Back-propagation Artificial Neural Network Method Research Articles

OPTIMASI METODE JARINGAN SARAF TIRUAN BACKPROPAGATION UNTUK PERAMALAN CURAH HUJAN BULANAN DI KOTA DENPASAR

Rainfall is a natural phenomenon that depends on many factors that are an important part of life on earth. The high intensity of rainfall can lead to disasters. Therefore, this study aims to forecast monthly rainfall. The data used was obtained from BMKG Bali Province, namely monthly rainfall data for Denpasar City from 2009 to 2019. The method used is backpropagation artificial neural network. The artificial neural network method is an information processing method inspired by the human nervous system. Optimal backpropagation network architecture is needed so that the prediction results have a low error rate, by optimizing the use of training data and test data taken from sample data. Based on the results of the testing and prediction process with the parameters of one hidden layer with 50 neorons, epoch 11 and learning rate 0.01, the results obtained with the MSE value in network testing are 0.037. So it can be concluded that the backpropagation artificial neural network method has good accuracy results used as a reference for decision making in predicting monthly rainfall in Denpasar City in the future.
  

Identification of Bioethanol Quality for Motorcycle Fuel

The availability of crude oil as a raw material for vehicle fuel is dwindling and limited in nature. One of the renewable energies worth developing is bioethanol, which is one of the alternative fuels that can be used as a biofuel and can be processed from plants containing starch and glucose. In this research, the entire bioethanol identification system in a sugar cane drip distillation apparatus was examined. The distillation process using MQ3 and MQ135 sensors resulted in an alcohol percentage of 42% and 46%. The maximum temperature measured by a thermocouple during distillation was 88°C, while the minimum temperature recorded was 87°C. This study utilized a backpropagation artificial neural network method to identify the detected bioethanol. The architecture of the artificial neural network included 2 input nodes, 4 neuron nodes, and 2 output nodes. The training and testing results showed that the formed backpropagation was able to identify and differentiate the detection of bioethanol according to the given inputs with a success rate of 88.86% for detected bioethanol and 94.86% for undetected bioethanol..

Design and Development of a Coffe Blending Device with Carbon Monoxide (CO) Level Identification Based on Artificial Neural Networks

Coffee is categorized into three types Robusta, Arabica, and Liberica. The roasting process is the most crucial step in developing the aroma, flavor, and underlying color that determine coffee quality. The coffee roasting process produces complex aroma compounds that impart the desired taste and aroma characteristics of coffee. This research aims to design a coffee content detection tool by determining the carbon monoxide (CO) level in Arabica, Robusta, and Liberica coffee. The research uses the Backpropagation artificial neural network method with 2 hidden layers, including 4 input layers and 3 output layers, to identify the tested coffee varieties. The highest carbon monoxide (CO) levels were found in Arabica Special coffee, with an ADC level of 662 carbon monoxide gas. The lowest carbon monoxide (CO) levels were detected in Liberica coffee, with an ADC level of 105 carbon monoxide gas. Coffee identification was carried out using an artificial neural network method with a success rate of 98% for Liberica coffee, 100% for Arabica coffee, and 98% for Robusta coffee.

The Analysis and Rapid Non-Destructive Evaluation of Yongchuan Xiuya Quality Based on NIRS Combined with Machine Learning Methods

