Artificial Neural Model Research Articles

Optimization artificial neural network classification analysis model diagnosis Gingivitis disease

<span lang="EN-US">Gingivitis is a disease that can be caused by the buildup of bacteria and plaque caused by leftover food. This disease can attack anyone, especially children who are not aware of maintaining dental and oral health. This study aims to build and optimize the classification analysis model for the diagnosis of Gingivitis. The classification analysis model was built using the artificial neural network (ANN) method which was optimized using fuzzy logic and the multiple linear regression (MRL) method. Optimization with fuzzy aims to develop a pattern of rules in the detection. The MRL method is also used as a process of measuring analysis patterns to ensure the analytical model presents maximum results. The results study indicate that the optimization of fuzzy and MRL methods provides excellent output. These results are based on the fuzzy output which can provide a pattern of 40 rules. The MRL method is can present the level of correlation of each analysis variable with a significant output having an average value of 94.2%. Based on the results of this study, the analysis model that is optimized with the fuzzy logic method and MRL contributes to maximizing the process of diagnosing Gingivitis.</span>

Optimization of Filler Content and Size on Mechanical Performance of Graphene/Hemp/Epoxy-Based Hybrid Composites using Taguchi with ANN Technique

The usage of nanofillers in composite materials has grown over time due to various benefits, including superior properties, better adhesion, and high stiffness. To accomplish this, 150, 200, 250, and 300 gsm of hemp fiber mat with various thicknesses and weight proportions of graphene powder, including 0%, 3%, 6%, and 9%, as well as 3, 6, 18, and 25 µm-sized particles, were used. High-speed mechanical stirring was used to evenly mix the nanofiller (nanographene) with the epoxy-based nanocomposites at various loadings. We looked at the bending and interlaminar shear strength (ILSS) properties of hybrid nanomaterials. According to the study, adding 300 gsm of hemp epoxy composites filled with 6 wt% nanographene has significantly improved mechanical properties. The development of a forecasting model to determine the mechanical properties using artificial neural networks (ANN). The constructed model has a significant connection with the test findings. A correlation of 0.9724 for the Levenberg–Marquardt training procedure indicates a significant connection between the predicted and experimental artificial neural models. The observational and projected results for bending and ILSS have <3% and 4% errors, corresponding to the ANN prediction and Taguchi L16 matrix. The potential of ANN for forecasting the bending and ILSS of composite materials is expanded by the close relationship between ANN and experimental findings. The following parameters were used in the current study to determine the flexural strength: graphene content (40.79%), graphene size (34.19%), the number of hemp layers (12.57%), and hemp fiber thickness (11.65%). Similar to ILSS, graphene content accounts for 47.82% of the total, with graphene size (27.87%), hemp fiber thickness (11.80%), and the number of hemp layers (also 11.80%) all contributing (11.78%).

Machine learning algorithms applied to intelligent tyre manufacturing

ABSTRACT Intelligent manufacturing is a way to expand industrial manufacturing by integrating artificial intelligence and device technologies to provide great solutions to solve complex problems and improve industrial processes. Artificial intelligence has been used in intelligent manufacturing for monitoring and optimization processes, focusing on improving efficiency. This paper examines the predictive performance of six machine learning algorithms for modeling tyre weight in smart tire manufacturing from real data. The main contribution of this research is developing a scheme solution that uses machine learning algorithms to industrial processes in stored data large manufacturing processes, allowing the process engineer to manage the finished products and the process parameters. The proposed relevance vector machine is compared with other algorithms such as support vector machine, artificial neural network, k-nearest neighbors, random forest, and model trees. RVM algorithm presented the smallest measures of squared error and better performance than the other algorithms. This novel approach accurately predicts tyre weight patterns during production using machine learning algorithms to analyze relevant features and detect anomalies based on predicted process data.

