Artificial Neural Network Method Research Articles

Comparative analysis of ANN performance of four feature extraction methods used in the detection of epileptic seizures

Epilepsy, a prevalent neurological disorder characterized by disrupted brain activity, affects over 70 million individuals worldwide, as reported by the World Health Organization (WHO). The development of computer-aided diagnosis systems has become vital in assessing epilepsy severity promptly and initiating timely treatment. These systems enable the detection of epileptic seizures by analyzing the electrical activity in the EEG recordings of the patients. In addition, it helps doctors to choose suitable treatment by quickly determining the type, duration, and characteristics of seizures and increases the patient's quality of life. The proposed computer-aided diagnosis system in this study comprises three modules: preprocessing, feature extraction, and classification. The initial module employs a low-pass Chebyshev II filter to eliminate noise artifacts from signal recordings. The second module involves deriving feature vectors using Bispectrum Analysis, Empirical Mode Decomposition, Discrete Wavelet Transform, and Wavelet Packet Analysis. The third module employs the Artificial Neural Networks method for epileptic seizure detection. This study not only enables the comparison of feature extraction efficacy among Bispectrum Analysis, Empirical Mode Decomposition, Discrete Wavelet Transform, and Wavelet Packet Analysis techniques, but it also reveals that Bispectrum Analysis and Empirical Mode Decomposition yield the highest accuracy rate. The method achieves 100% accuracy in detecting epileptic seizures. Additionally, sensitivity analysis has been conducted to enhance the success of Discrete Wavelet Transform and Wavelet Packet Analysis methods and to identify significant features.

Esiımating the Export Value of Broad Economic Categories by Artificial Neural Networks Method

Bu çalışmada Türkiye dış ticaretine ait geniş ekonomik grupların aylık ihracat değerlerinin tahminlenmesi hedeflenmektedir. Çalışmada ele alınan geniş ekonomik gruplar: Yatırım malları, ham madde ve tüketim mallarıdır. İlgili aylık ihracat değerleri bir yapay zekâ tekniği olan yapay sinir ağları yöntemiyle tahminlenmiştir. Yapay sinir ağı yöntemi analizleri MATLAB 2013 paket programı aracılığıyla gerçekleştirilmiştir. Çalışmada kullanılan veriler Türkiye Cumhuriyet Merkez Bankası web sayfalarından alınmıştır. Elde edilen sonuçlara göre üç farklı geniş ekonomik grubun ihracat değerlerini tahminlemede kurulan yapay sinir ağı modelleri en başarılı tahminini tüketim malları ihracat değeri tahminlemesinde gerçekleştirmiştir. Ham madde ihracat değeri ve yatırım malları ihracat değeri tahminlemesinde kurulan yapay sinir ağları modelleri birbirlerine yakın tahmin performansları göstermekle beraber yatırım malları ihracat değeri tahminlemesi için kurulan model daha başarılı olmuştur.

QSAR, DFT studies, docking molecular and simulation dynamic molecular of 2-styrylquinoline derivatives through their anticancer activity

In this study, a 2D-QSAR (quantitative structure–activity relationship) was performed on 54 new 2-Styrylquinoline derivatives as anticancer substances capable of inhibiting the p53 protein in the cell HCT116++. The 54 2-Styrylquinoline derivatives was calculated applying DFT 6-31G basis to calculate Quantum descriptors, using MM2 for: Topological, Physico-chemical, Geometrical and Constitutional. The study was carried out by performing multiple linear regression (R2 = 0.90), the QSAR model achieved was tested by artificial neural networks method, which is showed high predictability (R2ANN = 0.89). A DFT study was performed to determine the reactivity of the 2-Styrylquinoline derivatives using frontier molecular orbital analysis and analysis of the molecular electrostatic potential (MEP). Derivatives of 2–4 Styrylquinoline are studied for their synthetic accessibility and their similarity to drug. The obtained results show that all the evaluated compounds have similar properties to drug and are accessible to synthesize.A molecular docking analysis was performed for three compounds: 14, 34, and 54, having various reactivities against the p53 HCT116++ protein (identified by PDB ID: 2GEQ). The results showed strong interactions between the three ligands and the 2GEQ protein, the amino acids HIS 176, SER A180, PRO A188 and ARG A178 are the most active sites of the 2GEQ protein, and based on these result we performed a molecular dynamics simulation to evaluate the stability of our complexes. The MD demonstrates the thermodynamic stability of select compounds during 40 and 100 ns, with all three complexes showing a high level of structural stability.