This paper attempts to analyze and assess Yongchuan Xiuya tea quality quickly, accurately, and digitally. The sensory evaluation method was first used to assess Yongchuan Xiuya tea quality, and then near infrared spectroscopy (NIRS) was obtained, and standard methods were applied to the testing of the chemical components. Next, principal component analysis (PCA) and the correlation coefficient method were used to comprehensively screen out the representative components. Finally, NIRS combined with partial least squares regression (PLSR) and back propagation artificial neural network (BP-ANN) methods were applied to build quality evaluation models for Yongchuan Xiuya tea, respectively, and external samples were employed to examine the practical application results of the best model. The cumulative variance contribution rate of the first three principal components of the ingredients in tea was 97.73%. Seven components closely related to tea quality were screened out, namely, amino acids, total catechin, epigallocatechin gallate (EGCG), tea polyphenols, water extracts, epicatechin gallate (ECG), and epigallocatechin (EGC) (p < 0.01). Between the two models established to predict the tea quality, the model built by the PLS method had the better results, whose coefficient of determination of prediction (Rp2) and root mean square error of prediction (RMSEP) were 0.7955 and 1.2263, respectively, and the best results were obtained by the nonlinear BP-ANN model, whose Rp2 and RMSEP were 0.9315 and 0.6787, respectively. The 10 external Yongchuan Xiuya samples were employed to test the best BP-ANN model, and the results of R2 and RMSEP were 0.9579 and 0.6086, respectively, meaning that the model has good robustness. Therefore, the model established by NIRS combined with the BP-ANN method can be used to assess Yongchuan Xiuya tea quality rapidly, accurately, and digitally, and it can also provide new ideas and methods for evaluating the quality of other teas.

Implementasi Backpropagation ANN dan Algoritma Genetika Terhadap Estimasi Pendapatan Agen Ekspedisi Pengiriman Barang

Income is the amount of income received by a person or resident for their work performance during a certain period, whether daily, weekly, monthly or yearly. This research implements the Backpropagation Artificial Neural Network and Genetic Algorithm methods to estimate the income of JNE Express Sekaran agents. Artificial Neural Network and Genetic Algorithm are modern forecasting methods that produce the smallest and most accurate error values. Based on the research that has been done, the Backpropagation Artificial Neural Network method produces the best architectural model, namely 4-10-1 with 4 as the input layer, 10 as hidden neurons, and 1 as the output layer. With epoch 487 obtains an MSE 0,150807. While the Genetic Algorithm method produces the best fitness value is 10209,02 with a population size of 200, crossover probability 0,8, mutation probability 0,03 in the 498th generation and obtains an MSE value of 0,000098. So, it can be predicted that income for the following month is October 2021 of IDR 25.011.603, November 2021 of IDR 20.920.021, and December 2021 of IDR 50.553.019

Comparison of Data Fusion Methods in Fusing Satellite Products and Model Simulations for Estimating Soil Moisture on Semi-Arid Grasslands

In arid and semi-arid areas, soil moisture (SM) plays a crucial role in land-atmosphere interactions, hydrological processes, and ecosystem sustainability. SM data at large scales are critical for related climatic, hydrological, and ecohydrological research. Data fusion based on satellite products and model simulations is an important way to obtain SM data at large scales; however, little has been reported on the comparison of the data fusion methods in different categories. Here, we compared the performance of two widely used data fusion methods, the Ensemble Kalman Filter (EnKF) and the Back-Propagation Artificial Neural Network (BPANN), in the degraded grassland site (DGS) and the alpine grassland site (AGS). The SM data from the Community Land Model 5.0 (CLM5.0) and the Soil Moisture Active and Passive (SMAP) were fused and validated against the observations of the Cosmic-Ray Neutron Sensor (CRNS) to avoid the impacts of scale-mismatch. Results show that compared with the original data sets at both sites, the RMSE of the fused data by BPANN (FD-BPANN) and EnKF (FD-EnKF) had improved by more than 50% and 31%, respectively. Overall, the FD-BPANN performs better than the FD-EnKF because the BPANN method assigned higher weights to input data with better performance and the EnKF method is affected by the strong variabilities of both the fused CLM5.0 and SMAP data and the CRNS data. However, in terms of the percentile range, the FD-BPANN showed the worst performance, with overestimations in the low SM range of 25th percentile (<Q25), because the BPANN method tends to be trapped in a local minimum. The BPANN method performed better in humid areas, then followed by semi-humid areas, and finally arid and semi-arid areas. Moreover, compared with the previous studies in arid and semi-arid areas, the BPANN method in this study performed better.

