Artificial Neural Model Research Articles

Multi-objective optimization of CO2 ejector by combined significant variables recognition, ANN surrogate model and multi-objective genetic algorithm

The ejectors are crucial in enhancing the efficiency of the CO2-based refrigeration cycle. Although the ejector can be optimized by experimental and computational fluid dynamic simulation to improve its performance, these methods are time-consuming and complicated. This research aims to present a fast and systematic approach for optimizing CO2 ejector by combining variance analysis, surrogate model, and non-dominated sorting genetic algorithm. Firstly, the key geometric structures affecting the performance of ejector were determined by variance analysis. Secondly, the influence of key geometric structures and boundary conditions on ejector efficiency and entrainment ratio was analyzed by using computational fluid dynamic simulation, and the database was generated. Next, the artificial neural network surrogate model was established to forecast the ejector performance. Finally, the non-dominated sorting genetic algorithm was involved to optimize the ejector for maximizing ejector efficiency and entrainment ratio. The results show that the efficiencies of the optimized ejectors are above 42%, and the entrainment ratios exceed 0.7. Compared with the basic model, the average efficiencies have increased about 13.20%. When the pressure lift is 0.7 MPa, the entrainment ratios of the optimized ejectors are 0.696 (−20 °C ≤ Te < −15 °C), 0.82(-15 °C ≤ Te < −5 °C), 0.60 (−5 °C ≤ Te < 5 °C) and 0.90 (5 °C ≤ Te < 15 °C), respectively. The above research demonstrates that the success of this approach in addressing time-consuming multi-optimization problems. It offers a fast and systematic approach for the multi-objective optimization of CO2 ejector as a valuable reference for engineering applications.

VALIDATION OF KEY PERFORMANCE INDICATORS OF MOBILE TELECOMMUNICATION OPERATORS USING ENSEMBLE MODELS AND ARTIFICIAL NEURAL NETWORKS WITH NIGERIAN COMMUNICATION COMMISSION’S THRESHOLDS

This paper presents the comparative studies among the predictive models used for the validation of the key parameter indicators of mobile network operators with the Nigerian Communication Commission’s threshold. Four Key Performance Indicators were predicted using artificial neural networks and ensemble models which include bagging and LSBoost models. The Key Performance Indicators and weather parameters for six locations in Southwestern Nigeria were employed. MATLAB R2020a was employed to develop the three models. Microsoft Excel was used in the analysis of the dataset. The bagging model gave the best average compliance of 94% and 100% for CSSR and TCH Congestion Rate respectively while the ANN model yielded the best average compliance of 76.7% and 85.2% for DCR and SDCCH Congestion Rate respectively..

Valence-isomer selective cycloaddition reaction of cycloheptatrienes-norcaradienes

The rapid and precise creation of complex molecules while controlling multiple selectivities is the principal objective in synthetic chemistry. Combining data science and organic synthesis to achieve this goal is an emerging trend, but few examples of successful reaction designs are reported. We develop an artificial neural network regression model using bond orbital data to predict chemical reactivities. Actual experimental verification confirms cycloheptatriene-selective [6 + 2]-cycloaddition utilizing nitroso compounds and norcaradiene-selective [4 + 2]-cycloaddition reactions employing benzynes. Additionally, a one-pot asymmetric synthesis is achieved by telescoping the enantioselective dearomatization of non-activated benzenes and cycloadditions. Computational studies provide a rational explanation for the seemingly anomalous occurrence of thermally prohibited suprafacial [6 + 2]-cycloaddition without photoirradiation.

Establishment and analysis of artificial neural network diagnosis model for coagulation-related molecular subgroups in coronary artery disease.