Prediction of uniaxial compressive strength of the Kızılkaya ignimbrite with variable properties using MRA and ANN, Cappadocia (Turkey)

Cappadocia in Turkey is an important region with emphasis on ethnic and historic structures and geological features. Because of volcanic eruptions, ash flow materials deposited at different levels. These different colored ignimbrite levels have a wide range of geomechanical properties. In the region, the Kızılkaya ignimbrite covers a very large area and is frequently used as building dimension stone in for the restoration of old historical buildings such as churches, caravansaries and mosques as well as new buildings. It contains tuffaceous matrix with some minerals and rock fragments. The rock has variable character. In this study, the relationship between petrographic and physico-mechanical properties of the Kızılkaya ignimbrite was investigated. Rate of change between uniaxial compressive strength and the other index properties of the rock was statistically examined utilizing multiple regression analysis (MRA) and Artificial Neural Network (ANN) methods. The study has shown that uniaxial compressive strength (UCS) of the ignimbrite can be successfully estimated by the use of dry unit weight, effective porosity, sonic velocity, and grain matrix ratio (GMR) parameters. A new UCS prediction equation is proposed in this paper for the ignimbrite with variable character. Since properties of the ignimbrite at different distances from the eruption area changes significantly, the approach presented in this study can be considered for the ignimbrites especially covering a large area with different welding degrees and grains.

Automatic Weight of Color, Texture, and Shape Features in Content-Based Image Retrieval Using Artificial Neural Network

Image retrieval is the process of finding images in the database that are similar to the query image by measuring how close the feature values of the query image are to other images. Image retrieval is currently dominated by approaches that combine several different representations or features. The optimal weight of each feature is needed in combining the image features such as color features, texture features, and shape features. In this study, we use a multi-layer perceptron artificial neural network (MLP) method to obtain feature weights automatically and simultaneously look for optimal weights. The color moment is used to find nine color features, Gray Level Co-occurrence Matrix (GLCM) to find four texture features, and Hu Moment to find seven shape features totaling 20 neurons and all of these features become the input layer in our MLP network. Three neurons in output layers become the automatic weight of each feature. These weights are used to combine each feature's role in obtaining the relevant image. Euclidean Distance is used to measure similarity. The average precision values obtained using automatic feature weights are 93.94% for the synthetic dataset, 91.19% for the Coil-100 dataset, and 54.31% for the Wang dataset. These results have an average difference of 5.06% with the target so automatic feature weighting works well. This value is obtained at a hidden layer size of 11 and a learning rate of 0.1. In addition, the use of automatic feature weighting gives more accurate results compared to manual feature weighting.

Implementasi Backpropagation ANN dan Algoritma Genetika Terhadap Estimasi Pendapatan Agen Ekspedisi Pengiriman Barang

Income is the amount of income received by a person or resident for their work performance during a certain period, whether daily, weekly, monthly or yearly. This research implements the Backpropagation Artificial Neural Network and Genetic Algorithm methods to estimate the income of JNE Express Sekaran agents. Artificial Neural Network and Genetic Algorithm are modern forecasting methods that produce the smallest and most accurate error values. Based on the research that has been done, the Backpropagation Artificial Neural Network method produces the best architectural model, namely 4-10-1 with 4 as the input layer, 10 as hidden neurons, and 1 as the output layer. With epoch 487 obtains an MSE 0,150807. While the Genetic Algorithm method produces the best fitness value is 10209,02 with a population size of 200, crossover probability 0,8, mutation probability 0,03 in the 498th generation and obtains an MSE value of 0,000098. So, it can be predicted that income for the following month is October 2021 of IDR 25.011.603, November 2021 of IDR 20.920.021, and December 2021 of IDR 50.553.019

Measurements of the Hubble constant from combinations of supernovae and radio quasars

