Multiple Artificial Neural Network Research Articles

Refined Equivalent Modeling Method for Mixed Wind Farms Based on Small Sample Data

For equivalent modeling of mixed wind farms (WFs), existing clustering indicators cannot consider the complex coupling characteristics between different types of wind turbines (WTs). In this paper, a refined equivalent modeling approach based on artificial intelligence technology is proposed. Firstly, the electromechanical transient performance of mixed WFs is analyzed. The WT type, wind speed and direction, and voltage dip are considered the dominant factors affecting the external dynamic response of mixed WFs. Secondly, the equivalent node model is established, including the selection of independent and dependent variables. Then, the multiple artificial neural networks (ANNs) are trained one by one based on small sample data, to fit the nonlinear relationship between the dependent variables and the independent variables. Finally, the dynamic response of the power systems with a mixed WF is simulated in the MATLAB platform. A comparison of the errors in electromechanical phenomena demonstrates that the proposed model can reflect the external characteristics of the test mixed WF in different wind conditions and voltage dips.

Detecting Cybersecurity Threats using AI Network

Finding a method to quickly and efficiently identify online hazards is one of the most crucial issues in the world of cybersecurity. This study demonstrates a novel approach to identifying internet threats using artificial intelligence and artificial neural networks. The suggested method significantly increases the ability to identify cyber threats by breaking down a huge number of security events into individual event profiles and using a deep learning-based detection mechanism. AI-SIEM (Artificial Intelligence Security Information and Event Management) has been developed as a means of achieving this. This system integrates multiple artificial neural network methods, such as Fully Connected Neural Networks (FCNN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks, with event profiling for data preparation.

Evaluating teaching quality in colleges using combination of artificial neural networks (ANNs) and black hole optimization (BHO)

Automated evaluation of educational quality can be an effective measure of the efficiency of teaching methods, enabling the determination of the best teaching approach based on the educational environment conditions. Machine learning techniques have been used in various research studies as tools for automated evaluation of teaching quality. However, the low accuracy of classical learning models in quantitative quality estimation remains a challenge. To address this issue, one can utilize optimization strategies for learning models or combine multiple learning models as an ensemble system. These aspects are studied in the current paper. In the proposed method, automated evaluation of English teaching quality is performed through two phases: "identification of prominent quality evaluation indicators" and "quality estimation based on ensemble learning." In the first phase, the Black Hole Optimization (BHO) algorithm is used to determine the minimum number of indicators required for accurate quality estimation. In the second phase, the proposed method combines multiple artificial neural networks (ANNs) to predict education quality. In this ensemble model, the configuration and weight vector of each ANN are adjusted by the BHO algorithm to minimize training error. Then, an averaging strategy is employed to determine the final output of the ensemble system. The performance of the proposed method is evaluated using real English teaching data. Based on the results, the proposed method can achieve an average accuracy of 98.53 % in estimating English teaching quality, which represents a 2.19 % improvement compared to previous methods.

Reducing the risk of gas leaks into the ocean floor induced by offshore production well failure

Considering the high number of wells in offshore formations such as the Gulf of Mexico having a risk of leaking gas into the surrounding formations, a deep understanding of the fate and transport of gas released from damaged wells is of special relevance for hazard assessment and prevention in offshore petroleum operations. This work explores a robust strategy to reduce the risk and impact of contaminant releases in an offshore formation by analyzing the applicability of machine learning technology as a tool to forecast the information regarding a possible broaching in a loss of containment scenario of an offshore well. Numerical simulations to describe the system behavior in hydrate-bearing media were implemented to generate the data regarding the broaching day and location, and the hydrate mass generated and the total released CH4 in gas phase in the system. Using the data generated from the different scenarios, we trained multiple Artificial Neural Networks for the prediction of the different outputs, which showed excellent correlations between the input and output features. This is the first study to combine machine learning technology for advanced reservoir simulation to reduce the broaching hazard of gas escaping from an offshore production well.

Predicting intubation risk among COVID-19 hospitalized patients using artificial neural networks.