Background: Coronary artery disease (CAD) is the most common type of cardiovascular disease and cause significant morbidity and mortality. Abnormal coagulation cascade is one of the high-risk factors in CAD patients, but the molecular mechanism of coagulation in CAD is still limited. Methods: We clustered and categorized 352 CAD paitents based on the expression patterns of coagulation-related genes (CRGs), and then we explored the molecular and immunological variations across the subgroups to reveal the underlying biological characteristics of CAD patients. The feature genes between CRG-subgroups were further identified using a random forest model (RF) and least absolute shrinkage and selection operator (LASSO) regression, and an artificial neural network prediction model was constructed. Results: CAD patients could be divided into the C1 and C2 CRG-subgroups, with the C1 subgroup highly enriched in immune-related signaling pathways. The differential expressed genes between the two CRG-subgroups (DE-CRGs) were primarily enriched in signaling pathways connected to signal transduction and energy metabolism. Subsequently, 10 feature DE-CRGs were identified by RF and LASSO. We constructed a novel artificial neural network model using these 10 genes and evaluated and validated its diagnostic performance on a public dataset. Conclusion: Diverse molecular subgroups of CAD patients may each have a unique gene expression pattern. We may identify subgroups using a few feature genes, providing a theoretical basis for the precise treatment of CAD patients with different molecular subgroups.

TEMPORAL ANALYSIS AND PREDICTIVE MODELING OF AMBIENT AIR QUALITY IN HULU LANGAT DISTRICT, SELANGOR, MALAYSIA: A CHEMOMETRIC APPROACH

One of the most important environmental problems facing the globe today is air pollution. The centre area for the local populace is the Hulu Langat district, which borders Kuala Lumpur, the capital. The purpose of this study is to look at how the ambient air quality varies in Hulu Langat, Selangor. The Air Quality Division of the Malaysian Department of Environment provided five years' worth of secondary data on the air quality at Hulu Langat. The database included five primary air pollutant characteristics sulphur dioxide (SO2), carbon monoxide (CO), ozone (O3), nitrogen dioxide (NO2), and particulate matter with a diameter of 10 microns or less (PM10), in addition to data from the Air Pollutant Index (API). Chemometric analysis was used to examine the results. According to the results, SO2, NO2 and PM10 had the greatest correlations with API readings. A statistical process known as statistical control (SPC) showed that certain PM10 values were over national recommendations and control limits. The artificial neural network method's air quality prediction model demonstrated good accuracy with real data (R2 = 0.9). The results of this investigation indicated a strong correlation between the Hulu Langat air quality data. In order to achieve sustainable environmental practices in the future, it is imperative to engage in extensive collaboration across environmental departments and relevant authorities and engage in continuous monitoring of air quality.

Alkali resistance prediction and degradation mechanism of basalt fiber: Integrated with artificial neural network machine learning model

Basalt fiber is commonly regarded as an alkaline corrosion-resistant material, capable of being transformed into various products (such as basalt fiber roving, chopped yarn and composite reinforcement). However, the main composition of the basalt fiber network skeleton consists of Si ∼ O bonds, which can still react with ∼OH in the alkaline environment. Nevertheless, there are differing viewpoints on the alkaline corrosion of basalt fibers within literatures. Therefore, this study aims to select three representative types of basalt fibers and compare them with two alkali-resistant glass fibers and one regular glass fiber. The attenuation mechanism of basalt fibers were investigated through orthogonal experiments, practical application scenarios and microscopic characterization methods. Additionally, we employed the Weibull model to analyze failure probabilities after erosion on basalt fibers while also applying a machine learning artificial neural network (ANN) model for predicting their alkali resistance. The results indicated that the tensile strength of basalt fiber tended to decrease and the alkali resistance of basalt fiber between alkali-resistant glass fiber and regular glass fiber in four alkaline solutions. The Weibull model also confirms that erosion increases failure probability of basalt fiber and glass fiber. Moreover, Si ∼ O, which forms the network reacted with OH-, resulting in a reduction in surface Si and Al elements content. It became possible to predict the alkali resistance of basalt fiber accurately by establishing an ANN model. Our study provide a theoretical foundation for predicting the lifespan of basalt fibers under corrosive conditions while offering guidance for enhancing their alkali resistance.