In this letter, we propose an improved cosmological model independent method of determining the value of the Hubble constant H0. The method uses unanchored luminosity distances H0dL(z) from SN Ia Pantheon data combined with angular diameter distances dA(z) from a sample of intermediate luminosity radio quasars calibrated as standard rulers. The distance duality relation between dL(z) and dA(z), which is robust and independent of any cosmological model, allows to disentangle H0 from such combination. However, the number of redshift matched quasars and SN Ia pairs is small (37 data-points). Hence, we take an advantage from the Artificial Neural Network (ANN) method to recover the dA(z) relation from a network trained on full 120 radio quasar sample. In this case, the result is unambiguously consistent with values of H0 obtained from local probes by SH0ES and H0LiCOW collaborations. Three statistical summary measures: weighted mean H˜0=73.51(±0.67) km s−1 Mpc−1, median Med(H0)=74.71(±4.08) km s−1 Mpc−1 and MCMC simulated posterior distribution H0=73.52−0.68+0.66 km s−1 Mpc−1 are fully consistent with each other and the precision reached 1% level. This is encouraging for the future applications of our method. Because individual measurements of H0 are related to different redshifts spanning the range z=0.5−2.0, we take advantage of this fact to check if there is any noticeable trend in H0 measurements with redshift of objects used for this purpose. However, our result is that the data we used strongly support the lack of such systematic effects.

Modeling and Predicting the Mechanical Behavior of Standard Insulating Kraft Paper Used in Power Transformers under Thermal Aging

The aim of this research is to predict the mechanical properties along with the behaviors of standard insulating paper used in power transformers under thermal aging. This is conducted by applying an artificial neural network (ANN) trained with a multiple regression model and a particle swarm optimization (MR-PSO) model. The aging of the paper insulation is monitored directly by the tensile strength and the degree of polymerization of the solid insulation and indirectly by chemical markers using 2-furfuraldehyde compound content in oil (2-FAL). A mathematical model is then developed to simulate the mechanical properties (degree of polymerization (DPV) and tensile index (Tidx)) of the aged insulation paper. First, the datasets obtained from experimental results are used to create the MR model, and then the optimizer method PSO is used to optimize its coefficients in order to improve the MR model. Then, an ANN method is trained using the MR-PSO to create a nonlinear correlation between the DPV and the time, temperature, and 2-FAL values. The acquired results are assessed and compared with the experimental data. The model presents almost the same behavior. In particular, it has the capability to accurately simulate the nonlinear property behavior of insulation under thermal aging with an acceptable margin of error. Since the life expectancy of power transformers is directly related to that of the insulating paper, the proposed model can be useful to maintenance planners.

Predicting customer deposits with machine learning algorithms: evidence from Tunisia

PurposeThis paper aims to evaluate the performance of the multiple linear regression (MLR) using a fixed-effects model (FE) and artificial neural network (ANN) models to predict the level of customer deposits on a sample of Tunisian commercial banks.Design/methodology/approachTraining and testing datasets are developed to evaluate the level of customer deposits of 15 Tunisian commercial banks over the 2002–2021 period. This study uses two predictive modeling techniques: the MLR using a FE model and ANN. In addition, it uses the mean absolute error (MAE), R-squared and mean square error (MSE) as performance metrics.FindingsThe results prove that both methods have a high ability in predicting customer deposits of 15 Tunisian banks. However, the ANN method has a slightly higher performance compared to the MLR method by considering the MAE, R-squared and MSE.Practical implicationsThe findings of this paper will be very significant for banks to use additional management support to forecast the level of their customers' deposits. It will be also beneficial for investors to have knowledge about the capacity of banks to attract deposits.Originality/valueThis paper contributes to the existing literature on the application of machine learning in the banking industry. To the author's knowledge, this is the first study that predicts the level of customer deposits using banking specific and macroeconomic variables.

Simulation of Zanjan temperature trends based on climate scenarios and artificial neural network method

Simulation of Zanjan temperature trends based on climate scenarios and artificial neural network method

Research on meteorological temperature prediction based on machine learning

Predicting temperature has been a great challenge in meteorology. Accurate temperature prediction is more conducive to human production and life. This study investigated the ability of artificial neural network (ANN) and random forest (RF) methods to predict short-term monthly temperatures. The study data has been processed from the global surface temperature change estimated by NASA Goddard Institute for Space Studies. The average temperature from three months ago, the average temperature two months ago, and the average temperature one month ago were used as inputs to the application model. Both the models gave comparable results, but the superiority of the artificial neural network model over the random forest model in the present study.