Delamination identification in sandwich composite structures using machine learning techniques

Recent advances in machine learning have enabled powerful strategies for autonomous data-driven damage detection and identification in structural systems. This work proposes a novel method for 3D delamination identification in sandwich composite structures. Sandwich structures are prone to damage that is difficult to detect, necessitating efficient and complex inspection techniques. In this context, automated structural health monitoring techniques are of great impact and importance in engineering. Such techniques use data obtained by sensors to identify damage to the structure. In this paper, a complete methodology for damage (delamination) identification in sandwich composite structures using machine learning is proposed. The damage was parameterized in two different ways: as parametrized two- and three-dimensional ellipses, and it was considered in three different groups: the core, interface, and skin. The modal data, obtained by the finite element method, was used to train several machine learning models in order to classify the location of the damage. In addition, modal dataset was also used to train artificial neural network regression models for damage localization and sizing. Both classification and regression strategies showed substantial results, and the models proved to be robust enough to identify a wide variety of damages. Results showed that classification models correctly identified the damage on the composite skin and incorrectly identified the interface core-skin damage. The regression model proved to be reliable in identifying an approximate location with an average accuracy of 85%. However, damage sizing is still a challenge to predict based only on modal datasets.

Assessing the Contribution of Managerial Accounting in Sustainable Organizational Development in the Healthcare Industry

Sustainability and digital transformation are two phenomena influencing the activities of all organizations. Managerial accounting is an essential component of these transformations, having complex roles in decision-making to ensure sustainable development through implementing modern technologies in the accounting process. This paper studies the roles of digitized managerial accounting in organizational sustainability drivers from a decision-making perspective. The empirical investigation assesses the influence of managerial accounting on the economic, social, and environmental drivers of sustainability from the perception of 396 Romanian accountants using an artificial neural network analysis and structural equation modeling. As a result, the research provides a holistic view of the managerial accounting roles enhanced by digital technologies in the sustainable development of healthcare organizations. From the accountants' perception, the leading managerial accounting roles on organizational sustainability are enablers and reporters of the sustainable value created in the organization. Additionally, the roles of creators and preservers are seen as relevant by a significant part of the respondents. Therefore, healthcare organizations must implement a sustainability vision in managerial accounting and accounting information systems using the capabilities offered by new digital technologies.

Fast and robust parameter estimation with uncertainty quantification for the cardiac function

Background and objectivesParameter estimation and uncertainty quantification are crucial in computational cardiology, as they enable the construction of digital twins that faithfully replicate the behavior of physical patients. Many model parameters regarding cardiac electromechanics and cardiovascular hemodynamics need to be robustly fitted by starting from a few, possibly non-invasive, noisy observations. Moreover, short execution times and a small amount of computational resources are required for the effective clinical translation. MethodsIn the framework of Bayesian statistics, we combine Maximum a Posteriori estimation and Hamiltonian Monte Carlo to find an approximation of model parameters and their posterior distributions. Fast simulations and minimal memory requirements are achieved by using an accurate and geometry-specific Artificial Neural Network surrogate model for the cardiac function, matrix–free methods, automatic differentiation and automatic vectorization. Furthermore, we account for the surrogate modeling error and measurement error. ResultsWe perform three different in silico test cases, ranging from the ventricular function to the entire cardiocirculatory system, involving whole-heart mechanics, arterial and venous hemodynamics. By employing a single central processing unit on a standard laptop, we attain highly accurate estimations for all model parameters in short computational times. Furthermore, we obtain posterior distributions that contain the true values inside the 90% credibility regions. ConclusionsMany model parameters regarding the entire cardiovascular system can be fastly and robustly identified with minimal hardware requirements. This can be achieved when a small amount of non-invasive data is available and when high levels of signal-to-noise ratio are present in the quantities of interest. With these features, our approach meets the requirements for clinical exploitation, while being compliant with Green Computing practices.