Accurately predicting the intubation risk in COVID-19 patients at the admission time is critical to optimal use of limited hospital resources, providing customized and evidence-based treatments, and improving the quality of delivered medical care services. This study aimed to design a statistical algorithm to select the best features influencing intubation prediction in coronavirus disease 2019 (COVID-19) hospitalized patients. Then, using selected features, multiple artificial neural network (ANN) configurations were developed to predict intubation risk. In this retrospective single-center study, a dataset containing 482 COVID-19 patients who were hospitalized between February 9, 2020 and July 20, 2021 was used. First, the Phi correlation coefficient method was performed for selecting the most important features affecting COVID-19 patients' intubation. Then, the different configurations of ANN were developed. Finally, the performance of ANN configurations was assessed using several evaluation metrics, and the best structure was determined for predicting intubation requirements among hospitalized COVID-19 patients. The ANN models were developed based on 18 validated features. The results indicated that the best performance belongs to the 18-20-1 ANN configuration with positive predictive value (PPV) = 0.907, negative predictive value (NPV) = 0.941, sensitivity = 0.898, specificity = 0.951, and area under curve (AUC) = 0.906. The results demonstrate the effectiveness of the ANN models for timely and reliable prediction of intubation risk in COVID-19 hospitalized patients. Our models can inform clinicians and those involved in policymaking and decision making for prioritizing restricted mechanical ventilation and other related resources for critically COVID-19 patients.

Research on Sound Imagery of Electric Shavers Based on Kansei Engineering and Multiple Artificial Neural Networks

The electric shaver market in China reach 26.3 billion RMB by 2021. Nowadays, in addition to functional satisfaction, consumers are increasingly focused on the emotional imagery conveyed by products with multiple-senses, and electric shavers are not only shaped to attract consumers, but their product sound also conveys a unique emotional imagery. Based on Kansei engineering and artificial neural networks, this research explored the emotional imagery conveyed by the sound of electric shavers. First, we collected a wide sample of electric shavers in the market (230 types) and obtained the consumers’ perceptual vocabulary (85,710 items) through a web crawler. The multidimensional scaling method and cluster analysis were used to condense the sample into 34 representative samples and 3 groups of representative Kansei words; then, the semantic differential method was used to assess the users’ emotional evaluation values. The sound design elements (including item and category) of the samples were collected and classified using Heardrec Devices and ArtemiS 13.6 software, and, finally, multiple linear and non-linear correlation prediction models (four types) between the sound design elements of the electric shaver and the users’ emotional evaluation values were established by the quantification theory type I, general regression neural network, back propagation neural network, and genetic algorithm-based BPNN. The models were validated by paired-sample t-test, and all of them had good reliability, among which the genetic algorithm-based BPNN had the best accuracy. In this research, four linear and non-linear Kansei prediction models were constructed. The aim was to apply higher accuracy prediction models to the prediction of electric shaver sound imagery, while giving specific and accurate sound design metrics and references.

Pedestrian Road Crossing Behavior and Optimal Selection of Pedestrian Facilities at Mid-Block Crossings

Pedestrians are considered the most vulnerable of all road users, particularly in developing counties. Therefore, the safety of pedestrians plays a significant role during road crossing. The pedestrian gap acceptance and level of service (LOS) can be used to evaluate pedestrian crossing behavior. The existing statistical models are failed to predict the accurate level of pedestrian safety due to various assumptions. Thus, the objectives of this study are to develop pedestrian crossing behavior models, level of service model, and systematic methodology to select optimal pedestrian crossing facilities at midblock under mixed traffic conditions. The required data were collected from selected six midblock locations in Tiruchirappalli, India, by conducting videographic and questionnaire surveys simultaneously. Various influencing parameters on pedestrian crossing behavior were identified by conducting statistical correlation analysis. First, the pedestrian field critical gap was estimated and compared with various methods such as Raff, Greenshield, Ashworth, and Highway Capacity Manual 2010. The pedestrian gap acceptance model was developed by adopting stepwise multiple linear regression and non-linear artificial neural network methods. The developed models were validated and compared using the field data. The pedestrian LOS model was developed by utilizing the conventional regression method by using qualitative and quantitative data. Pedestrian LOS model was validated using another set of field data. Finally, the approximate solution to find the best crossing facility was found by performing weighting by a ranking method and analytical hierarchy process in all six locations. This study helps in identifying the most significant factors influencing road crossing behavior of pedestrians for the selected locations. The study results help design pedestrian facility and thereby improve pedestrian safety at uncontrolled intersections.

