Artificial Neuronal Network Research Articles

Prediction of Molecular Weight of Petroleum Fluids by Empirical Correlations and Artificial Neuron Networks

The exactitude of petroleum fluid molecular weight correlations affects significantly the precision of petroleum engineering calculations and can make process design and trouble-shooting inaccurate. Some of the methods in the literature to predict petroleum fluid molecular weight are used in commercial software process simulators. According to statements made in the literature, the correlations of Lee–Kesler and Twu are the most used in petroleum engineering, and the other methods do not exhibit any significant advantages over the Lee–Kesler and Twu correlations. In order to verify which of the proposed in the literature correlations are the most appropriate for petroleum fluids with molecular weight variation between 70 and 1685 g/mol, 430 data points for boiling point, specific gravity, and molecular weight of petroleum fluids and individual hydrocarbons were extracted from 17 literature sources. Besides the existing correlations in the literature, two different techniques, nonlinear regression and artificial neural network (ANN), were employed to model the molecular weight of the 430 petroleum fluid samples. It was found that the ANN model demonstrated the best accuracy of prediction with a relative standard error (RSE) of 7.2%, followed by the newly developed nonlinear regression correlation with an RSE of 10.9%. The best available molecular weight correlations in the literature were those of API (RSE = 12.4%), Goosens (RSE = 13.9%); and Riazi and Daubert (RSE = 15.2%). The well known molecular weight correlations of Lee–Kesler, and Twu, for the data set of 430 data points, exhibited RSEs of 26.5, and 30.3% respectively.

Evaluation of Materials and Structures with a Multistatic Ultra-Wideband Impulse Radar: A Concept Validation

This document describes the results of the study contributing to the methods and tools applicable in plastic waste sorting systems that exploit the multistatic ultra-wideband impulse radar enforced with a deep learning signal processing back-end. The novelty of the research is the use of synthetic data for the development of a trained neural network before real data are available, and the use of a multistatic radar for the improvement of the training data set. The study results are described in multiple publications; the current paper shows the applicability of the described approach. The main results are as follows: a monostatic impulse radar can be used for the determination of material properties, such as thickness, dielectric permittivity, and losses, with limited accuracy; multistatic radar configuration increases the accuracy of the material property estimation; an open source finite difference time domain simulator can be used to simulate electromagnetic wave propagation in dielectric structures in order to generate synthetic data for development of optimized artificial neuron network structures used for the estimation of dielectric material properties, and the developed network can successfully be used for multistatic radar data processing.

Evaluation and Development of Pedotransfer Functions and Artificial Neural Networks to Saturation Moisture Content Estimation

Modeling of irrigation and agricultural drainage requires knowledge of the soil hydraulic properties. However, uncertainty in the direct measurement of the saturation moisture content (θs) has been generated in several methodologies for its estimation, such as Pedotransfer Functions (PTFs) and Artificial Neuronal Networks (ANNs). In this work, eight different PTFs were developed for the (θs) estimation, which relate to the proportion of sand and clay, bulk density (BD) as well as the saturated hydraulic conductivity (Ks). In addition, ANNs were developed with different combinations of input and hidden layers for the estimation of θs. The results showed R2 values from 0.9046≤R2≤0.9877 for the eight different PTFs, while with the ANNs, values of R2>0.9891 were obtained. Finally, the root-mean-square error (RMSE) was obtained for each ANN configuration, with results ranging from 0.0245≤RMSE≤0.0262. It was found that with particular soil characteristic parameters (% Clay, % Silt, % Sand, BD and Ks), accurate estimate of θs is obtained. With the development of these models (PTFs and ANNs), high R2 values were obtained for 10 of the 12 textural classes.

Optimal Artificial Neural Network using Particle Swarm Optimization

Artificial neuron networks (ANNs) are widely used for data analyticS in broad areas of engineering applications and commercial services. The ANN has one to two hidden layers. In advanced ANN, multiple-layer ANN is used where the network extracts different features until it can recognize what it is looking for through deep learning approaches. Usually, a backpropagation algorithm is used to train the network and fix weights and biases associated with each network neuron. This paper proposes a particle swarm optimization (PSO) based algorithm for training ANN for better performance and accuracy. Two types of ANN models and their training using PSO have been developed. The performance of the developed models has been analyzed on a standard dataset. Also, the effectiveness and suitability of the developed approach have been demonstrated through statistics of the obtained results.