Model of Multi-Algorithmic-Based Optimization of 4D Approach Trajectory under Thunderstorm Weather

Thunderstorms are recognized as perilous meteorological phenomena characterized by irregular and nonlinear movement, posing significant risks to approaching aircraft and necessitating technical methods to ensure safety to the aviation operations. This research specifically addresses the challenges associated with aircraft during the approach segment and introduces a multialgorithmic model focusing on the optimization of 4D approach trajectory. Firstly, the artificial neural network intelligent model was used to predict the thunderstorm movement track. Secondly, the multialgorithmic model combined by the rapidly exploring random tree with artificial potential field was built to plan the trajectory of the approaching aircraft under thunderstorm weather, and then, the mean filter was adopted to smooth the simulated approaching trajectory. Finally, the reliability of the model with a real case study was demonstrated. After optimized simulation by predicting the thunderstorm weather and trajectory-optimized multialgorithmic model mentioned above, the approach trajectory can be outputted successfully, but with some distortions, postprocessing with the mean filter results in a remarkably smooth approach trajectory, providing enhanced feasibility and efficiency for pilots navigating through thunderstorm weather conditions. It is ultimately proved that refined 4D trajectory operations under hazardous weather conditions hold substantial significance in advancing aviation safety and operational effectiveness.

Comparison of an Ultrasound-Assisted Aqueous Two-Phase System Extraction of Anthocyanins from Pomegranate Pomaces by Utilizing the Artificial Neural Network-Genetic Algorithm and Response Surface Methodology Models.

As a by-product of pomegranate processing, the recycling and reuse of pomegranate pomaces (PPs) were crucial to environmentally sustainable development. Ultrasound-assisted aqueous two-phase extraction (UA-ATPE) was applied to extract the anthocyanins (ACNs) from PPs in this study, and the central composite design response surface methodology (CCD-RSM) and artificial neural network-genetic algorithm (ANN-GA) models were utilized to optimize the extraction parameters and achieve the best yield. The results indicated that the ANN-GA model built for the ACN yield had a greater degree of fit and accuracy than the RSM model. The ideal model process parameters were optimized to have a liquid-solid ratio of 49.0 mL/g, an ethanol concentration of 28 g/100 g, an ultrasonic time of 27 min, and an ultrasonic power of 330 W, with a maximum value of 86.98% for the anticipated ACN yield. The experimental maximum value was 87.82%, which was within the 95% confidence interval. A total of six ACNs from PPs were identified by utilizing UHPLC-ESI-HRMS/MS, with the maximum content of cyanidin-3-O-glucoside being 57.01 ± 1.36 mg/g DW. Therefore, this study has positive significance for exploring the potential value of more by-products and obtaining good ecological and economic benefits in the future.

Employing artificial neural networks for the assessment of the aqueous solubility of drug –like substances

This research has advanced Quantitative Structure-Property Relationship (QSPR) models for predicting the aqueous solubility of drug-like substances. By integrating multivariate regression and neural network techniques, the study utilized the backward algorithm to strategically select 2D and 3D molecular descriptors, resulting in the development of an optimal QSPRMLR model with k = 23. The artificial neural network regression model(QSPRANN), derived from selected descriptors of the multivariable linear regression model(QSPRMLR), demonstrated enhanced predictive capabilities for logS values in both validationand prediction groups, yielding SE values of 0.786 and 0.808, respectively. The QSPRANNsignificantly improved the overall predictability of the multivariate regression model. Statistical assessments of the QSPRANN model revealed SE = 0.699, R2train = 0.918, and Q2v = 0.878. The predicted logS values from the QSPRANN model align well with experimental data,confirming the reliability and accuracy of the developed model.

Comparison of Some Selected Models of Daily Water Supply in Abuja, Federa Capital Territory (FCT) Of Nigeria.

