Artificial Neural Network Method Research Articles

Diagnosing Voltage and Current Imbalance of Three-Phase Induction Motor with Artificial Neural Network Method

Diagnosing Voltage and Current Imbalance of Three-Phase Induction Motor with Artificial Neural Network Method

A Novel Machine-Learning Algorithm to Predict the Early Termination of Nutrition Support Team Follow-Up in Hospitalized Adults: A Retrospective Cohort Study.

For hospitalized adults, it is important to initiate the early reintroduction of oral food in accordance with nutrition support team guidelines. The aim of this study was to develop and validate a machine learning-based algorithm that predicts the early termination of medical nutritional therapy (the transition to oral feeding). This retrospective cohort study included consecutive adult patients admitted to the Hacettepe hospital (from 1 January 2018 to 31 December 2022). The outcome of the study was the prediction of an early transition to adequate oral feeding before discharge. The dataset was randomly (70/30) divided into training and test datasets. We used six ML algorithms with multiple features to construct prediction models. ML model performance was measured according to the accuracy, area under the receiver operating characteristic curve, and F1 score. We used the Boruta Method to determine the important features and interpret the selected features. A total of 2298 adult inpatients who were followed by a nutrition support team for medical nutritional therapy were included. Patients received parenteral nutrition (1471/2298, 64.01%), enteral nutrition (717/2298, 31.2%), or supplemental parenteral nutrition (110/2298, 4.79%). The median (interquartile range) Nutritional Risk Screening (NRS-2002) score was 5 (1). Six prediction algorithms were used, and the artificial neural network and elastic net models achieved the greatest area under the ROC in all outcomes (AUC = 0.770). Ranked by z-value, the 10 most important features in predicting an early transition to oral feeding in the artificial neural network and elastic net algorithms were parenteral nutrition, surgical wards, surgical outcomes, enteral nutrition, age, supplemental parenteral nutrition, digestive system diseases, gastrointestinal complications, NRS-2002, and impaired consciousness. We developed machine learning models for the prediction of an early transition to oral feeding before discharge. Overall, there was no discernible superiority among the models. Nevertheless, the artificial neural network and elastic net methods provided the highest AUC values. Since the machine learning model is interpretable, it can enable clinicians to better comprehend the features underlying the outcomes. Our study could support personalized treatment and nutritional follow-up strategies in clinical decision making for the prediction of an early transition to oral feeding in hospitalized adult patients.

Classification of Crude Palm Oil Quality Using Artificial Neural Networks Based on Chemical Components

Palm oil, known as Crude Palm Oil (CPO), is a flagship product in the palm oil industry, playing a crucial role in the economies of various tropical countries such as Indonesia. This study aims to classify the quality of CPO based on chemical components using the Artificial Neural Networks (ANN) method with a backpropagation algorithm. The research data was obtained from PT. Perkebunan Lembah Bhakti (PLB) 2 from January to October 2023, consisting of 225 entries with five main chemical variables: impurity level, moisture content, free fatty acid (FFA) level, Deterioration of Bleachability Index (DOBI), and carotenoids. The data preprocessing stage involved transforming and normalizing the data using the Z-score method. The ANN model used has a 5-5-2 architecture with ReLU activation functions for the input and hidden layers and a Softmax function for the output layer. Model evaluation was conducted using accuracy metrics, which showed that the ANN model could classify CPO quality with an accuracy of 97.78% on the test data. The research results show that ANN can classify CPO quality with a high level of accuracy. This indicates that this method has great potential for use in the industry to improve CPO quality assessment. The improvement in accuracy and validity of the ANN classification results has significant implications for the industry. With high accuracy, ANN can reduce human errors in quality assessment, speed up the process, and increase the consistency of assessment results. This is crucial because consistent quality assessment can enhance operational efficiency and reduce production costs.