Levenberg–Marquardt Training Technique Analysis of Thermally Radiative and Chemically Reactive Stagnation Point Flow of Non-Newtonian Fluid with Temperature Dependent Thermal Conductivity

We have examined the magnetized stagnation point flow of non-Newtonian fluid towards an inclined cylindrical surface. The mixed convection, thermal radiation, viscous dissipation, heat generation, first-order chemical reaction, and temperature-dependent thermal conductivity are the physical effects being carried for better novelty. Mathematical equations are constructed for four different flow regimes. The shooting method is used to evaluate the heat transfer coefficient at the cylindrical surface with and without heat generation/thermal radiation effects. For better examination, we have constructed artificial neural networking models with the aid of the Levenberg–Marquardt training technique and Purelin and Tan-Sig transfer functions. The Nusselt number strength is greater for fluctuations in the Casson fluid parameter, Prandtl number, heat generation, curvature, and Eckert number when thermal radiations are present.

The Use of Artificial Neural Networks in Agricultural Plants

Artificial Neural Networks use high-performance computing and big data technology, opportunities for science to create new opportunities in agriculture. The purpose of writing this article is to analyze the use of artificial neural networks on (a) plant diseases based on plant leaf diseases, (b) plant pests, (c) growth or quality, and (d) agricultural products. The writing method used is a literature study of the research that has been done. The keywords used in the search for references include ANN, plant, diseases, pests, growth or quality, and agricultural products. Publishers for the reference in this article are ScienceDirect and IEEE. The years of publication of the references are restricted from 2015 to 2022. Based on the literature study results, it was concluded that Artificial Neural Networks' deep learning models are accurate for detecting and classifying leaf diseases and pests, detecting growth, and application to agricultural plant products.

Akurasi Model Hybrid ARIMA-Artificial Neural Network dengan Model Non Hybrid pada Peramalan Peredaran Uang Elektronik di Indonesia

The purpose of this study is to model electronic money in Indonesia using a hybrid model and compare its accuracy with the non-hybrid model. The hybrid model used is Autoregressive Integrated Moving Average (ARIMA)-Artificial Neural Network. The data used is the amount of electronic money circulation for the monthly period January 2009 to October 2021. The ARIMA model formed from research data is ARIMA (1,1,0) with additive outliers and level shift outliers. For Artificial Neural Network modeling is limited by using one hidden layer with three neurons. In the modeling process, 20 repetitions were carried out. The smallest repetition value was obtained, namely the 13th repetition with an error value of 2.569. In this study, it was found that the ARIMA- Artificial Neural Network hybrid model had a smaller Root Mean Squared Error (RMSE) in sample and out sample than the non-hybrid model. Based on the results of the study, it can be concluded that by combining the ARIMA model with Artificial Neural Network, it can increase the accuracy of the data fit results and forecast results.

A Deep Learning Model for Energy-Aware Task Scheduling Algorithm Based on Learning Automata for Fog Computing

Abstract This paper presents an artificial intelligence deep learning model for an energy-aware task scheduling algorithm based on learning automata (LA) in the Fog Computing (FC) Applications. FC is a distributed computing model that serves as an intermediate layer between the cloud and Internet of Things (IoT) to improve the quality of service. The IoT is the closest model to the wireless sensor network (WSN). One of its important applications is to create a global approach to health care system infrastructure development that reflects recent advances in WSN. The most influential factor in energy consumption is task scheduling. In this paper, the issue of reducing energy consumption is investigated as an important challenge in the fog environment. Also, an algorithm is presented to solve the task scheduling problem based on LA and measure the makespan (MK) and cost parameters. Then, a new artificial neural network deep model is proposed, based on the presented LA task scheduling fog computing algorithm. The proposed neural model can predict the relation among MK, energy and cost parameters versus VM length for the first time. The proposed model results show that all of the desired parameters can be predicted with high precision.