Applied machine learning for prediction of waste plastic pyrolysis towards valuable fuel and chemicals production

Pyrolysis is a suitable conversion technology to address the severe ecological and environmental hurdles caused by waste plastics' ineffective pre- and/or post-user management and massive landfilling. By using machine learning (ML) algorithms, the present study developed models for predicting the products of continuous and non-catalytically processes for the pyrolysis of waste plastics. Along with different input datasets, four algorithms, including decision tree (DT), artificial neuron network (ANN), support vector machine (SVM), and Gaussian process (GP), were compared to select input variables for the most accurate models. Among these algorithms, the DT model exhibited generalisable and satisfactory accuracy (R2 > 0.99) with training data. The dataset with the elemental composition of waste plastics achieved better accuracy than that with the plastic-type for predicting liquid yields. These observations allow the predictions by the data from ultimate analysis when inaccessible to the plastic-type data in unknown plastic wastes. Besides, the combination of ultimate analysis input and the DT model also achieved excellent accuracy in liquid and gas composition predictions.

Integrated analysis of endoplasmic reticulum stress regulators' expression identifies distinct subtypes of autism spectrum disorder.

Endoplasmic reticulum (ER) stress has been demonstrated to play important roles in a variety of human diseases. However, their relevance to autism spectrum disorder (ASD) remains largely unknown. Herein, we aimed to investigate the expression patterns and potential roles of the ER stress regulators in ASD. The ASD expression profiles GSE111176 and GSE77103 were compiled from the Gene Expression Omnibus (GEO) database. ER stress score determined by the single sample gene set enrichment analysis (ssGSEA) was significantly higher in ASD patients. Differential analysis revealed that there were 37 ER stress regulators dysregulated in ASD. Based on their expression profile, the random forest and artificial neuron network techniques were applied to build a classifier that can effectively distinguish ASD from control samples among independent datasets. Weighted gene co-expression network analysis (WGCNA) screened out the turquoise module with 774 genes was closely related to the ER stress score. Through the overlapping results of the turquoise module and differential expression ER stress genes, hub regulators were gathered. The TF/miRNA-hub gene interaction networks were created. Furthermore, the consensus clustering algorithm was performed to cluster the ASD patients, and there were two ASD subclusters. Each subcluster has unique expression profiles, biological functions, and immunological characteristics. In ASD subcluster 1, the FAS pathway was more enriched, while subcluster 2 had a higher level of plasma cell infiltration as well as the BCR signaling pathway and interleukin receptor reaction reactivity. Finally, the Connectivity map (CMap) database was used to find prospective compounds that target various ASD subclusters. A total of 136 compounds were significantly enriched. In addition to some specific drugs which can effectively reverse the differential gene expression of each subcluster, we found that the PKC inhibitor BRD-K09991945 that targets Glycogen synthase kinase 3β (GSK3B) might have a therapeutic effect on both ASD subtypes that worth of the experimental validation. Our finding proved that ER stress plays a crucial role in the diversity and complexity of ASD, which may inform both mechanistic and therapeutic assessments of the disorder.

Forecasting Suitable Supplier for Construction Project Using Machine Learning Techniques

The aim of the research is to forecast the suitable suppliers for construction project using machine learning techniques. Firstly the librarian studies were conducted and research gap is extracted. Then innovation was determined. Based on the innovation a model for suitable supplier forecasting for construction project using machine learning techniques were provided. The model includes 12 entry variables and 1 output variable that include supplier performance. The model using 2 algorithm of artificial neuron network and support vector machine were conducted and the most influencing factors were determined using decision tree algorithm. The general comparison between artificial neuron network and support vector machine indicate the better performance of artificial neuron network based on decision tree. Based on decision tree results we can say that the supplier company income is considered as most important variable. The order change cost variable play the separator role in lower level. The life variables of companied and guarantees after company income and change cost of order play the main role.

Can Presurgical Interhemispheric EEG Connectivity Predict Outcome in Hemispheric Surgery? A Brain Machine Learning Approach.