Analysis of Machining Parameters for Turning of AL-6061 and Optimization

The paper shows and includes targeted supervision of optimizing machining parameters. Material Removal Rate and surface roughness being integral to machining efficacy of any workpiece , simulation based modeling helps in failure mitigation.Thepotential of ANN-GA mathematical approach for prediction and optimization of MRR and surface roughness of AL 6061 , a analysis based statistical study has been discussed. The computational model between the desired output and the inputs have been configured using Multiple Regression- Genetic Algorithm and Artificial Neural Network(ANN) methods. The closeness in predicted and optimized data sets were mapped using integrational ANN with GA to interpolate efficacy in optimality. Keywords: Artificial Neural Network(ANN)k, Material Removal Rate(MRR), Genetic algorithm(GA), Surface roughness , depth of cut , feedrate , Regression analysis, ANOVA

Artificial neural networks for the prediction of mechanical properties of CGNP/PLGA nanocomposites

The mechanical properties of composite-based components have an impact on both their quality and efficacy. As a result, a scientific framework is needed to discover the practical set of progression constraints that will result in exceptional mechanical qualities. The possibilities of an artificial neural network (ANN) for predicting mechanical properties—specifically, the density and hardness of a carboxyl decorated graphene Nanocomposites (CGNP)/Poly Lactic-co-Glycolic Acid (PLGA) nanocomposite created under various spark plasma sintering (SPS) operating conditions—are explored in this work. A back-propagation with a 2–10-2 structural design and Levenberg-Marquardt algorithm was advanced to anticipate the automated performance of CGNP/PLGA nanocomposites in expressions of density and hardness parameters. The hypothesized outcomes of the models were compared to the actual experimental value. Density (0.9842) and hardness (0.9737) were found to be near to one; the archetypal accomplished well, with a good correlation coefficient (R) for both outputs and a low root-mean-squared error. The anticipated data findings were found to be quite compatible with the values acquired from the investigational assessment results. Our findings demonstrate the utility of a well-trained ANN method in assessing the density and hardness properties of SPSed CGNP/PLGA nanocomposites. As a result, the ANN system provides an unswerving tool for making decisions that can reduce the high costs involved with the experimental characterization of newly manufactured polymer composites.

Intelligent Model for Avoiding Road Accidents Using Artificial Neural Network

Accidents typically occurred on roads, resulting in significant societal losses. Road accidents are a worldwide issue that result in the loss of precious human lives and property. The purpose of this paper is to create an intelligent system-based on Machine Learning model for avoiding road accidents, as well as a system that effectively reduces road accidents severities. The Artificial Neural Network (ANN) algorithm, along with others such as Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Nave Bayes (NB), Stochastic Gradient Descent (SGD), Random Forest (RF), Gradient Boosting (GB), and AdaBoost, is used to create an intelligence system. Many driving collaborator procedures, installed in a few vehicles, assist drivers in avoiding vehicle crashes by providing early cautioning messages. The intelligence road crash avoidance system model is built on dataset of 29 columns and 1048575 rows. Preprocessing, feature selection, and feature extraction performed with the help of heat map and correlation matrix are used to select features. Linear Discriminant Analysis (LDA) is used for feature extraction. The testing dataset revealed that the proposed ANN method outperforms other algorithms with an accuracy of 0.856. Intelligent systems aid in the prevention of traffic accidents, which aids police officers and researchers in developing new policies.