Prediction of Soil Water Content Based on Hyperspectral Reflectance Combined with Competitive Adaptive Reweighted Sampling and Random Frog Feature Extraction and the Back-Propagation Artificial Neural Network Method

The soil water content (SWC) is a critical factor in agricultural production. To achieve real-time and nondestructive monitoring of the SWC, an experiment was conducted to measure the hyperspectral reflectance of soil samples with varying levels of water content. The soil samples were divided into two parts, SWC higher than field capacity (super-θf) and SWC lower than field capacity (sub-θf), and the outliers were detected by Monte Carlo cross-validation (MCCV). The raw spectra were processed using Savitzky–Golay (SG) smoothing and then the spectral feature variable of SWC was extracted by using a combination of competitive adaptive reweighted sampling (CARS) and random frog (Rfrog). Based on the extracted feature variables, an extreme learning machine (ELM), a back-propagation artificial neural network (BPANN), and a support vector machine (SVM) were used to establish the prediction model. The results showed that the accuracy of retrieving the SWC using the same model was poor, under two conditions, i.e., SWC above and below θf, mainly due to the influence of the lower accuracy of the super-θf part. The number of feature variables extracted by the sub-θf and super-θf datasets were 25 and 18, respectively, accounting for 1.85% and 1.33% of the raw spectra, and the variables were widely distributed in the NIR range. Among the models, the best results were achieved by the BPANN model for both the sub-θf and the super-θf datasets; the R2p, RMSEp, and RRMSE of the sub-θf samples were 0.941, 1.570%, and 6.685%, respectively. The R2p, RMSEp, and RRMSE of the super-θf samples were 0.764, 1.479%, and 4.205%, respectively. This study demonstrates that the CARS–Rfrog–BPANN method was reliable for the prediction of SWC.

A creep life prediction model of P91 steel coupled with back-propagation artificial neural network (BP-ANN) and θ projection method

In order to predict the long-term creep life of P91 steel, this work proposed a coupled model, combining the error-trained back-propagation artificial neural network (BP-ANN) and an improved θ model. Both the short-term rupture life obtained by creep experiments and the related creep data of National Institute for Materials Science (NIMS) database were used to validate the above model. In this model, creep parameters (temperature, stress) were used as the input and relative error of 5 θ model extrapolations as the output. Then, the prediction errors of BP-ANN method were introduced to correct the 5 θ model extrapolation results to achieve a more accurate prediction. Consequently, the long-term creep life of P91 steel was predicted. It demonstrated that with the proposed model, the prediction capability for long-term creep life of P91 steel with 200,000 h is much better than those of other θ methods, which has a prediction uncertainty less than 5%.

BPNN Optimization With Genetic Algorithm For Classification of Tobacco Leaves With GLCM Extraction Features

Tobacco leaves are one of the agricultural commodities cultivated by Indonesian farmers. In their application in the field, there are many obstacles in tobacco leaf cultivation, one of which is declining tobacco quality caused by weather factors. In this study, a technology-based analysis step was carried out to determine the classification in determining the quality of tobacco leaves. The research was carried out by applying the classification optimization of the Backpropagation Artificial Neural Network Method and genetic algorithms to determine the weights obtained from extracting GLCM features. You can get the weight value from the genetic algorithm on the homogeneity variable from this analysis step. The variable gets a weight value of 1. The results of this study obtained a classification value with the Backpropagation Artificial Neural Network Method model getting an accuracy value of 53.50% at a hidden layer value of 2,4,5,7. For classification with the Artificial Neural Network Method, Backpropagation, which is optimized with genetic algorithms, you get an accuracy value of 64.50% at the 4th hidden layer value. From this study, the value of optimization accuracy increased by 11% after being optimized with genetic algorithms.
  

