediction of items to be selected by the user in the GUI based system applying the backpropagation neural network techniques to improve the performance of the overall selection process.

Establishment of a seismic topographic effect prediction model in the Lushan Ms 7.0 earthquake area

SUMMARYThe seismic topographic effect is one of the debated research topics in seismology and earthquake engineering. This debate is due to the discrepancy between the observed amplification and the amplification underestimation in numerical simulations. Although the numerical simulation of ground motion, which began in the 1970s, has been an important and effective way to study topographic effects, the quantitative mathematical model of topographic amplification is urgent. The actual influences on ground motion due to the topography depends on multiple topographic features, such as the topographic slope, topographic geometrical scale. To date, no definite conclusions regarding the main influencing factors and how to express the influencing factors have been made. In this paper, by introducing the back-propagation (BP) neural network technique, a set of mathematical parameters are determined to establish a quantitative topographic effect prediction model. These parameters are the elevation, the first gradient of the elevation and the higher order gradient in two orthogonal directions. Theoretically, the set of mathematical parameters is directly related to the simple topographic features, such as the elevation, topographic slope and height-to-width ratio. Furthermore, their combinations indirectly denote the complex topographic geometrical features, such as the different topographic geometrical scales, designated by the elevation (large-scale variable), the first gradient (middle-scale variable), the second-order gradient (small-scale variable) and so on (smaller scale variable), and the hill ridges that correspond to the sites with the first gradient of the elevation equal to zero and an elevation larger than its surrounding. In 2013, an earthquake of Ms 7.0 occurred in the Lushan area of Sichuan Province in Western China, where the topography sharply fluctuates. At station 51BXD, an acceleration was recorded close to 1.0 g, while at station 51BXM (14 km away from station 51BXD), the acceleration was recorded at only 0.2–0.3 g. In this paper, the spectral element method (SEM) is used to simulate the ground motion in the Lushan Ms 7.0 earthquake area. Then, the topographic amplification ratio of the simulated ground motion is calculated. Furthermore, a BP topographic amplification prediction model is established and compared based on different parameters. A rms of less than or close to 10 per cent between the BP model prediction results and topographic amplification ratio calculated using the simulated ground motion suggests that the parameters of the topographic elevation, the first gradient of the elevation and the second-order gradient in two orthogonal directions are enough to provide the acceptable topographic effect model in the Lushan area. Finally, using the prediction model, the topographic spectral ratio at stations 51BXD and 51BXM is predicted, and the topography amplification due to the scattering of seismic waves by the irregular topography at 51BXD is found to be 1.5–2 times that of 51BXM. The most important highlights of this paper identify the main factors of the topographic effect for the first time and provide an effective method for establishing a quantitative topographic effect prediction model.

An enhanced back propagation method for change analysis of remote sensing images with adaptive preprocessing

ABSTRACT Automatic change detection in remote sensing images of a specified image acquired at various time period, which is unique and fascinating idea of image processing. The significance of change-detection techniques depends on probability of recognizing the changes in land covers by investigating multispectral images acquired at different session. Based on the previous papers accurate change detection (CD) is not yet identified. Enhanced Back-Propagation Neural Network (EBPNN) technique for CD is used to enhance the accuracy based on many existing techniques. This method involves an Adaptive Median Filter (AMF) that is responsible to remove the noise identified in remote sensing images. Moreover, feature extraction is achieved with the Tamura and Law’s mask features by which minute features are extorted from the images. By contrasting numerous existing techniques, the precision is measured with the support of different parameters.

Prediction of Fuel Consumption for Enroute Ship Based on Machine Learning

Due to the hike in fuel price and environmental awareness by the International Maritime Organization, more attention has been given in order to optimize the fuel consumption of ships. The capability to predict the fuel consumption of ships plays a significant role in the optimization process. To date, most research on predicting ship fuel consumption did not consider marine environmental factors such as wind, wave, current, and etc. Furthermore, traditional statistical methods on predicting ship fuel consumption have low accuracy. In this paper, two different sets of data showing the fuel consumption of a voyage ship with and without the influence of marine environmental factors were obtained. The Back-Propagation Neural Network (BPNN) and Gaussian Process Regression (GPR) techniques in machine learning were used to train and predict the two datasets. Thereafter, the predictive performance of these two techniques was compared and analyzed. Results showed that both techniques were able to accurately predict the ship fuel consumption, especially on the dataset with the influence of marine environmental factors. Quantitatively, the mean prediction accuracy for GPR (mean R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.9887) is slightly higher than BPNN (mean R <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> = 0.9817). However, GPR requires longer runtime (mean T = 2236.4 s) compared to BPNN (mean T = 14.7 s). Due to the longer runtime, GPR is less preferable for online and real-time prediction of enroute ship fuel consumption. The ship real-time fuel consumption data can be accurately predicted by machine learning, which will be beneficial to achieve the goal of ship fuel consumption optimization and greenhouse gas emission reduction in the future.