Hemispherotomy (HT) is a surgical option for treatment of drug-resistant seizures due to hemispheric structural lesions. Factors affecting seizure outcome have not been fully clarified. In our study, we used a brain Machine Learning (ML) approach to evaluate the possible role of Inter-hemispheric EEG Connectivity (IC) in predicting post-surgical seizure outcome. We collected 21 pediatric patients with drug-resistant epilepsy; who underwent HT in our center from 2009 to 2020; with a follow-up of at least two years. We selected 5-s windows of wakefulness and sleep pre-surgical EEG and we trained Artificial Neuronal Network (ANN) to estimate epilepsy outcome. We extracted EEG features as input data and selected the ANN with best accuracy. Among 21 patients, 15 (71%) were seizure and drug-free at last follow-up. ANN showed 73.3% of accuracy, with 85% of seizure free and 40% of non-seizure free patients appropriately classified. The accuracy level that we reached supports the hypothesis that pre-surgical EEG features may have the potential to predict epilepsy outcome after HT. The role of pre-surgical EEG data in influencing seizure outcome after HT is still debated. We proposed a computational predictive model, with an ML approach, with a high accuracy level.

A Scientific Perspective on Using Artificial Intelligence in Sustainable Urban Development

Digital transformation (or digitalization) is the process of continuous further development of digital technologies (such as smart devices, cloud services, and Big Data) that have a lasting impact on our economy and society. In this manner, digitalization is a huge driver for permanent change, even in the field of Sustainable Urban Development. In the wake of digitalization, expectations are changing, placing pressure at the societal level on the design and development of smart environments for everything that means Sustainable Urban Development. In this sense, the solution is the integration of Artificial Intelligence into Sustainable Urban Development, because technology can simplify people’s lives. The aim of this paper is to ascertain which Sustainable Urban Development dimensions are taken into account when integrating Artificial Intelligence and what results can be achieved. These questions formed the basic framework for this research article. In order to make the current state of Artificial Intelligence in Sustainable Urban Development as a snapshot visible, a systematic review of the current literature between 2012 and 2022 was conducted. The data were collected and analyzed using PRISMA. Based on the studies identified, we found a significant growth in studies, starting in 2018, and that Artificial Intelligence applications refer to the Sustainable Urban Development dimensions of environmental protection, economic development, social justice and equity, culture, and governance. The used Artificial Intelligence techniques in Sustainable Urban Development cover a broad field of Artificial Intelligence, such as Artificial Intelligence in general, Machine Learning, Deep Learning, Artificial Neuronal Networks, Operations Research, Predictive Analytics, and Data Mining. However, with the integration of Artificial Intelligence in Sustainable Urban Development, challenges are marked out. These include responsible municipal policies, awareness of data quality, privacy and data security, the formation of partnerships among stakeholders (e.g., local citizens, civil society, industry, and various levels of government), and transparency and traceability in the implementation and rollout of Artificial Intelligence. A first step was taken towards providing an overview of the possible applications of Artificial Intelligence in Sustainable Urban Development. It was clearly shown that Artificial Intelligence is also gaining ground in this sector.

Research on Application of artificial Neural Network in econometrics

As a fringe subject of artificial intelligence and systems engineering, artificial neuron network can not only discover more valuable data information, but also accelerate the calculation speed of data information in econometrics. With the rapid development of econometrics, the artificial neural network method has received wide attention of scholars research at home and abroad, compared with the traditional econometric method, artificial neural network algorithm with adjustable parameters and highly nonlinear simulation operation ability, self-learning and self-organization can function in dealing with practical problems, present a're likelier to carry a strong and adaptability. Therefore, on the basis of understanding the research status of econometrics and artificial neural networks, this paper mainly discusses how to apply artificial neural networks in econometrics, and makes clear the future application direction from the perspective of the development of the new era.

Several machine learning techniques comparison for the prediction of the uniaxial compressive strength of carbonate rocks

In engineering practices, it is critical and necessary to either measure or estimate the uniaxial compressive strength (UCS) of the rock. Measuring the UCS of rocks requires comprehensive studies in the field and in the laboratory for the rock block sampling, coring, and testing. These studies are time-consuming, expensive and go through difficult processes. Alternatively, the UCS can either be estimated by empirical relationships or predictive models with various measured mechanical and physical parameters of the rocks. Previous studies used different methods to predict UCS, including least squares regression techniques (MLR), adaptive neuro-fuzzy inference system (ANFIS), Sequential artificial neuron networks (SANN), etc. This study is intended to estimate the UCS of the carbonate rock by using a simple, measured Schmidt Hammer (SHVC) test on core sample and a unit weight (γn) of carbonate rock. Principal components regression (PCR), MLR, SANN, and ANFIS are employed to predict the UCS. We are not aware of any study compared the performances of these methods for the prediction of the UCS values. Based on the root mean square error, mean absolute error and R2, the Sequential artificial neural network has a slight advantage against the other three models.