Prediksi Kebutuhan Energi Listrik Menggunakan Metode Jaringan Syaraf Tiruan

Government owned company of electricity play an important role in the distribution of electrical energy services. The Bagan Batu Auxiliary Service Unit (ULP) is one of the ULPs that plays an important role in the distribution of electrical energy in the Bagan Batu area. Along with the increase in the number of customers every year, the problem of demand for electrical energy changes and increases every year. To predict short-term electrical energy needs, this study uses the Backpropagation Artificial Neural Network method with the help of the MATLAB R2015B tool. The research data for training and network testing uses the history of energy sold (kWh) for the last 10 years with other variables consisting of household customers, business, social, industrial, population growth, Gross Regional Domestic Product (GRDP). The results of the research produce predictions of electrical energy for the next 3 years from 2022 to 2024. This research produces the best architectural model 6-6-1 with the smallest MSE error of 0.003312731 and produces Mean Absolute Percentage Error (MAPE) value of 6%. The research implies benefits for stakeholders to take action on the provision of electrical energy

Circulation analysis and forecasting of fuel sales using the backpropagation artificial neural network method

The availability of a general fuel supply for the community is an interesting matter to study. This is because fuel is a basic need for the community. This paper aims to model and predict the general fuel demand and circulation using the Backpropagation Artificial Neural Network (ANN) method. A neural network consists of a set of numbers in simple processing elements called neurons, units, cells, or nodes. Each neuron is connected to the other neurons in a manner directed by communication links and by interrelated weights. Weights are represented as information that will be used by the network to solve a problem. In this study, secondary data is used on the volume of fossil fuel sold daily at the Hasanuddin gas station in Makassar from January 1, 2018 – March 29, 2021, with a lot of data 1121 days. The types of fossil fuels studied are Premium and Pertalite. The results obtained indicate that the best model obtained for the Pertalite ANN architecture with 4 inputs and 5 neurons in the hidden layer has the best accuracy with a MAPE of 17.64% which is classified as good, while the Pertalite ANN architecture with 7 inputs and 25 neurons in the hidden layer has accuracy. the best with a MAPE of 14.64% which is classified as good.

Rapid quantification of acid value in frying oil using iron tetraphenylporphyrin fluorescent sensor coupled with density functional theory and multivariate analysis

Abstract A metalloporphyrin-based fluorescent sensor was developed to determine the acid value in frying oil. The electronic and structural performances of iron tetraphenylporphyrin (FeTPP) were theoretically investigated using time-dependent density functional theory and density functional theory at the B3LYP/LANL2DZ level. The quantified FeTPP-based fluorescent sensor results revealed its excellent performance in discriminating different analytes. In the present work, the acid value of palm olein was determined after every single frying cycle. A total of 10 frying cycles were conducted each day for 10 consecutive days. The FeTPP-based fluorescent sensor was used to quantify the acid value, and the results were compared with the chemical data obtained by conventional titration method. The synchronous fluorescence spectrum for each sample was recorded. Parallel factor analysis was used to decompose the three-dimensional spectrum data. Then, the support vector regression (SVR), partial least squares, and back-propagation artificial neural network methods were applied to build the regression models. After the comparison of the constructed models, the SVR models exhibited the highest correlation coefficients among all models, with 0.9748 and 0.9276 for the training and test sets, respectively. The findings suggested the potential of FeTPP-based fluorescent sensor in rapid monitoring of frying oil quality and perhaps also in other foods with higher oil contents.

Prediction of Patients' Illness Based on Average Temperature and Rainfall In Az-Zainiyah Clinic Using Backpropagation Method