FORECASTING CHANGE IN THE LEVEL OF FOREST COVERAGE USING THE GLOBAL FOREST WATCH SERVICE AND THE PROGRAMMING AND DATA ANALYSIS LANGUAGE R

The problem of calculating the level of forest cover is considered, including forecasting changes in forest cover in individual forestry. It is stated that the authors previously developed software for calculating forest cover and processing information about forest plantations using the example of the village of Spivakivka in the Izyum district of the Kharkiv region. A comparison of forest cover over a number of years was also made using the Global Forest Watch resource. From this resource, images of Prydonetsk Forestry were taken with conventional designations: areas where new forest plantations are being planted are shown in blue, and areas where cutting is taking place are shown in pink. It is proposed to divide each of the uploaded images of the selected forestry into squares, and then analyze the data for each square. The pink color saturation was calculated and stored in the table. It is noted that forecasting the change in forest stands on the selected site, that is, the change in the percentage of felling, can be done in different ways. First, use regression analysis - apply the regression equation separately to the values of each square, as well as to the entire forestry. Secondly, to form a list of input factors containing indicators on the selected plot in the two previous years and the same indicators on neighboring plots. Thus, the number of factors will be equal to 27: 26 input and 1 output (values on the studied square). Such a forecasting problem can be solved either by the method of multivariate linear regression or by the method of artificial neural networks. The R programming and data analysis language was used to perform calculations using both methods. A script was created that performs calculations by constructing regression lines and an artificial neural network, and also allows determining the best architecture of a neural network and a more effective method of its training for a certain data set. The calculation of the felling dynamics in the entire forestry (the forecast for the last year provides an error of 1 %) and the calculation of the felling dynamics in the selected square (the forecast for the last year provides an error of 3.5 %) are given. After many runs of the script, it was found that the best result is provided by a perceptron with two hidden layers and two neurons in each layer. The results of the calculations indicate a high correlation of the data for determining the percentage of forest that will be cut down in a certain square. Application of this perceptron for forecasting for the last year showed an error of 3 %.

Enhanced photocatalytic degradation of tetracycline using α-Fe2O3@TiO2- impregnated Mxene photocatalyst: Mechanism and optimization of process via RSM and ANN

This study involves the synthesis, characterization, and optimization of a remarkably effective α-Fe2O3@TiO2@MXene ternary photocatalyst, which was synthesized by employing an expeditious and controllable ultrasonic-assisted technique. The tetracycline (TC) photocatalytic decomposition was investigated under visible-light, an effective and eco-friendly approach. Impact of different factors on the synthesis process, including α-Fe2O3@TiO2 content (2−32 wt%) and calcination temperature (300–600°C), were examined via Response Surface Methodology- Central Composite Design (RSM-CCD) for the first time. Based on degradation test results, the optimum conditions were determined to be 18.91 % and 441°C, respectively. Additionally, the operational parameters for TC degradation were explored within dosage of catalyst (0.2−1.5 g.L−1), tetracycline concentration (5−65 ppm), irradiation time (20−160 min), and pH (2−10) by RSM and Artificial Neural Network (ANN) methods. Optimal operating conditions for aforementioned variables were found to be 0.54 g.L−1, 39.37 ppm, 124 min, and pH of 4.83, respectively, with degradation efficiency of 98.36 % and 96.22 % according to RSM-CCD and ANN analysis. Considering the trapping test, •O2- and •OH- radicals are the primary species responsible for the degradation of TC. The PL analysis indicated that the rate of photogenerated recombination diminished following the impregnation of Fe2O3/TiO2 particles onto the MXene. Furthermore, the experimental evidence demonstrated that the Fe2O3@TiO2@MXene heterojunction photocatalyst effectively decomposed TC with 84.65 % Chemical oxygen demand (COD) removal. The stability of the Fe2O3@TiO2@MXene catalyst was exceptional throughout the photocatalysis process with negligible leaching of Fe2O3@TiO2 over four cycles.

Preparation of expandable polystyrene/acrylonitrile-butadiene-styrene by multi-stage initiator dosing with the application of artificial neural networks

By increasing usage of polymers, environmental problems for them increase. The polymers that after usage, contribute to these issues, their preparation process may generate wastage, that affects production. In the production of expandable polystyrene (EPS), several batches on batch were discharged due to disruption in suspension, and the presence of these wastages in the production place can cause problems. This study tries to introduce a new polymer with special features by mixing different percentages of this polymer (10, 20, 30) with ABS polymer. According to the fact that disarray can occur in 60, 63, 66, and 69% of the polymerization, the polymerization continued until those percentages and then mixed with ABS. Different tests (like: Elongation at break, yellow index, Modular melt flow, Impact test, and Vicat softening temperature) was performed for mixed polymer. The results show that in some materials the quality of the mixed polymer may decrease but it is still in an acceptable range. The Multi-Layer Perceptron method of Artificial Neural Networks has been used in order to simulate data that has not been tested.