Water is considered as an essential commodity in human society. It has been observed that the basic standard of living of any Country can be measure through the effective portable water supply for consumption, sanitation and hygiene for the citizen. Its production and supply in the Federal Capital Territory (FCT), Abuja, Nigeria is a challenge, as dominant percentages of lower- class workforce live outside the FCTWB existing water network, and depend on borehole or tanker for water. The demand on the water supply system in FCT, Abuja has exceeded its initial design population, and the system is incomplete and operating with only 720 million liter of water per day (MLD) functioning plant. On this basis, this study seeks to identify the best model that fit daily water supply data in FCT, Abuja and to forecast the future daily water supply in this area. The comparing models were artificial neural, multiple linear and non-linear regression model were applied to the data set of daily water production, daily water treated, daily water supply, daily water leakage, Number of household connected to Federal Capital Territory Water board water network, Number of Commercial area connected to Federal Capital Territory Water board water network, and the Estimated population of Federal Capital Territory ,Abuja from (2013 to 2020), and it was emerged that the most adequate model for the data was Multiple linear regression model (MLR), with (R2 =1.000), (RMSE = 0.00282), and (MAE = 6.540). Artificial neural network records the high value of (RMSE = 432.4321), (MAE = 549.444) and (R2 =0.921), and multiple nonlinear regression record the highest value of (RMSE = 806.687), (MAE = 666.421) and (R2 = 0.999). From the statistical measure of goodness of fit, the three models compared results indicate that MLR model forecast are closely matching with actual observations values, artificial neural network model over-forecast some days volume of daily water supply by FCTWB, cooperation and multiple nonlinear regression model under-forecast some days volume of daily water supply by FCTWB, corporation. The three models compared depicts the influential variables of FCTWB Corporation daily water supply, (ANN = DWP, DWT), (MLR = DWT, DWL) and (MNLR = DWP, DWL), and their forecast graphs shows downward daily water supply in FCT, Abuja. It is recommended that the FCT, Abuja water Board Corporation should consider multiple linear regression (MLR) model and its forecasted values as a road map in its operations and planning toward water supply sustainability in FCT, Abuja.

Urban community governance and machine learning: practice and prospects for intelligent decision making

Abstract Urban community governance faces unprecedented challenges, but machine learning provides new ideas for it. The objective of this study is to examine the use of machine learning technology in urban community governance to enhance governance efficiency and decision-making quality. The study constructs an artificial neural network intelligent decision support model based on genetic algorithm optimization, which is based on the operational requirements of a smart decision support system. A weighted fuzzy inference network is further developed by the fusion of fuzzy logic and neural networks to enhance the system’s ability to deal with uncertainty and ambiguity. Next, prediction tests were conducted on the development levels of six communities to validate the model’s effectiveness. After 1686 training steps, the error squared SSE drops below 0.2%, according to the results. The composite index’s prediction error was 5.12%, while the minimum error was −1.79%. The predicted rankings of the communities did not change from the actual ones, which was in line with the normal trend, and the algorithmic model achieved better prediction results. This study not only provides a new intelligent decision support tool for community governance but also sets a theoretical and practical foundation for the intelligent development of urban community governance in the future.

Design and optimization of the Teaching evaluation system based on artificial intelligence

Abstract In today’s highly developed information society, the construction work of educational informatization has become the focus of the future development of major universities. This paper combines artificial neural networks and UML software modeling technologies to design a teaching evaluation system using artificial neural network technology. The system requirements are analyzed from three aspects: system feasibility, functional requirements, and neural network evaluation function. The proposed system performance requirements are based on these three aspects. The neural network approximation problem can be solved using the gradient descent method based on the BP neural network model. After a series of operations, such as data preprocessing, the Design of the teaching evaluation system is completed, realizing the joint role of teaching and neural network evaluation module, and at the same time, proposing a system optimization decision for the teaching quality aspect. The teaching evaluation system designed in this study passed the test as the average response time of the whole system was 94.366 seconds when the number of users was 100, and there was no phenomenon such as transaction unresponsiveness. After the use of the teaching system, the feedback from the students’ use shows that the number of computer science students who mastered more than 80% of the system concepts is 42, and the rest of the knowledge is concentrated in the number of people who mastered 40% to 80%.

SPADA: A Toolbox of Designing Soft Pneumatic Actuators for Shape Matching Based on Surrogate Modeling.