The purpose of this study is to predict the type of disease in students based on the average temperature and rainfall at the Az-Zainiyah clinic using the backpropagation method. With this research, we hope that the prediction/estimation process on the type of patient's disease using the backpropagation artificial neural network method provides a solution with precise and accurate prediction results based on data on many patients, average temperature, and previous rainfall. This research is carried out through a process of predicting the type of disease by collecting time-series data from patient visit reports. The raw data obtained are examined for completeness and quality of the data. Then, the data was analyzed and applied to an artificial neural network method to predict the type of patient's disease based on many patients, average temperature, and rainfall. Furthermore, the artificial neural network will be optimized by the backpropagation algorithm. From this study, we find that the percentage of precision obtained in the experimental type of pharyngitis/sore throat disease in November 2020 with an average precision percentage is 68.92%, the best precision percentage is 90.25%, and the worst precision percentage 47.59%. In December 2020, the average precision percentage is 41.46%, with the best precision percentage being 65.55%, and the worst precision percentage 4.92%. In the type of dermatitis/itching disease in November 2020, the best precision percentage is 98.81%, the average precision percentage is 68.31%, and the worst precision percentage is -21.57 %. For December 2020, the average precision percentage is -63.27%, the best precision percentage is 48.37%, and the worst precision percentage is -183.85%.

İnsansız Hava Araçlarının (İHA) Şifrelenmiş Wi-Fi Trafiği Üzerinden Çalışma Modlarının Yapay Sinir Ağları Aracılığı İle Belirlenmesi

Developing technology has also made the Unmanned Aerial Vehicles (UAV) widespread. While UAVs provide beneficial use in many sectors from engineering solutions to visual arts, they also come up with malicious uses and can even be used as a tool for committing crimes. Although the states are trying to register its use with legislation in order to prevent this problem, the problem has not been completely eliminated. The most important problem we face about UAVs is to be able to percept quickly and effectively for what purpose they are flying over a certain region. Although previous studies in the literature were partially successful in solving this problem, it could not be considered as an effective solution due to high costs and long detection time. In this study, the encrypted wi-fi traffic was tried to be defined by the data packet size analysis method to determine the operating modes of the UAVs. Since the amount of data and data processing speed are the most important factors in the detection of UAVs, processes based on artificial intelligence and machine learning have been applied. Using the feed-forward backpropagation artificial neural network method, the operating modes of the UAVs were determined and a success rate of 99.29% was achieved.

Artificial neural network for quantitative and qualitative determination of the viscosity of nanofluids by ATR-FTIR spectrometry

The multivariate data analysis refers to the process by which determination and classification of new unknown samples are made by accurate and economically practicable methods. In this paper, new analytical methods were utilized as a fast analytical method for regression and classification of polyacrylamide-nano silica (PAM-SiO2) as an influential factor in the rheological performance of the nanofluids, utilizing attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy and chemometric methods. The effect of nanoparticle concentration on the viscosity measurement was determined. The spectral data were used for determination of viscosity value according to back-propagation artificial neural network (BP-ANN) algorithm. The root mean square errors (RMSEs) of model and test set in BP-ANN method were 0.051, and 3.548, respectively. In classification model, the ATR-FTIR spectral data were applied for analysis by using the counter-propagation artificial neural networks (CP-ANN) for classification of PAM-SiO2 nanofluids. The samples were classified based on the effect of nanoparticle concentration on viscosity values. The correct classification of the four classes was obtained by using CP-ANN modelling procedure. This work attempts to propose an analytical method to regression and classification viscosity of real-world data sets.

Implementation of Backpropagation Artificial Network Methods for Early Children’s Intelligence Prediction

Intelligence is the ability to process certain types of information derived from human biological and psychological factors. This study aims to implement a Backpropagation artificial neural network for prediction of early childhood intelligence and how to calculate system accuracy on children's intelligence using the backpropagation artificial neural network method. The Backpropagation Neural Network method is one of the best methods in dealing with the problem of recognizing complex patterns. Backpropagation Neural Networks have advantages because the learning is done repeatedly so that it can create a system that is resistant to damage and consistently works well. The application of the Backpropagation Neural Network method is able to predict the intelligence of early childhood. The results of the calculation of the Backpropagation Artificial Neural Network method from 42 children's intelligence data being tested, with 27 training data and 15 test data, the results obtained 100% accuracy percentage results.