Predicting project duration using a coupled artificial neural network and Taguchi method approach

Accurate project duration prediction is increasingly important for management because it defines the expected timeline for project realization. This study utilizes an integrated approach combining neural networks with the Taguchi method to forecast the time required to complete projects within predetermined deadlines. The methodology involves modelling and simulating the network of project activities to estimate the total average project duration. ration. The neural network model uses input variables such as success probability, effort, and learning factor to predict the total time necessary for project completion. The total average project duration is the output variable that is critical during the design phase. Subsequently, the Taguchi method optimizes the neural network’s outputs, incorporating mean squared error (MSE) values to enhance predictive accuracy. accuracy. This study underscores the efficacy of artificial neural networks (ANNs) as predictive tools, demonstrating their ability to meticulously estimate project duration. The proposed method’s efficiency and applicability are demonstrated by MATLAB simulation analyses, highlighting its effectiveness in precise deadline estimation. In the realm of engineering, ANNs stand tall as formidable predictive tools, their efficacy underscored by this study’s successful application. By harnessing ANNs and simulation data, this research crafts a predictive model adept at estimating the average total duration of projects. Through meticulous consideration of crucial parameters like the probability of success and effort factors, the model emerges as a beacon of accuracy within the design domain. Future research will explore the effects of additional parameters on activity networks and alternative transfer functions, as well as the potential integration of reinforcement algorithms to improve resource allocation, risk management, and project outcomes through online training data.

Modeling and Prediction of Surface Roughness in Hybrid Manufacturing–Milling after FDM Using Artificial Neural Networks

Three-dimensional printing, or additive manufacturing, represents one of the fastest growing branches of the industry, and fused deposition modeling (FDM) is one of most frequently used technologies. Three-dimensional printing does not provide high-quality surfaces, so finishing is required, and milling is one of the best methods for improving surface quality. The combination of 3D printing and traditional manufacturing technologies is known as hybrid manufacturing. In order to improve quality and determine optimal machining parameters, researchers increasingly use artificial intelligence methods. In the context of manufacturing technologies, both multiple regression analysis (MRA) and artificial neural networks (ANNs) have proven to be highly reliable in predicting and optimizing machining processes. This study focuses on the use of MRA and an ANN to analyze the influence of machining parameters such as feed rate, depth of cut, and spindle speed on the surface roughness of a 3D-printed part in a milling process. The study compares the measured results with the outcomes obtained through MRA and the ANN to assess their effectiveness in predicting and optimizing surface roughness. The results show that higher accuracy was obtained from the ANN method.

Assessing carbon budgets and reduction pathways in different income levels with neural network forecasting

Understanding carbon emissions across income levels is vital to limiting global warming to below 1.5 °C and 2 °C, as the Paris Agreement outlines. Unequal emission patterns can affect global remaining carbon budgets, necessitating differentiated strategies. This paper introduces a unique perspective to forecasting carbon emissions and determining the remaining carbon budget relative to income levels and associated socioeconomic factors. Leveraging Pearson correlation analysis and Bayesian-optimised Artificial Neural Network methods, the study examines emissions and carbon budgets of thirty countries, representing 82 % of global carbon emissions in 2022, under a business-as-usual scenario across various income levels. Findings reveal distinct patterns, with high-income countries experiencing declining emissions while middle- and low-income countries anticipate increases. High-income countries are projected to deplete their 2.0 °C budgets later than middle- and low-income countries, with an estimated depletion around 2052 and 2046–2048, respectively. Proposed mitigation and adaptation strategies tailored to income levels include investment in advanced technologies for high-income countries, promoting energy efficiency and renewable energy transition for middle-income countries, and expanding clean energy access for low-income countries. This study advocates the importance of integrating income levels and socioeconomic factors into climate policymaking, offering insights for policymakers, environmentalists, and businesses to tailor interventions and promote equitable climate action.