Prediction of Mycotoxin Response of DNA-Wrapped Nanotube Sensor with Machine Learning

DNA-wrapped single-walled carbon nanotubes (SWCNTs) have demonstrated great versatility in their use as optical sensors. SWCNTs emit a near-infrared fluorescence that is responsive to even the slightest changes in the nanotube environment, enabling sensors that can respond to single-molecule fluctuations within the vicinity of their surfaces. The fluorescence response and surface interactions of these sensors are determined by the DNA wrapping sequence. However, the lack of information on the relationship between the DNA sequence and its effect on the SWCNT fluorescence remains a bottleneck for designing sequences that are specific to analytes of interest. We have recently demonstrated the use of directed evolution to control the fluorescence response of SWCNTs through DNA design. Iterative cycles of DNA mutation, screening, and selection allowed us to evolve sequences that yield DNA-wrapped SWCNT sensors with a desired fluorescence response to mycotoxins.In this work, we apply the screening results of the DNA libraries used in this approach to train machine learning (ML) algorithms. Artificial neural network (ANN) and support vector machine (SVM) methods were used to predict the response of ssDNA-SWCNT sensors to a specific mycotoxin. The reliability of these models was further assessed through cross-validation. The ANN and SVM models with cross-validation were able to accurately classify the various DNA sequences as yielding either a high or low fluorescence response with an accuracy of 73 and 81%, respectively. The models were further used to predict the performance of alternative DNA sequences outside the initial training dataset, using the Hierarchy and k-means ++ clustering methods to evaluate the similarity and dissimilarity of each DNA sequence. Compared to the SVM model, the ANN model showed an improved ability to predict high responses for dissimilar DNA sequences. We further applied a combinatorial approach based on SVM and ANN models to design new DNA sequences for improving sensor performance. The success of this approach was validated experimentally, demonstrating the rational design of improved sensors with 95% prediction accuracy.The application of ML algorithms to directed evolution libraries of DNA thus allows one to accurately map the performances of these sensors within a particular sequence space. The computational success of this mapping provides a framework for replacing current empirical approaches with the rational design of DNA sequences for SWCNT sensing. Keywords: Nano Biosensor, DNA-SWCNT, Mycotoxin, Machine learning, Directed evolution method

The evaluation of potentially toxic elements using artificial neural networks and fuzzy linear regression analysis methods in cappadocian volcanic ash soils of Turkey

The aim of this study is to determine the relationships between some potentially toxic elements (PTE) (Cu, Mn, Ni, Zn) in human stomach and intestinal tissues and toxic element contents in soil, vegetables and fruits. This study was conducted in the eastern of Erciyes Strato volcano, an area of 2400 km2 in Turkey. Tissue samples taken from the stomach and intestines of people living in the study area, soils, vegetables, and fruits were used as material. In the study, tissue samples of 26 people's stomach and intestines, 576 soil samples from 192 points and 3 different depths (0–30 cm, 30–60 cm, and 60–90 cm) and vegetable and fruit samples from 137 sampling points were taken. Cu, Mn, Ni, and Zn contents of human tissue samples, soil samples, vegetable and fruit samples were determined. Artificial Neural Networks method (ANN) and Fuzzy Linear Regression Analysis (FLRA) methods were used to determine the relationships between PTE contents in human tissue samples and soils, vegetables, and fruits. Root Mean squared error (RMSE) and coefficient of determination (R2) indices were used as the test criteria for goodness of fit. When compared with ANN method, it was determined that PTE values in stomach and intestinal tissue estimated by FLRA method had the lowest error and high R2 values. It was found that the most effective variable in estimating the average PTE value in stomach and intestinal tissue is PTE values in soil. It was determined that the FLRA regression analysis method has a better predictive power than the ANN method. Using FLRA and ANN regression methods, it was determined that there is a statistically high relationship between PTE contents in soils and stomach and intestinal tissues. It is recommended to make the study findings more meaningful with effective and reliable service planning by using different regression analysis methods in ecological and clinical studies.

Multi-objective optimization of the combustion chamber geometry for a highland diesel engine fueled with diesel/n-butanol/PODEn by ANN-NSGA III