Soft pneumatic actuators (SPAs) produce motions for soft robots with simple pressure input, however, they require to be appropriately designed to fit the target application. Available design methods employ kinematic models and optimization to estimate the actuator response and the optimal design parameters to achieve a target actuator's shape. Within SPAs, bellow SPAs excel in rapid prototyping and large deformation, yet their kinematic models often lack accuracy due to the geometry complexity and the material nonlinearity. Furthermore, existing shape-matching algorithms are not providing an end-to-end solution from the desired shape to the actuator. In addition, despite the availability of computational design pipelines, an accessible and user-friendly toolbox for direct application remains elusive. This article addresses these challenges, offering an end-to-end shape-matching design framework for bellow SPAs to streamline the design process, and the open-source toolbox SPADA (Soft Pneumatic Actuator Design frAmework) implementing the framework with a graphic user interface for easy access. It provides a kinematic model grounded on a modular design to improve accuracy, finite element method (FEM) simulations, and piecewise constant curvature (PCC) approximation. An artificial neural network-trained surrogate model, based on FEM simulation data, is trained for fast computation in optimization. A shape-matching algorithm, merging three-dimensional (3D) PCC segmentation and a surrogate model-based genetic algorithm, identifies optimal actuator design parameters for desired shapes. The toolbox, implementing the proposed design framework, has proven its end-to-end capability in designing actuators to precisely match two-dimensional shapes with root-mean-squared-errors of 4.16, 2.70, and 2.51 mm, and demonstrating its potential by designing a 3D deformable actuator.

Relay model of a fading neuron

This study is a continuation of M. M. Preobrazhenskaya’s work “Relay System of Differential Equations with Delay as a Perceptron Model”, which aimed to combine approaches related to artificial neural networks and modeling biological neurons using differential equations with delay. The model of a single neuron was proposed, which allows for the existence of special modes called “aging” and “dying” behavior of the neuron. The study found a certain range of parameters where the “dying” mode of the neuron exists and numerically demonstrated the existence of the “aging” mode. Purpose. We will unify the concepts of “aging” and “dying” neurons into the term “freezing” neuron. For this neuron, we will analytically construct a solution and find the range of parameters for its existence and stability, which will extend the results of the reference article. Methods. To study this model, an auxiliary equation obtained by exponential substitution in the original equation is considered. Then, the method of step integration of a differential equation with delay and the introduction of additional functions are used. Results. A solution of the “freezing” neuron type for the original model is constructed, and the range of parameters for the existence and stability of this solution is described. Conclusion. The study obtained an extension of results for solutions of a special type in the model proposed by M. M. Preobrazhenskaya.

A Physical-Based Artificial Neural Networks Compact Modeling Framework for Emerging FETs

We report a compact modeling framework based on the Grove–Frohman (GF) model and artificial neural networks (ANNs) for emerging gate-all-around (GAA) MOSFETs. The framework consists of two ANNs; the first ANN constructed with the drain current model not only can capture the main trend of device <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\textit{I}$</tex-math> </inline-formula> – <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\textit{V}$</tex-math> </inline-formula> characteristics but also can predict its variation even when the amount of training data for the ANN is insufficient or outside the range of applied biases. The second one is then designed to improve the model accuracy by further minimizing the errors between the target and the model outputs. We implement the proposed framework to accurately model emerging GAA nanosheet (NS) MOSFETs and complementary FETs (CFETs) without suffering from divergent issues in circuit simulation. In addition, nonphysical behaviors, such as nonzero current at zero bias, do not occur in the modeling framework. Compared to recently reported machine-learning (ML) models, our approach can achieve a similar level of model accuracy with merely 20% amount of the training data.

Testing Game Theory of Mind Models for Artificial Intelligence

In this article, we investigate the relative performance of artificial neural networks and structural models of decision theory by training 69 artificial intelligence models on a dataset of 7080 human decisions in extensive form games. The objective is to compare the predictive power of AIs that use a representation of another agent’s decision-making process in order to improve their own performance during a strategic interaction. We use human game theory data for training and testing. Our findings hold implications for understanding how AIs can use constrained structural representations of other decision makers, a crucial aspect of our ‘Theory of Mind’. We show that key psychological features, such as the Weber–Fechner law for economics, are evident in our tests, that simple linear models are highly robust, and that being able to switch between different representations of another agent is a very effective strategy. Testing different models of AI-ToM paves the way for the development of learnable abstractions for reasoning about the mental states of ‘self’ and ‘other’, thereby providing further insights for fields such as social robotics, virtual assistants, and autonomous vehicles, and fostering more natural interactions between people and machines.