QSAR analysis on a large and diverse set of potent phosphoinositide 3-kinase gamma (PI3K\u03b3) inhibitors using MLR and ANN methods

Phosphorylation of PI3Kγ as a member of lipid kinases-enzymes, plays a crucial role in regulating immune cells through the generation of intracellular signals. Deregulation of this pathway is involved in several tumors. In this research, diverse sets of potent and selective isoform-specific PI3Kγ inhibitors whose drug-likeness was confirmed based on Lipinski’s rule of five were used in the modeling process. Genetic algorithm (GA)-based multivariate analysis was employed on the half-maximal inhibitory concentration (IC50) of them. In this way, multiple linear regression (MLR) and artificial neural network (ANN) algorithm, were used to QSAR models construction on 245 compounds with a wide range of pIC50 (5.23–9.32). The stability and robustness of the models have been evaluated by external and internal validation methods (R2 0.623–0.642, RMSE 0.464–0.473, F 40.114, Q2LOO 0.600, and R2y-random 0.011). External verification using a wide variety of structures out of the training and test sets show that ANN is superior to MLR. The descriptors entered into the model are in good agreement with the X-ray structures of target-ligand complexes; so the model is interpretable. Finally, Williams plot-based analysis was applied to simultaneously compare the inhibitory activity and structural similarity of training, test and validation sets.

Development of New Models to Determine the Rheological Parameters of Water-Based Drilling Fluid using Artificial Neural Networks

It is well known that drilling fluid is a key parameter for optimizing drilling operations, cleaning the hole, and managing the rig hydraulics and margins of surge and swab pressures. Although the experimental works represent valid and reliable results, they are expensive and time consuming. In contrast, continuous and regular determination of the rheological fluid properties can perform its essential functions during good construction. The aim of this study is to develop empirical models to estimate the drilling mud rheological properties of water-based fluids with less need for lab measurements. This study provides two predictive techniques, multiple regression analysis and artificial neural networks, to determine the rheological properties of water-based drilling fluid using other simple measurable properties. While mud density, marsh funnel, and solid% are key input parameters in this study, the output models are plastic viscosity, yield point, apparent viscosity and gel strength. The prediction methods have been applied on datasets taken from the final reports of two wells drilled in the Ahdeb oil field, eastern Iraq. To test the performance ability of the developed models, two error-based metrics (determination coefficient R2 and root mean square error have been used in this study. The current results support the evidence that MW, MF, and solid% are consistent indexes for the prediction of rheological mud properties. Both mud density and solid content have a relative-significant effect on increasing PV, YP, AV, and gel strength. The results also reveal that both MRA and ANN are conservative in estimating the fluid rheological properties, but ANN is more precise than MRA. Eight empirical mathematical models with high performance capacity have been developed in this study to determine the rheological fluid properties using simple and quick equipment such as mud balance and marsh funnel. This study presents cost-effective models to determine the rheological fluid properties for future well planning in Iraqi oil fields.

Artificial neural networks for resources optimization in energetic environment

Resource Planning Optimization (RPO) is a common task that many companies need to face to get several benefits, like budget improvements and run-time analyses. However, even if it is often solved by using several software products and tools, the great success and validity of the Artificial Intelligence-based approaches, in many research fields, represent a huge opportunity to explore alternative solutions for solving optimization problems. To this purpose, the following paper aims to investigate the use of multiple Artificial Neural Networks (ANNs) for solving a RPO problem related to the scheduling of different Combined Heat & Power (CHP) generators. The experimental results, carried out by using data extracted by considering a real Microgrid system, have confirmed the effectiveness of the proposed approach.

Survey of Cryptocurrency Volatility Prediction Literature Using Artificial Neural Networks

We start by presenting a short description of the concept of cryptocurrency and the history behind it. Recently-developed literature that attempt to predict volatilities of cryptocurrency valuations through creation of hybrid artificial neural network models are then discussed. For the major part of the paper, we delve into details of multiple hybrid artificial neural networks that were thoroughly implemented to predict cryptocurrency volatilities. Results are reported within the form of a survey. Finally, we compare different methods and discuss their results follow at the end.