In China, about one-third of the land area is over 2000 m, and a large number of equipments using diesel engines are operating in these areas. In order to optimizate the performance and emission characteristics of diesel engines, the investigation have been carried out for a highland diesel engine fueled with 80% diesel +10% n-butanol +10% PODE3 at an altitude of 2000 m. Firstly, a source model of the diesel engine was developed in CONVERGE and validated. Secondly, the combustion chamber geometry (CCG) of the diesel engine was expressed using two cubic Bézier curves and the shape of the curves was controlled using five variables (Hdep, C1, C2, LP2a and LP2b) and two fixed values. Then, the soot, NOx and HC emissions were predicted for different CCG shapes using response surface methodology and artificial neural networks (ANN), and a more appropriate prediction method for ANN was determined by comparing the performance of both. Finally, the predictions of the ANN were optimized using Non-dominated sorting genetic algorithm III (NSGA III) to obtain the Pareto fronts and the optimal solutions were selected from the Pareto fronts using VlseKriterijumska Optimizacija I Kombrissino Resenje (VIKOR). Through optimization, the optimal solution reduced soot, NOx and HC emissions by 67.15%, 7.08% and 92.48%, respectively, compared with the original CCG of the CI engine. In addition, the best CCG was analyzed in detail. Overall, ANN-NSGA III is an efficiently optimized method. The optimized CCG can effectively reduce the emission of CI engine.

A rapid dynamic headspace method for authentication of whiskies using artificial neural networks

A rapid headspace analysis method for the authenticity testing of whiskies of different brands and years was developed for a low cost, deployable atmospheric pressure ionisation mass spectrometer, which required minimal sample preparation. Principal component analysis was applied to the time-averaged mass spectra, the classification results for which were compared against artificial neural network methods. The artificial neural network was found to outperform PCA, achieving ≥95% accuracy for all sampling conditions, with only two misclassifications under the ideal conditions, while requiring less development time.

Numerical simulation accompanied by an intelligent computing system for the chemical reaction of Casson nanofluid and radiative heat flux on a nonlinear stretching surface

This study investigates the impact of radiative heat flux phenomena and magnetized Casson nanofluid flow on boundary layer flow along a non-linear stretching surface. Brownian motion and thermophoresis effects are used to highlight the properties of the nanofluid, including electrical conductivity. The flow curves and fluid behavior of particle suspensions in lithographic coatings used to make printing paints are well-described by the nonlinear Casson framework. Suction, chemical reaction, and a homogeneous magnetic field are all considered. An effective Levenberg-Marquardt Methodology (LMM) for artificial neural networks (ANNs) method is presented in this article. The LMM is one of the back-propagation algorithms with the lowest nonlinear latency. The required changes are necessary to convert a quasi-network of partial differential equations (PDEs) expressing the chemical reaction of the Casson nanofluid and radiative heat flux into a set of standards. The couple system regarding the model are facilitated via numerical shooting algorithm The compared to prior findings, the current ones have a very high degree of accuracy. The effects of different factors on the rate of heat transfer, the skin friction coefficient, the concentration of nanoparticles, the Sherwood number, the velocity, and the temperature profiles are illustrated in a tabular and visual form. The temperature and concentration fields exhibit the opposite effect on velocity as magnetic parameters change. The fluid's velocity is slowed down by a Lorentz force that is stronger at greater values of the magnetic field. Due to the suction parameter, the thickness of the momentum, temperature, and concentration boundary layers decreases. In physical terms, pressure forces are generated in the flow when the suction parameter is positive, and the opposite occurs when the suction parameter is negative. It is revealed that enhancement in thermal and concentration phenomenon is predicted by increasing Casson fluid parameter. For ANN analysis, the gradient numerical values reduced upon enhancing the number of epoch.

Development of the VGF Crystal Growth Recipe: Intelligent Solutions of Ill‐Posed Inverse Problems using Images and Numerical Data

AbstractDevelopment of the Vertical Growth Freeze crystal growth process is a typical example of solving the ill‐posed inverse problem, which violates one or more of Hadamard's well‐posedness criteria of solution existence, uniqueness, and stability. In this study, different data‐driven approaches are used to solve inverse problems: Reduced Order Modelling method of Proper Orthogonal Decomposition with Inverse Distance weighting (ROM POD InvD), an approximation method of Kriging and Artificial Neural Networks (ANN) employing images, combination of images and numerical data and solely numerical data, respectively. The ≈200 training data are generated by Computational Fluid Dynamics (CFD) simulations of the forward problem. Numerical input data are related to the temperatures and coordinates in 10 characteristic monitoring points in the melt and crystal, while the image input data are related to the interface shape and position. Using the random mean squared error as a criterion, the Kriging method based on images and numerical data and the ANN method based on numerical data are able to capture the system behavior more accurately, in contrast to the ROM POD InvD method, which is based solely on images.