Estimating Crop LAI Using Spectral Feature Extraction and the Hybrid Inversion Method

The leaf area index (LAI) is an essential indicator used in crop growth monitoring. In the study, a hybrid inversion method, which combined a physical model with a statistical method, was proposed to estimate the crop LAI. The simulated compact high-resolution imaging spectrometer (CHRIS) canopy spectral crop reflectance datasets were generated using the PROSAIL model (the coupling of PROSPECT leaf optical properties model and Scattering by Arbitrarily Inclined Leaves model) and the CHRIS band response function. Partial least squares (PLS) was then used to reduce the dimension of the simulated spectral data. Using the principal components (PCs) of PLS as the model inputs, the hybrid inversion models were built using various modeling algorithms, including the backpropagation artificial neural network (BP-ANN), least squares support vector regression (LS-SVR), and random forest regression (RFR). Finally, remote sensing mapping of the CHRIS data was achieved with the hybrid model to test the inversion accuracy of LAI estimates. The validation result yielded an accuracy of R2 = 0.939 and normalized root-mean-square error (NRMSE) = 6.474% for the PLS_RFR model, which indicated that the crops LAI could be estimated accurately by using spectral feature extraction and a hybrid inversion strategy. The results showed that the model based on principal components extracted by PLS had a good estimation accuracy and noise immunity and was the preferred method for LAI estimation. Furthermore, the comparative analysis results of various datasets showed that prior knowledge could improve the precision of the retrieved LAI, and using this information to constrain parameters (e.g., chlorophyll content or LAI), which make important contributions to the spectra, is the key to this improvement. In addition, among the PLS, BP-ANN, LS-SVR, and RFR methods, RFR was the optimal modeling algorithm in the paper, as indicated by the high R2 and low NRMSE in various datasets.

QSPR studies on the blood-air partition coefficient of volatile organic compounds using theoretical descriptors derived from electrostatic potentials on molecular surface

Volatile organic compounds (VOCs) is a sort of important environmental pollutant. Based on study on Quantitative Structure-Property Relationship (QSPR), geometrical optimization and electrostatic potential calculations have been performed for 143 VOC molecules at the HF/6-31G* level of theory. A number of statistically-based parameters have been obtained. Multiple Linear Regression (MLR) and back-propagation artificial neural network (BP-ANN) nonlinear regression are used for the model building. The result shows that the BP-ANN can better expresses the relation between molecule surface electrostatic potential and blood-air partition coefficient than MLR, and the QSPR model established has comparatively stronger stability and predictive ability using BP-ANN method. The result also proves the applicability of molecule surface electrostatic potential parameter in QSPR study of Volatile organic chemical.

Designing a Diabetes Mellitus Detection Tool Using the Backpropagation Method

Technological advances in the field of medical electronics are developing very rapidly; one of the positive effects of advances in electronic technology in the world of health is the detection of Diabetes Mellitus (DM) with urine odor which based on microcontrollers with Backpropagation artificial neural network methods. Diabetes Mellitus is a chronic disease characterized by high levels of sugar (Glucose), and is caused by the inability of pancreas to produce insulin. The detection of diabetes mellitus in this study used gas sensors of TGS 2602, TGS 2610 and TGS 813. Results of the study showed several sensor values; 120-290 for TGS 2610, 120-290 for TGS 813, and 100-170 for TGS 2610. The undertaken artificial neural network method was able to identify two urine samples, of which each sample was tested and conducted a training test with success rate results of 75%.

Expert System of Diagnosing Building Damage due to Earthquake using Backpropagation Artificial Neural Network Method

Earthquake is one of the most destructive natural disasters. After the earthquake, experts were deployed to survey the damage that occurred. One of the main objectives of the assessment task carried out by experts is to evaluate and classify buildings into several categories based on the level of damage that occurs. In this study, an expert system that could facilitate the assessment of building damage due to the earthquake was made using Backpropagation neural network method. The testing techniques used in this system are blackbox, accuracy and Mean Opinion Score (MOS) testing. MOS testing conducted by 30 respondents produced an MOS value of 4.54 from a scale of 5. While the average accuracy of the system obtained is 82.22% of the 30 case cases tested by 3 building damage experts.