A Loosely Coupled Model for Simulating and Predicting Land Use Changes

The analysis and modeling of spatial and temporal changes in land use can reveal changing urban spatial patterns and trends. In this paper, we introduce a linear transformation optimization Markov (LTOM) model that can be exploited to estimate the state transition probability matrix of land use, building a loosely coupled ANN-CA-LTOM model for simulating and predicting land use changes. The advantages of this model are that it is flexible and high expansibility; it can maintain semantic coupling between the Artificial Neural Networks (ANN), Cellular Automata (CA), and LTOM model and enhance their functions; and it can break the limitation of requiring two periods of land use data when calculating the transition probability matrix. We also construct a suitability atlas of land use as the transition rules into the CA-LTOM model, taking into account the regional natural and socioeconomic driver factors, by exploiting the ANN model. The ANN-CA-LTOM model is employed to simulate the distribution of the three major types of land use, i.e., construction land, agricultural land, and unused land, in the Nansha District, China, in 2018 and 2020. The results show that the model performs well and the overall accuracy of the land use simulation was 97.72%, with a kappa coefficient of 0.962761. Furthermore, the simulated and predicted results of land use changes from 2021 to 2023 in Nansha District show changing trends in construction, agricultural, and unused land use. This study provides an approach for estimating a Markov transition probability matrix and a coupled mode of the models for simulating and predicting land use changes.

Investigating the Accuracy of Hybrid Models with Wavelet Transform in the Forecast of Watershed Runoff

In the hydrological cycle, runoff precipitation is one of the most significant and complex phenomena. In order to develop and improve predictive models, different perspectives have been presented in its modeling. Hydrological processes can be confidently modeled with the help of artificial intelligence techniques. In this study, the runoff of the Leilanchai watershed was simulated using artificial neural networks (ANNs) and M5 model tree methods and their hybrid with wavelet transform. Seventy percent of the data used in the train state and thirty percent in the test state were collected in this watershed from 2000 to 2021. In addition to daily and monthly scales, simulated and observed results were compared within each scale. Initially, the rainfall and runoff time series were divided into multiple sub-series using the wavelet transform to combat instability. The resultant subheadings were then utilized as input for an ANN and M5 model tree. The results demonstrated that hybrid models with wavelet improved the ANN model's daily accuracy by 4% and its monthly accuracy by 26%. It also improved the M5 model tree's daily and monthly accuracy by 4% and 41%. The wavelet-M5 model's accuracy does not diminish to the same degree as the wavelet-ANN (WANN) model as the forecast horizon lengthens. Consequently, the Leilanchai watershed has a relatively stable behavior pattern. Finally, hybrid models, in conjunction with the wavelet transform, improve forecast accuracy.

The Use of Intelligent Mathematical Models for Regional Investment Distribution Processes Analysis

In this article, the artificial neural network mathematical model is used for Regional Investment Distribution Processes Analysis in the regions of the Republic of Uzbekistan; forecasts are made using this model, and the results are compared with the results determined using the trend and panel methods, and the preferred method is defined. Multi-layer perceptron, radial-basis grid, generalized-regression grid, and recurrent grid can be used to solve the forecasting problem. In the study, a program for intellectual analysis and forecasting of socio-economic development indicators of the regions of the Republic of Uzbekistan using the generalized regression network was developed. This program makes it possible to extract the most necessary factors from other methods even in the presence of multi-factor indicators and determine the future forecast result under their influence. According to the results of the forecast determined using the intellectual mathematical model developed because of the research, by 2025, the volume of the gross regional product of Andijan region is expected to be equal to 95607.34 billion soums, and in Samarkand region, it is expected to be equal to 80419.73 billion soums, in Tashkent city it is expected to be 259301.8 billion soums. According to the error levels of the results determined by the intellectual mathematical method, it represents an average error of 1.13% compared to the forecast period. If we determine the result of the trend by the level of error, it is equal to an average of 4.96% error compared to the forecast period, and these results prove the superiority of the intellectual mathematical method developed in the research.