Life expectancy at birth in RF regions with diriment sanitary-epidemiological wellbeing and different lifestyles.management reserves

The article focuses on estimating reserves of growth in life expectancy at birth (LEB) for the RF population in regions with different sanitary-epidemiological wellbeing and people’s lifestyles. The existing trends in the country development within the regional context corroborate relevance of the present study. The methodical approach includes use of factor and cluster analysis, artificial neuron networks, and scenario forecasting. Activities performed by Rospotrebnadzor within its authority produce positive modifying effects on LEB as an integral health indicator. Differentiated contribution made by these activities to achieving regional target LEB levels by 2024 (COVID-related processes excluded) amounts to 8–62 % as per the group of indicators that describes a sanitary-epidemiological situation on a given territory and 5–45 % as per the group of lifestyle-related indicators. We identified priority factors for each of four types of regions; these factors provide the maximum positive effect on LEB. Working conditions for working population, quality of drinking water, ambient air and nonfoods are priority manageable factors in regions where the sanitary-epidemiological situation is the most unfavorable. Levels of alcohol and food consumption, balanced diets and people’s physical activity are the priority manageable factors in regions with the most unfavorable lifestyle-related indicators. The study revealed that additional LEB growth would be secured if the targets set within national projects were achieved. By 2024, this additional LEB growth would equal 6–420 days and 107–659 days accordingly given the existing trends and regional differentiation as regards improved sanitary-epidemiological situation in regions and people’s lifestyles. Improved working conditions, better quality of drinking water and ambient air are reserves of LEB growth for all types of the RF regions in short and middle-term. A potential reserve of LEB growth and priority determinants were identified for each type of regions. These identified national and regional determinants should be considered when building an optimization model of LEB management allowing for reserves of its growth. The study results develop the authors’ methodical approach to estimating potential LEB growth based on scenario modeling; they are consistent with the results obtained by other relevant studies. We have identified limitations of the present study as well as prospects and trends for future research.

Ожидаемая продолжительность жизни в субъектах Российской Федерации с различным уровнем санитарно-эпидемиологического благополучия и образа жизни населения. резервы управления

The article focuses on estimating reserves of growth in life expectancy at birth (LEB) for the RF population in regions with different sanitary-epidemiological wellbeing and people’s lifestyles. The existing trends in the country development within the regional context corroborate relevance of the present study. The methodical approach includes use of factor and cluster analysis, artificial neuron networks, and scenario forecasting. Activities performed by Rospotrebnadzor within its authority produce positive modifying effects on LEB as an integral health indicator. Differentiated contribution made by these activities to achieving regional target LEB levels by 2024 (COVID-related processes excluded) amounts to 8–62 % as per the group of indicators that describes a sanitary-epidemiological situation on a given territory and 5–45 % as per the group of lifestyle-related indicators. We identified priority factors for each of four types of regions; these factors provide the maximum positive effect on LEB. Working conditions for working population, quality of drinking water, ambient air and nonfoods are priority manageable factors in regions where the sanitary-epidemiological situation is the most unfavorable. Levels of alcohol and food consumption, balanced diets and people’s physical activity are the priority manageable factors in regions with the most unfavorable lifestyle-related indicators. The study revealed that additional LEB growth would be secured if the targets set within national projects were achieved. By 2024, this additional LEB growth would equal 6–420 days and 107–659 days accordingly given the existing trends and regional differentiation as regards improved sanitary-epidemiological situation in regions and people’s lifestyles. Improved working conditions, better quality of drinking water and ambient air are reserves of LEB growth for all types of the RF regions in short and middle-term. A potential reserve of LEB growth and priority determinants were identified for each type of regions. These identified national and regional determinants should be considered when building an optimization model of LEB management allowing for reserves of its growth. The study results develop the authors’ methodical approach to estimating potential LEB growth based on scenario modeling; they are consistent with the results obtained by other relevant studies. We have identified limitations of the present study as well as prospects and trends for future research.