Assessment and development of air quality forecasting models by the combination of PCA and ANN at metropolis Kolkata, India

PM10, PM2.5, SO2, NO2, Pb, As and Ni were monitored at Jadavpur, Kolkata over the time span of October 2016 to March 2017. The air quality of the study area was assessed in terms of air quality index (AQI) which is calculated on the assessed concentration of the pollutants. The result of the study showed significant seasonal variance and the ambient air of the study area is highly polluted in terms of particulate matters, NO2 and metallic pollutants. AQI study reveals that PM2.5 was found responsible for this degraded air quality of Kolkata. Principal component analysis (PCA) was used to identify possible contributors i.e. i) construction work, windblown dust, road dust and earth crust (variance- 28.98%); ii) automobile exhaust (variance- 20.47%); iii) brake wear source, road dust and tire wear (variance- 18.07%) of air pollution in the study area. Multiple linear regression (MLR) and feedforward backpropagation artificial neural network (FFBPANN) were used in combination with PCA to predict the future PM2.5 concentrations. Several performance indexes were used to assess the degree of accuracy and the magnitude of error in the model predicted values. Overall performance index establishes the fact that PCA-FFBP-ANN model most accurately predicts the future PM2.5 concentrations.

Hybrid Data Mining Forecasting System Based on Multi-Objective Optimization and Selection Model for Air pollutants

The air quality index (AQI) indicates the short-term air quality situation and changing trend of the city, which includes six air pollutants: PM2.5, PM10, CO, NO2, SO2 and O3. Due to the diversity of pollutants and the fluctuation of single pollutant time series, it is a challenging task to find out the main pollutants and establish an accurate forecasting system in a city. Previous studies primarily focused on enhancing either forecasting accuracy or stability and failed to analyze different air pollutants at length, leading to unsatisfactory results. In this study, a model selection forecasting system is proposed that consists of data mining, data analysis, model selection, and multi-objective optimized modules and effectively solves the problems of air pollutants monitoring. The proposed system employed fuzzy C-means cluster algorithm to analyze 13 original AQI series, and fuzzy comprehensive evaluation is used to find out the main air pollutants in each city. And then multiple artificial neural networks are used to forecast the main air pollutants for each category and find the optimal models. Finally, the modified multi-objective optimization algorithm is used to optimize the parameters of optimal models and model selection to obtain final forecasting values from optimal hybrid models. The experiment results of datasets from 13 cities in the Beijing–Tianjin–Hebei Urban Agglomeration demonstrated that the proposed system can simultaneously obtain efficient and reliable data for air quality monitoring.

Toward an Adaptive Artificial Neural Network–Based Postprocessor

AbstractWe introduce an adaptive form of postprocessor where algorithm structures are neural networks where the number of hidden nodes and the network training features evolve. Key potential advantages of this system are the flexible, nonlinear mapping capabilities of neural networks and, through backpropagation, the ability to rapidly establish capable predictors in an algorithm population. The system can be implemented after one initial training process and future changes to postprocessor inputs (new observations, new inputs, or model upgrades) are incorporated as they become available. As in prior work, the implementation in the form of a predator–prey ecosystem allows for the ready construction of ensembles. Computational requirements are minimal, and the use of a moving data window means that data storage requirements are constrained. The system adds predictive skill to a demonstration dynamical model representing the hemispheric circulation, with skill competitive with or exceeding that obtainable from multiple linear regression and standard artificial neural networks constructed under typical operational limitations. The system incorporates new information rapidly and the dependence of the approach on the training data size is similar to multiple linear regression. A loss of performance occurs relative to a fixed neural network architecture in which only the weights are adjusted after training, but this loss is compensated for by gains from the ensemble predictions. While the demonstration dynamical model is complex, current numerical weather prediction models are considerably more so, and thus a future step will be to apply this technique to operational weather forecast data.