Mathematical modeling and optimization of gas foil bearings-rotor system in hydrogen fuel cell vehicles

Gas foil bearings-rotor system is particularly crucial to affect the performance and energy efficiency of the air compressor for hydrogen fuel cell vehicles. However, the existing air compressors have the problem of poor stability and high energy consumption. To address this issue, the systematic multi-optimization method of the bearings-rotor system considering both the larger load and lower power consumption based on artificial neural network intelligent regression model and nondominated sorting genetic algorithms III is presented in this work for the first time. The optimal bearings-rotor system with a load capacity of 192.03 N and a power consumption of 15.38W is obtained. Under the optimum system, the input factors combination composed of the nominal clearance of 7.9 μm, foil thickness of 0.17 mm, half bump length of 0.942 mm, friction coefficient of 0.047, and rotation speed of 28462 rpm is determined. Compared to the average value of the original sample, the optimal system increases by 3.49 times in load capacity while decreasing by 30 % in power consumption. These findings and methodology are highly favorable for hydrogen energy vehicles with respect to improving stability and energy efficiency.

DDOS Attack Prediction using Deep Learning

DDoS attacks on distributed networks are another name for distributed network attacks. These attacks exploit specific constraints that are applicable to every arrangement asset, like the authorized organization’s website framework. This proposes a deep learning approach for predicting DDoS attacks. Deep learning methods were developed for the purpose of classifying attacks. The deep learning method includes the classification methods Multilayer Perceptron and Long Short-Term Memory Grids. The datasets are pre-processed using StandardScaler. Distributed denial-of-service attack detection and categorization are aided by deep learning techniques. MLP is an artificial neural network feed-forward model that maps input sets to output sets. The LSTM classifier is designed to classify faults based on this proposed project produced a confusion matrix to identify the performance of the model, and it is used for fault diagnosis in that region. This implemented in Python software.

Screening and identification of unknown chemical contaminants in food based on liquid chromatography–high-resolution mass spectrometry and machine learning

Unknown or unexpected chemical contaminants and/or their transformation products in food that may be harmful to humans need to be discovered for comprehensive safety evaluation. Liquid chromatography–high-resolution mass spectrometry (LC-HRMS) is a powerful tool for detecting chemical contaminants in food samples. However, identifying all of peaks in LC-HRMS is not possible, but if class information is known in advance, further identification will become easier. In this work, a novel MS2 spectra classification-driven screening strategy was constructed based on LC-HRMS and machine learning. First, the classification model was developed based on machine learning algorithm using class information and experimental MS2 data of chemical contaminants and other non-contaminants. By using the developed artificial neural network classification model, in total 32 classes of pesticides, veterinary drugs and mycotoxins were classified with good prediction accuracy and low false-positive rate. Based on the classification model, a screening procedure was developed in which the classes of unknown features in LC-HRMS were first predicted through the classification model, and then their structures were identified under the guidance of class information. Finally, the developed strategy was tentatively applied to the analysis of pork and aquatic products, and 8 chemical contaminants and 11 transformation products belonging to 8 classes were found. This strategy enables screening of unknown chemical contaminants and transformation products in complex food matrices.

Artificial neural network surrogate modeling for uncertainty quantification and structural optimization of reinforced concrete structures

AbstractOptimization approaches are important to design sustainable structures. In structural mechanics, different design objectives can be defined, for example, to minimize the required construction material or to maximize the structural durability. In this paper, the durability of a reinforced concrete (RC) structure is assessed by advanced finite element (FE) models to simulate the cracking behavior and the chloride transport process. The corrosion initiation time is used as durability measure to be maximized within an optimization approach, where the concrete cover is defined as design variable. The variability of structural loads and material parameters and unavoidable construction imprecision leads to a probabilistic reliability and durability assessment, where aleatory as well as epistemic uncertainties are quantified by random variables, intervals and probability‐boxes. The FE simulation models cannot directly be applied to structural analyses and optimizations with polymorphic uncertain parameters and design variables because of the high computational demand of the multi‐loop algorithm (Monte Carlo simulation, interval analysis, global optimization). In this paper, a new surrogate modeling strategy is presented, where artificial neural networks are trained sequentially to speed‐up the coupled mechanical and transport simulation FE models. The new approach is applied to the uncertainty quantification and the structural durability optimization of a RC structure.