Performance prediction of parallel applications using artificial neuronal network and graph representation

SummaryModeling and predicting the performance of HPC applications is exceedingly important for several purposes. These incorporate scheduling and managing tasks, understanding application behavior, and estimating resource requirements. Many issues impact the performance of parallel applications, including data decomposition, load balancing, and inter processors communication. Predicting the performance of parallelism accurately is a challenging task, especially since it depends on several hardware and software parameters that are difficult to identify. The graph representation is an efficient way to model a parallel application. Based on this representation, this study purports to predict the optimal number of partitions (processors) to run efficiently a parallel application on multi‐core architectures using an artificial neural network. The numerical simulation applications are modeled as a graph of tasks and their associated data. Using the characteristics of the graphs as inputs of the ANN model, we obtained satisfactory results with an accuracy of 91% for the optimal number of processors and 93% for the maximum speedup.

Enhancing wind power forecast accuracy using the weather research and forecasting numerical model-based features and artificial neuronal networks

Forecasting with accuracy the quantity of energy produced by wind power plants is crucial to enabling its optimal integration into power systems and electricity markets. Despite the remarkable improvements in the wind forecasting systems in recent years, large errors can still be observed, especially for longer time horizons. This work focuses on identifying new numerical weather prediction (NWP)-based features aiming to improve the overall quality of wind power forecasts.The methodology also incorporates a sequential forward feature selection algorithm. This algorithm was designed to select iteratively the meteorological features which minimize the wind forecast errors.The methodology was applied separately to seven wind parks in Portugal with different climate characteristics. The proposed approach allowed a reduction between 13% and 37% in the root mean square errors of wind power forecasts, compared with a baseline scenario. While the meteorological features identified for each wind park showed similarities within regions with analogous wind power generation profiles, each wind park required specific meteorological parameters as input data to obtain the best performance. Thus, the results show to be crucial to select the most relevant features of a specific site to maximize the accuracy of a wind power forecast.

Prediction of chitosan modification based on artificial neural network

As a high-absorption, low-cost adsorbent, chitosan has a wide range of applications in adsorbing pigments and dyes. In this paper, the artificial neuron network is used to study the modification of chitosan, and the modification of chitosan is predicted through the artificial neuron network. Moreover, this paper uses neural network to combine the prediction results of multiple gray prediction models, and uses the prediction results of multiple gray prediction models as the input variables of the neural network prediction model. In addition, this paper uses the good nonlinear processing ability of neural network to obtain the weight of each gray model, and expands the prediction based on some experiments. The research results show that the method proposed in this paper has a certain effect.

Probability Prediction Approach of Fatigue Failure for the Subsea Wellhead Using Bayesian Regularization Artificial Neural Network

The subsea wellhead (SW) system is a crucial connection between blowout preventors (BOPs) and subsea oil and gas wells. Excited by cyclical fatigue dynamic loadings, the SW is prone to fatigue failure, which would lead to the loss of well integrity and catastrophic accidents. Based on the Bayesian Regularization Artificial Neuron Network (BRANN), this paper proposes an efficient probability approach to predict the fatigue failure probability of SW during its entire life. In the proposed method, the BRANN fatigue damage (BRANN-FD) model reflecting the non-linear relationship between the input and output data was developed by the limited fatigue damage analysis data, which was utilized to generate thousands of non-numerical fatigue damage data of SW rapidly. Combining parametric and non-parametric estimation methods, the probability density function (PDF) of SW fatigue damage was determined to calculate the accumulation fatigue damage during service life. Using the logistic regression, the fatigue failure probability of SW was predicted. The application of the proposed approach was demonstrated by a case study. The results illustrated that the fatigue damage of SW would be viewed as obeying the Lognormal distribution, which could be used to obtain the accumulation fatigue damage in operation conveniently. Furthermore, the fatigue failure probability of SW nonlinearly increased with the increment in the accumulation fatigue damage of SW, which could be helpful to ensure the operation safety of SW in deepwater oil and gas development, especially for aged wellhead.