A Combined Forecasting System Based on Modified Multi-Objective Optimization for Short-Term Wind Speed and Wind Power Forecasting

Wind speed and wind power are two important indexes for wind farms. Accurate wind speed and power forecasting can help to improve wind farm management and increase the contribution of wind power to the grid. However, nonlinear and non-stationary wind speed and wind power can influence the forecasting performance of different models. To improve forecasting accuracy and overcome the influence of the original time series on the model, a forecasting system that can effectively forecast wind speed and wind power based on a data pre-processing strategy, a modified multi-objective optimization algorithm, a multiple single forecasting model, and a combined model is developed in this study. A data pre-processing strategy was implemented to determine the wind speed and wind power time series trends and to reduce interference from noise. Multiple artificial neural network forecasting models were used to forecast wind speed and wind power and construct a combined model. To obtain accurate and stable forecasting results, the multi-objective optimization algorithm was employed to optimize the weight of the combined model. As a case study, the developed forecasting system was used to forecast the wind speed and wind power over 10 min from four different sites. The point forecasting and interval forecasting results revealed that the developed forecasting system exceeds all other models with respect to forecasting precision and stability. Thus, the developed system is extremely useful for enhancing forecasting precision and is a reasonable and valid tool for use in intelligent grid programming.

Validation of a Point-of-Care Optical Coherence Tomography Device with Machine Learning Algorithm for Detection of Oral Potentially Malignant and Malignant Lesions.

Simple SummaryEarly detection is crucial towards improving survival in patients diagnosed with oral cancer. Non-invasive strategies equivalent to histology diagnosis are extremely valuable in oral cancer screening and early detection in resource-constrained settings. Optical coherence tomography (OCT), an optical biopsy technique enables real-time imaging with periodic surveillance and capability to image architectural features of the tissues. We report that while OCT system delineates oral pre-cancer and cancer with more than 90% sensitivity, integration, with artificial neural network-based analysis efficiently identifies high-risk, oral pre-cancer (83%). This study provides evidence that the robust, low-cost system was effective as a point-of-care device in resource-constrained settings. The high accuracy and portability signify widespread clinical application in oral cancer screening and/or surveillance.Non-invasive strategies that can identify oral malignant and dysplastic oral potentially-malignant lesions (OPML) are necessary in cancer screening and long-term surveillance. Optical coherence tomography (OCT) can be a rapid, real time and non-invasive imaging method for frequent patient surveillance. Here, we report the validation of a portable, robust OCT device in 232 patients (lesions: 347) in different clinical settings. The device deployed with algorithm-based automated diagnosis, showed efficacy in delineation of oral benign and normal (n = 151), OPML (n = 121), and malignant lesions (n = 75) in community and tertiary care settings. This study showed that OCT images analyzed by automated image processing algorithm could distinguish the dysplastic-OPML and malignant lesions with a sensitivity of 95% and 93%, respectively. Furthermore, we explored the ability of multiple (n = 14) artificial neural network (ANN) based feature extraction techniques for delineation high grade-OPML (moderate/severe dysplasia). The support vector machine (SVM) model built over ANN, delineated high-grade dysplasia with sensitivity of 83%, which in turn, can be employed to triage patients for tertiary care. The study provides evidence towards the utility of the robust and low-cost OCT instrument as a point-of-care device in resource-constrained settings and the potential clinical application of device in screening and surveillance of oral cancer.

COMPUTATIONAL SCREENING AND QSAR STUDY ON A SERIES THEOPHYLLINE DERIVATIVES AS ALDH1A1 INHIBITORS

In the present study, we explored a series of molecules with anticancer activity, so that qualitative and quantitative studies of the structure-activity relationship (SAR/QSAR) were performed on seventeen theophylline derivatives. These are inhibitors of ALDH1A1. The present study shows the importance of quantum chemical descriptors, constitutional descriptors and hydrophobicity to develop a better QSAR model, whose studied descriptors are LogP, MW, Pol, MR, S, V, HE, DM, EHOMO and ELUMO. A multiple linear regression (MLR) and artificial neural networks (ANN) procedure was used to design the relationships between molecular descriptors and the inhibition of ALDH1A1 by theophylline derivatives. The validation and good quality of the QSAR model are confirmed by a strong correlation between experimental and predicted activity.