Fragility analysis of high arch dam against far-field underwater blast

The security assessment of high arch dams is a significant topic that has been researched in recent years. It is troublesome to develop a security assessment for high arch dams under far-field underwater blasts because the high arch dam is a sophisticated statically indeterminate spatial shell structure, and the underwater blasting shock wave has the characteristics of a large peak value and high frequency. Hence, the fragility analysis of a 300-m-high arch dam against a far-field underwater blast based on the probabilistic method is conducted for safety evaluation with the index of downstream peak displacement (and Downstream Peak Displacement-Span ratio). The fragility analysis process of the high arch dam under the far-field underwater blast is proposed for the first time. The impact of foundation plasticity on the high arch dam under far-field underwater blast is discussed regarding dynamic response and damage patterns with the coupled acoustic-structural (CAS) method first. The damage limit states are presented based on different damage patterns and index values from enormous computational schemes. The fragility curves with different indexes of downstream peak displacement, upstream peak displacement, and damage volume ratio are also compared. The fragility curves of the high arch dam against the far-field underwater blast with different explosive distances of 50 to 200 m are established with the Artificial Neural Network method. The results demonstrate that the non-linear dynamic response and damage of the high arch dam under the far-field underwater blast are significantly influenced by the foundation plasticity, especially for vibration upstream and damage of the foundation face. The explosive situations with an explosive distance of 50–100 m and explosive weight of more than 12000 kg cause a greater threat to the security of the high arch dam with the probability of severe damage approaching 100 %. The explosive situations with an explosive distance of more than 150 m or explosive weight of less than 3000 kg have a small effect. The research results can be used as a reference when conducting safety assessments of high arch dams to blasting loads.

Anomaly detection in groundwater monitoring data using LSTM-Autoencoder neural networks.

Groundwater monitoring data can be prone to errors and biases due to various factors like borehole and equipment malfunctions, or human mistakes. These inaccuracies can jeopardize the groundwater system, leading to reduced efficiency and potentially causing partial or complete failures in the monitoring system. Traditional anomaly detection methods, which rely on statistical and time-variant techniques, struggle to handle the complex and dynamic nature of anomalies. With advancements in artificial intelligence and the growing need for effective anomaly detection and prevention across different sectors, artificial neural network methods are emerging as capable of identifying more intricate anomalies by considering both temporal and contextual aspects. Nonetheless, there is still a shortage of comprehensive studies on groundwater anomaly detection. The intricate patterns of sequential data from groundwater present numerous challenges, necessitating sophisticated modeling techniques that combine mathematics, statistics, and machine learning for viable solutions. This paper introduces a model designed for high accuracy and efficient computation in detecting anomalies in groundwater monitoring data through a probabilistic approach. We employed the Monte Carlo method and SEAWAT numerical simulation to ascertain the uncertainty in groundwater salinity. Subsequently, a Long Short-Term Memory (LSTM)-Autoencoder model was trained and evaluated, forming the basis of an anomaly detection framework. Each piece of training data was assessed by the LSTM-Autoencoder using the Negative Log Likelihood (NLL) score and a predefined threshold to determine the data's abnormality percentage. The accuracy evaluation of the proposed LSTM-Autoencoder algorithm revealed that this approach achieved commendable performance, with an accuracy of 98.47% in anomaly detection.

A study on the application of artificial neural network to predict k-eff and peaking factor of a small modular PWR

Machine learning (ML) using artificial neural network (ANN) methods is being applied to predict required parameters for nuclear reactors based on learning from big data sets. The ML models usually give faster calculation speed while the accuracy is good agreement with physical simulators. In this work, a multi-layer perceptron network was built and trained to predict k-eff and peaking factor of a small modular pressurized water reactor (PWR). The results are compared with those obtained by using a reactor physics code system, i.e. SRAC2006. The comparison shows good agreement accuracy and higher performance of the ML models.