Prediction of methyl orange dye (MO) adsorption using activated carbon with an artificial neural network optimization modeling

In this study, methyl orange (MO) dye removal by adsorption utilizing activated carbon made from date seeds (DPAC) was modeled using an artificial neural network (ANN) technique. Instrumental investigations such as X-ray diffraction (XRD), scanning electron microscopy (SEM), and Brunauer-Emmett-Teller (BET) analysis were used to assess the physicochemical parameters of adsorbent. By changing operational parameters including adsorbent dosage (0.01–0.03 g), solution pH 3–8, initial dye concentration (5–20 mg/L), and contact time (2–60 min), the viability of date seeds for the adsorptive removal of methyl orange dye from aqueous solution was assessed in a batch procedure. The system followed the pseudo 2nd order kinetic model for DPAC adsorbent, according to the kinetic study (R2 = 0.9973). The mean square error (MSE), relative root mean square error (RRMSE), root mean square error (RMSE), mean absolute percentage error (MAPE), relative error (RE), and correlation coefficient (R2) were used to measure the ANN model performance. The maximum RE was 8.24% for the ANN model. Two isotherm models, Langmuir and Freundlich, were studied to fit the equilibrium data. Compared with the Freundlich isotherm model (R2 = 0.72), the Langmuir model functioned better as an adsorption isotherm with R2 of 0.9902.Thus, this study demonstrates that the dye removal process can be predicted using an ANN technique, and it also suggests that adsorption onto DPAC may be employed as a main treatment for dye removal from wastewater.

APPLICATION OF THE MODERN EVALUATION’S METHOD OF SOCIO-ECONOMIC POTENTIAL OF REGIONS

In this article, the programs of artificial neural network mathematical models are recommended, which are a new direction for analysis of problems arising in the distribution of investments in the regions of the Republic of Uzbekistan; forecasts are made using this program, and the results are compared with the results determined using the trend and panel methods, and the preferred method is defined

Neural networking analysis for MHD mixed convection Casson flow past a multiple surfaces: A numerical solution

<abstract> <p>The heat and mass transfer within non-Newtonian fluid flow results in complex mathematical equations and solution in this regard remains a challenging task for researchers. The present paper offers a numerical solution for the non-Newtonian flow field by using Artificial neural networking (ANN) model with the Levenberg Marquardt training technique. To be more specific, we considered thermally magnetized non-Newtonian flow headed for inclined heated surfaces. The flow is carried with viscous dissipation, stagnation point, heat generation, mixed convection, and thermal radiation effects. The concentration aspects are entertained by the owing concentration equation. The shooting method is used to solve the mathematical flow equations. The quantity of interest includes the temperature and heat transfer coefficient. Two different artificial neural networking models have been built. The training of networks is done by use of the Levenberg Marquardt technique. The values of the coefficient of determination suggest artificial neural networks as the best method for predicting the Nusselt number at both surfaces. The thermal radiation parameter and Prandtl number admit a direct relationship to the Nusselt number while the differing is the case for variable thermal conductivity and Casson parameters. Further, by using Nusselt number (NN)-ANN models, we found that for cylindrical surface, the strength of the NN is greater than the flat surface.</p> </abstract>

Comparative study of single biological neuron with an artificial neuron

A number of artificial neural models have been presented in the literature in an effort to suggest a more accurate representation of a single biological neuron. There are numerous publications on synthetic neurons that attempted to replicate a single biological neuron, however, such models were unable to generate the spiking patterns of a real biological neuron. Therefore, there is still scope to design and research improved spiking neural models that more accurately reflect the functions of a biological neuron. This motivation drives extensive modification of an artificial neuron model to produce the spike patterns of a real biological neuron. The modified single artificial neuron model that has been proposed exhibits the functions of a biological neuron. It’s still crucial to model spiking bio-neuron behavior. Modeling a spiking bio-neuron is still an important exercise in view of possible applications of the underlying features in the areas of neuromorphic engineering, cognitive radio, and spiking neural networks

Elevation accuracy improvement in mobile devices by implementing artificial neural networks