NUMERICAL INVESTIGATIONS OF A FRACTIONAL NONLINEAR DENGUE MODEL USING ARTIFICIAL NEURAL NETWORKS

The aim of this study is to perform the numerical investigations of a fractional nonlinear dengue model using artificial neuron networks (ANNs) along with the Levenberg–Marquardt backpropagation (LMB), i.e. ANNs. The fractional nonlinear dengue model is divided into five classes. The stochastic-based ANNs-LMB scheme is pragmatic on three variants of authentication, training and testing. The data magnitudes for three different variations based on the fractional nonlinear dengue model are selected as 80% for training, 10% for both testing and validation. The numerical procedures of the fractional nonlinear dengue model will be performed through ANNs-LMB and comparative investigations using the reference values that are calculated on the basis of Adams–Bashforth–Moulton scheme. The solution of the fractional nonlinear dengue model is obtained through the ANNs-LMB to reduce the mean square error (MSE). To authenticate the capability and efficiency of the proposed ANNs-LMB, the obtained numerical measures of correlation, MSE results, regression and error histograms (EHs) are provided.

USE OF PYTHON, MATLAB, AND R FOR DEVELOPING ARTIFICIAL NEURAL NETWORK FOR IDENTIFICATION TYPE IN OVERHEAD TRANSMISSION LINES OF FAULT

Due to the increased devouring of electricity by a consumer, generating stations must provide an uninterrupted supply of electricity to load. For that intend, many steps had been taken for the detection of fault locations in overhead lines. Whenever any fault takes place in the transmission line, Fault Passage Indicators quickly detect fault and help the crew for clearing of fault as soon as possible. This will help in maintaining the constant supply of electricity to enduser equipment and increase the reliability of the load. These can be installed at different points for better operation in line. But all these traditional methods for detection of faults are time-consuming, hence with developing trends in Machine Learning and Artificial Neuron networks their concept can be used for the detection of faults in transmission lines. This report deals with the development of Ann for detection and identification a fault type in the 220kv line. As of 2020, python with Keras and Tensor Flow API is considered the best method for developing Ann models, hence a neural network is developed with them for the classification and detection of a fault utilizing Fast Fourier Transform. A Radial Basics Neural Network is formulated in MATLAB utilizing wavelet transform. A network is trained utilizing voltage sag and swell phenomena with a Resilient back propagation network in R language. At last, this report assists in understanding the nature of fault, occurring in transmission lines.

A framework for physics-driven generation of feature data for strain-based damage detection in aerospace sandwich structures

In recent years, structural health monitoring has been increasingly applied to composite sandwich structures, as typically used in aerospace applications. In addition, machine learning approaches are increasingly popular for damage detection, localization and size estimation, due to their great advantages in pattern recognition and anomaly detection. However, a major disadvantage of machine learning techniques is that these algorithms generally require large amounts of realistic data. In general, these data are expensive or even impossible to obtain within a feasible time. In order to overcome this hindrance, this work introduces a computationally inexpensive framework for physics-driven feature generation of strain data for the training of ML-based SHM methods using sub-structuring and the concept of reanalysis. First, the global FE model is subdivided into a monitored part, i.e., a smaller submodel, and a global model. Second, the stiffness matrix of the submodel is extracted from the finite element software. Then, static condensation is performed to further reduce the computational effort. Afterwards, selected eigenvectors are derived in terms of displacements of master nodes and the corresponding strains are calculated. Finally, a statistically varied linear combination between the different characteristic eigenvector load cases is performed based on the superposition principle. This procedure enables the efficient generation of a large number of different physics-driven determined strain solutions for a subsequent training of a ML algorithms. The proposed framework is evaluated by means of a damage detection approach, based on an artificial neuronal network classifier algorithm. The applied approach utilizes strain measurements from selected positions as physical quantity and is demonstrated using a composite sandwich structure imitating an aircraft spoiler. The key principle of the damage detection algorithm is based on the fact that a change in the relationship between sensors indicates the presence of damage. Additionally, to the numerical healthy strains resulting from the framework, synthetically generated damage data are used for training the neuronal network classifier. The synthetic data are obtained by statistical modifications of the healthy strains, to avoid time-consuming and expensive damage simulations. The feature generation framework and health monitoring approach are validated using experiments and numerical simulations of a glass fiber reinforced polymer sandwich structure with a hole considered as damage. The presented numerical and the experimental results clearly show the high potential for the efficient approach for damage detection in a sandwich structure.