Revisiting the nexus between financialization and natural Resource efficiency through the lens of financial development and green industrial optimization

Responsible natural resource management has become critical for ensuring the effective use of resources jeopardizing future generations' needs. Financialization based on artificial intelligence, green finance, and lower economic risks are important in this respect. The objective of this study is to explore the impact of financialization and economic uncertainty on the natural resource market. The analysis covers the period from 1980 to 2021 and is performed for selected South Asian Association for Regional Cooperation (SAARC) countries. In addition, among economic financialization processes, artificial intelligence (AI) based financial management (FM) is more significant than domestic financialization strategies. For that purpose, Artificial Neural Network (ANN) method and pooled regression analysis are employed for the empirical analysis. According to the findings, economic uncertainty has a stronger influence than economic financialization. Therefore, risk mitigation plays a larger role in creating shocks in all macroeconomic indicators and, as a result, on the natural resource market. The accuracy measures to support the finding's robustness like the value of R2 is highly acceptable and errors are minimum (% MAPE is 5.06 which falls under the criteria of high accuracy) in both testing and training datasets approximately by 50%. In addition, the findings of Garson method reveal that economic uncertainty and AI based FM are significantly important for the natural resource market as their important values (0.27, 0.26, and 0.20) touch the maximum importance statistics (0.30). The study, therefore, suggests that authorities in South Asian countries should focus on AI-based financial advancement and integrate AI into the traditional financialization methods to upgrade the regional economic financial system, which will help in regulating and improving the efficiency of the resource market. The results also provide the graphical and tabulation formation of financialization and economic uncertainty in SAARC countries. Additionally, analysis on the chosen variable by suing PCA has also been made to transform the dataset. Along with it, the regional corporation is crucial for dwindling economic uncertainty and promoting a steady growth and sustainable environment through the maintenance of the natural resource market.

Detection of different adulteration in cinnamon powder using hyperspectral imaging and artificial neural network method

Cinnamon is one of the medicinal spices that is important in point of economic and human health. The goal of the present research was to classify the levels of different adulterations in the spice using hyperspectral imaging technology. In the present research, three adulterants were investigated including sea foam powder and chickpea and wheat flour with 0, 5, 15, 30, and 50% adulteration levels. After sample preparation, the hyperspectral images of them were acquired using a line scan imaging system. The effective wavelengths were selected and image features were extracted. The effective features were selected and classified using the artificial neural network method. The classification accuracies of the classifier to identify sea foam powder and chickpea and wheat flour adulterants were equal to 98.9, 100, and 100%, respectively. The results showed the high ability of hyperspectral imaging combined with artificial neural networks method to detect adulteration in cinnamon with high reliability.

Artificial Intelligence for Application in Water Engineering: The Use of ANN to Determine Water Quality Index in Rivers

To improve water quality, total daily loads must be established, and this requires determining the quality of the water in rivers, storage tanks, ponds, and coastal areas. Current methods to evaluate water quality involve the collection of water samples for subsequent laboratory analysis. Although these technologies offer precise measurements for a specific location and time, they are expensive, time-consuming, and do not provide the continuous, temporal, or spatial conditions of water quality that are required for managing, assessing, and monitoring water quality. In order to calculate the water quality, the water quality index is modeled using artificial neural network models that incorporate feedforward neural network backpropagation neural networks and radial neural networks. The water quality index of Malaysia’s Klang River was determined by training the artificial network using six major sub-quality parameters. Compared to the current method, the artificial neural network simplifies and expedites the computation of the water quality index. The artificial neural network method could provide a significant saving in terms of money and time while offering a robust assessment of water quality. The proposed method could also be used as an early warning system for pollution of water bodies. The best artificial neural network was the feedforward neural network with one hidden layer containing 5 neurons. Furthermore, conventional approaches for calculating the water quality index rely on empirical equations, often introducing a high degree of approximation and uncertainty into the results. Moreover, these equations cannot be applied when some parameters are not measured. In contrast, the artificial neural network methods and technique offer an efficient and straightforward process for estimating and creating prediction models for water quality index. Doi: 10.28991/CEJ-2024-010-07-012 Full Text: PDF

Research on prediction model of quantitative relationship of pressure attenuation of hydrogen fuel cell air compressor based on artificial neural network