ABSTRACT An important feature of mobile devices relates to positioning, mainly relying on the global navigation satellite system sensor. In optimal conditions, this sensor provides horizontal positioning sufficient for most location-based services. The elevation, on the other hand, still lacks sufficient accuracy and reliability – mostly due to mobile device inadequacies that stem from technological limitations and environmental and physical conditions, which impact the observations quality. We suggest augmenting the elevation measurements of this sensor with measurements from supplementary embedded mobile device sensors, such as barometers and accelerometers, and with data from external mapping and environmental databases, namely topography and weather. We developed an artificial neural network deep-learning model that identifies parameter values for producing the highest predictive accuracy of the elevation value while relying on a comprehensive set of measurements. Our findings indicate very promising results, whereby we enhanced the elevation accuracy of testing data by 428%, while significantly reducing the elevation variance. These results show that using supplementary measurements and data improves elevation values while significantly reducing errors commonly associated with mobile device global navigation satellite system sensors. The proposed method has the capacity to improve outdoor kinematic positioning for location-based services, with a focus on urban and concealed areas.

PRELIMINARY INVESTIGATION ON THE EFFECT OF CUTTING PARAMETERS ON SURFACE ROUGHNESS AND FLATNESS IN DRY MILLING OF PMMA

Polymethylmethacrylate (PMMA) also known as Plexiglass is a commonly used material for many applications, especially in medical industry. In some application, PMMA parts may be also used as molds for enabling fabrication of final products. Some of these parts are manufactured by injection molding, but in many cases mechanical machining of some surfaces is still required. The cutting of PMMA requires a previous optimization of the cutting parameters combination (feed rate and spindle speed). If this optimization is not carried out, the problems encountered may refer to cutting debris or material melting during machining and, consequently, the material attaches to the tool cutting edge. This will result in a surface with very poor quality, in terms of aspect and surface roughness. This paper reports on the preliminary experimental investigation of cutting parameters on the surface roughness and flatness error in dry milling of PMMA. The cutting experiments were conducted on EMCO MILL 55 CNC drilling and milling machine. The design of experiment (DOE) consists in L27 (33) design, meaning a three factorial experimental plan (3 factors on 3 levels). The cutting parameters, respectively depth of cut, feed rate and spindle speed are taken as inputs and surface roughness and flatness are taken as outputs. The surface flatness was measured with TESA Micro-Hite coordinate measuring machine. Analysis of variance (ANOVA) was adopted to identify the statistical influence of each input parameter and combination of input parameters on surface roughness. From the preliminary results, it can be observed that optimum regime is a combination of low feed rate, low depth of cut and high spindle speed. Moreover, an artificial neural model is proposed for prediction of surface roughness and flatness considering the depth of cut, feed rate and spindle speed as input variables. This approach aims to reveal the possibility of predicting the output parameters using neural network modelling, that can be further used to optimize the cutting regime.

Innovative ANN hysteresis to predict hysteretic performance of composite reinforced concrete beam

This article assess the precise estimation of the hysteresis loop of reinforced concrete (RC) beams in distinct failure cases to verify inelastic seismic beam function. Any test failure in RC frame columns is able to produce hysteresis curves in low cyclic repeat load that follows the analysis of the hysteretic behavior of the frame columns. In this case, the application of fibers as a mass enhancement to improve the post-cracking of RC beams, strength, and delay cracking has been investigated. In this research, the hysteretic response of deep and slender SFRC beams enhanced with SF using ten beams under the reversal cyclic load was studied through innovative ANN hysteresis. Shear and flexural strength of SFRC beams were analyzed using a diverse number of fibers with content from 0.1 to 5% per volume, closed stirrups (from 0 to 0.5%), and steel reinforcing bars (0.50% and 1.50%). The innovative artificial neural network hysteresis model has been utilized to define the accuracy prediction of the parameters and determine the hysteresis loop of RC columns failing in different modes. Comparing the experimental findings properly indicated the accuracy of the model to capture the main features of the response, such as the load versus deformation cyclic envelope, SFRC tension softening effect, and the impact of the fibers on the hysteretic energy. The results revealed that SFRC beams represented developed cyclic efficiency in case of deformation, load-bearing capacity, residual stiffness, cracking and energy dissipation ability while generating their integrity within the imposed reversal cyclic experiments.