Longitudinal, transverse and ultrasound vibration for the prediction of stiffness using models incorporating features in Pinus sylvestris timber

Non-destructive testing was used to predict the static modulus of elasticity (MOES) of Scots pine (Pinus sylvestris) timber from the northeast of Spain. Three vibration tests were performed, longitudinal, flatwise and edgewise, to obtain the dynamic modulus of elasticity (MOEdyn) based on the fundamental resonant frequencies. The MOEdyn was additionally obtained from ultrasound tests. Measurements of different features were performed of the various samples, which were also subjected to a bending test to find the MOES. Different types of models, simple linear regression (SLR), multiple linear regression (MLR) and artificial neural network (ANN), were generated to predict the MOES based on the study variables. The predictive capacity of the different models was analysed by comparing the root mean square error (RMSE) obtained using the tenfold cross-validation method. The vibration techniques showed a better MOES prediction than the ultrasound techniques. The MOEdyn obtained from the fundamental resonant frequency of the edgewise flexural vibration (MOEEV) was the variable that best predicted the MOES. The error of the SLR with MOEEV was not significantly improved by any other model, whether univariate or multivariate. The ANN-based models did not significantly improve the error of the MLR-based models.

Two-Stage Artificial Neural Network Regression Modelling for Wheezing Risk Factors Among Children - A Case Study of Gatundu Hospital, Kenya

In Kenya wheezing that leads to asthma development in most cases remain under-diagnosed and under-treated. Currently there is no public supported wheezing and asthma care programmes to optimize care for patients with asthma which greatly compounds diagnosis and treatment of the disease. The aim of this study is therefore to consider and analyse the covariates of childhood wheezing among children below 10 years of age in Kenya, a case study of Gatundu hospital in order to improve the provision of wheezing and asthma care services in medical facilities. The possible risk factors in the study are selected from three major groups of demographic, socioeconomic and geographical location factors related to childhood wheezing. The longitudinal secondary data obtained from Gatundu hospital in Kenya were collected and a total of 584 complete cases were recorded. The predictor variables considered in the study include age of children in months, gender, exclusive breastfeeding, exposure to tobacco smoking, difficult living conditions, residence, atopy, maternal age and preterm births. Due to the binary nature of response variable in which data is recorded as presence or absence of wheezing, the risk factors were modelled using multiple logistic regression and Artificial Neural Network Models. Simple random samples of sizes n = 385 without replacement were selected and p-values at 5% level of significance for the variables were recorded. In multiple logistic regression, the five variables identified as possible risk factors for modelling with p-value less than or equal to 0.05 were selected that includes age of children, exclusive breastfeeding, exposure to tobacco smoking, difficult living conditions and residence that recorded p-values of 0.0151, 0.0000, 0.0071, 0.0274 and 0.0410. The best multiple logistic linear regression model selected was based on Akaike Information Criterion (AIC) criterion that recorded null deviance, residual deviance and AIC of 502.44, 179.57 and 191.57 respectively. The precision and accuracy of the multiple logistic regression model were recorded as 89.2% and 93.3% respectively. The Artificial Neural Network was considered for modelling as well, the model with one-hidden layer with four neurons in the hidden layer recorded precision of 97.1% and accuracy of 39.4% while the rest of the models with one hidden layer recorded precision and accuracy of 0.0% and 65.1% respectively. The Artificial Neural Network model with two-hidden layers were also considered and the Network with one neuron in both layers was selected as better performing model with precision and accuracy of 88.2% and 93.3%. The developed two-stage logistic Artificial Neural Network was found to have better performance compared to multiple linear logistic regression and Artificial Neural Networks since it recorded precision and accuracy of 97.1% and 99.0% respectively and hence recommended for consideration in modelling the risk factor of wheezing among children in Kenya.

Prediction of the dynamic properties in rubberized concrete

Throughout the previous years, many efforts focused on incorporating non-biodegradable wastes as a partial replacement and sustainable alternative for natural aggregates in cement-based materials. Currently, rubberized concrete is considered one of the most important green concrete materials produced by replacing natural aggregates with rubber particles from old tires in a concrete mixture. The main benefits of this material, in addition to its importance in sustainability and waste management, comes from the ability of rubber to considerably damp vibrations, which, when used in reinforced concrete structures, can significantly enhance its energy dissipation and vibration behavior. Nowadays, the literature has many experimental findings that provide an interesting view of rubberized concrete's dynamic behavior. On the other hand, it still lacks research that collects, interprets, and numerically investigates these findings to provide some correlations and construct reliable prediction models for rubberized concrete's dynamic properties. Therefore, this study is intended to propose prediction approaches for the dynamic properties of rubberized concrete. As a part of the study, multiple linear regression and artificial neural networks will be used to create prediction models for dynamic modulus of elasticity, damping ratio, and natural frequency.