Abstract This thesis considers the field of the pressure attenuation of hydrogen fuel cell air compressors as the main subject of its study. Traditional methods usually model the prediction of pressure attenuation based on a durability test or physical model, which is costly and time-consuming. Based on the method of artificial neural network (ANN), this paper establishes a prediction model of the quantitative relationship of outlet pressure attenuation of hydrogen fuel cell air compressors. A neural network is used to capture the nonlinear relationship of outlet pressure of air compressors, and the prediction results of the model are analyzed and explained to explore the attenuation process of outlet pressure of hydrogen fuel cell air compressors. The comparison between the actual test data and the predicted data through the endurance test of the air compressor shows that the prediction ability of the model is good, and the correlation of the regression analysis results of the prediction model is above 0.99, which can be used to predict the quantitative relationship of outlet pressure attenuation of hydrogen fuel cell air compressor.

Dự báo khả năng vỡ nợ của doanh nghiệp nhỏ và vừa tại Việt Nam: Nghiên cứu trên các mô hình học máy

This study develops a model for predicting default risk (DR) for small and medium-sized enterprises (SMEs) in Vietnam using machine learning methods such as Logistic Regression (LR), Decision Trees, XGBoost, and Artificial Neural Networks (ANN). The data is collected from the financial statements of enterprises borrowing from commercial banks and companies listed on the Vietnamese financial market from 2010 to 2022. The performance of the models is evaluated using metrics such as the F1 score and accuracy (ACC). Results show that Decision Trees, XGBoost, and ANN outperform LR. Specifically, ANN achieves an F1 score of 0.756 and an ACC of 0.9345 on the validation dataset, demonstrating excellent predictive capability. The ANN method has significant potential in identifying high-risk customers, thereby optimizing the credit risk management process. The study also identifies key predictive variables, providing insights for developing more effective DR models. Future research could apply advanced hyperparameter tuning techniques and expand the feature set to optimize the model further

Two-dimensional stiffness identification by inversion of local wavenumbers based on artificial neural network

Impact and fatigue damages in carbon fiber reinforced polymers (CFRP) are unavoidable in severe operating conditions, which will lead to the stiffness properties degrading and redistributing in space. The local wavenumbers of guided waves at a specific point depend on the stiffness at that spatial location. Therefore, the two-dimensional stiffness properties can be determined by inversion of local wavenumbers. In this paper, the relationship between the local wavenumbers and the stiffness coefficients was established by the artificial neural network (ANN) method. For each spatial point, based on the semi-analytical finite element (SAFE) method, the wavenumbers (inputs of ANN) with different frequencies can be obtained at given stiffness coefficients (outputs of ANN). Furthermore, the accuracy of the ANN method was validated by the finite element model. Results show that the predicted two-dimensional stiffness coefficients of the damaged region are close to the true ones, thus demonstrating the accuracy of the two-dimensional stiffness identification method.

Artificial neural network method in solving smart cities construction fuzzy multi-objective linear programming problems

Nowadays, the increasing demands of smart cities require innovative technologies to optimize resource utilization and minimize costs. This research focuses on the construction sector, specifically the production of advanced high-strength steel. We address practical application problems from the iron and steel factory in Annaba, Algeria, known as fuzzy multi-objective linear programming problems. Two methods are applied: a mathematical model and Artificial Neural Networks (ANNs). Results indicate that the ANN approach offers significant time and effort savings.

Improving support vector machine and backpropagation performance for diabetes mellitus classification

Diabetes mellitus (DM) is a glucose disorder disease in the human body that contributes significantly to the high mortality rate. Various studies on early detection and classification have been conducted as a DM prevention effort by applying a machine learning model. The problems that may occur are weak model performance and misclassification caused by imbalanced data. The existence of dominating (majority) data causes poor model performance in identifying minority data. This paper proposed handling the problem of imbalanced data by performing the synthetic minority oversampling technique (SMOTE) and observing its effect on the classification performance of the support vector machine (SVM) and Backpropagation artificial neural network (ANN) methods. The experiment showed that the SVM method and imbalanced data achieved 94.31% accuracy, and the Backpropagation ANN achieved 91.56% accuracy. At the same time, the SVM method and balanced data produced an accuracy of 98.85%, while the Backpropagation ANN method and balanced data produced an accuracy of 94.90%. The results show that oversampling techniques can improve the performance of the classification model for each data class.