Number Of Neurons In Layer Research Articles

Neural Network Used for the Fusion of Predictions Obtained by the K-Nearest Neighbors Algorithm Based on Independent Data Sources.

The article concerns the problem of classification based on independent data sets—local decision tables. The aim of the paper is to propose a classification model for dispersed data using a modified k-nearest neighbors algorithm and a neural network. A neural network, more specifically a multilayer perceptron, is used to combine the prediction results obtained based on local tables. Prediction results are stored in the measurement level and generated using a modified k-nearest neighbors algorithm. The task of neural networks is to combine these results and provide a common prediction. In the article various structures of neural networks (different number of neurons in the hidden layer) are studied and the results are compared with the results generated by other fusion methods, such as the majority voting, the Borda count method, the sum rule, the method that is based on decision templates and the method that is based on theory of evidence. Based on the obtained results, it was found that the neural network always generates unambiguous decisions, which is a great advantage as most of the other fusion methods generate ties. Moreover, if only unambiguous results were considered, the use of a neural network gives much better results than other fusion methods. If we allow ambiguity, some fusion methods are slightly better, but it is the result of this fact that it is possible to generate few decisions for the test object.

A Bayesian regularization-backpropagation neural network model for peeling computations

ABSTRACT A Bayesian regularization-backpropagation neural network (BR-BPNN) model is employed to predict some aspects of the gecko spatula peeling, viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. -fold cross validation is used to improve the effectiveness of the model. The input data is taken from finite element (FE) peeling results. The neural network is trained with of the FE dataset. The remaining are utilized to predict the peeling behavior. The training performance is evaluated for every change in the number of hidden layer neurons to determine the optimal network structure. The relative error is calculated to draw a clear comparison between predicted and FE results. It is shown that the BR-BPNN model in conjunction with the -fold technique has significant potential to estimate the peeling behavior.

Computational fluid dynamics (CFD), artificial neural network (ANN) and genetic algorithm (GA) as a hybrid method for the analysis and optimization of micro-photocatalytic reactors: NOx abatement as a case study

In this work the hybrid CFD-ANN-GA method is proposed as a tool for the analysis and optimization of micro-photocatalytic reactors, taking NOx abatement as a case study. Initially, a 3D CFD model of the microreactor allowed the investigation of the effects of residence time, light intensity, relative humidity and initial NO concentration on the performance of the photocatalytic reaction. Then, an artificial neural network (ANN) was implemented to predict the overall conversion of NO in the micro device. Different ANN structures were developed using data from 256 CFD simulations, and the best structure was chosen based on the performance factors MSE, RMSE and R2. Moreover, a genetic algorithm (GA) was used to find the optimal operating conditions that maximize the NO conversion. The best ANN model consisted of a feed-forward back-propagation structure with three layers and 11 neurons in the hidden layer (4:11:1), logsig-logsig transfer function and training through the Levenberg-Marquardt algorithm. This network presented a high predictivity (R2 = 0.9997), and it was used for optimization by GA to determine the optimum conditions. Based on the optimization results, full NO conversion (100%) was achieved when the residence time, light intensity, relative humidity and initial concentration were 2.12 s, 10 W·m−2, 10%, and 2.09 × 10−8 kmol·m−3, respectively. Furthermore, the most influential variable on the NO conversion prediction was the residence time, with a relative importance of 48.97%. The ANN was then modified to yield two outputs: NO consumption rate and pressure drop. All parameters were kept the same, except the number of neurons in the hidden layer (17). GA was then applied to a multi-objective optimization, aiming to maximize the NO consumption rate while minimizing the pressure drop in the system. The optimal set of operating conditions in this scenario was found based on a Pareto front analysis.

Color space influence on ANN skin lesion classification using statistics texture feature

This study aims to investigate the ability of an artificial neural network to differentiate between malign and benign skin lesions based on two statistics terms and for RGB (R red, G green, B blue) and YIQ (Y luminance, and I and Q chromatic differences) color spaces. The targeted statistics texture features are skewness (S) and kurtosis (K) which are extracted from the histograms of each color channel corresponding to the color spaces and for the two classes of lesions: nevi and melanomas. The extracted data is used to train the Feed-Forward Back Propagation Networks (FFBPNs). The number of neurons in the hidden layer varies: it can be 8, 16, 24, or 32. The results indicate skewness features computed for the red channel in the RGB color space as the best choice to reach the goal of our study. The reported result shows the advantages of monochrome channels representation for skin lesions diagnosis.

Feasibility of Hybrid PSO-ANN Model for Identifying Soybean Diseases

Soybean disease has become one of vital factors restricting the sustainable development of high-yield and high-quality soybean industry. A hybrid artificial neural network (ANN) model optimized via particle swarm optimization (PSO) algorithm, which is denoted as PSO-ANN, is proposed in this paper for soybean diseases identification based on categorical feature inputs. Augmentation dataset is created via Synthetic minority over-sampling technique (SMOTE) to deal with quantitative insufficiency and categorical unbalance of the dataset. PSO algorithm is used to optimize the parameters in ANN, including the activation function, the number of hidden layers, the number of neurons in each hidden layer and the optimizer. In the end, ANN model with 2 hidden layers, 63 and 61 neurons in hidden layers respectively, Relu activation function and Adam optimizer yields the best overall test accuracy of 92.00%, compared with traditional machine learning methods. PSO-ANN shows superiority on various evaluation metrics, which may have great potential in crop diseases control for modern agriculture.

Neural Approach in Short-Term Outdoor Temperature Prediction for Application in HVAC Systems

An accurate air-temperature prediction can provide the energy consumption and system load in advance, both of which are crucial in HVAC (heating, ventilation, air conditioning) system operation optimisation as a way of reducing energy losses, operating costs, as well as pollution and dust emissions while maintaining residents’ thermal comfort. This article presents the results of an outdoor air-temperature time-series prediction for a multifamily building with the use of artificial neural networks during the heating period (October–May). The aim of the research was to analyse in detail the created neural models with a view to select the best combination of predictors and the optimal number of neurons in a hidden layer. To meet that task, the Akaike information criterion was used. The most accurate results were obtained by MLP 3-3-1 (r = 0.986, AIC = 1300.098, SSE = 4467.109), with the ambient-air-temperature time series observed 1, 2, and 24 h before the prognostic temperature as predictors. The AIC proved to be a useful method for the optimum model selection in a machine-learning modelling. What is more, neural network models provide the most accurate prediction, when compared with LR and SVR. Additionally, the obtained temperature predictions were used in HVAC applications: entering-water temperature and indoor temperature modelling.

Artificial Neural Networks Based Optimization Techniques: A Review

In the last few years, intensive research has been done to enhance artificial intelligence (AI) using optimization techniques. In this paper, we present an extensive review of artificial neural networks (ANNs) based optimization algorithm techniques with some of the famous optimization techniques, e.g., genetic algorithm (GA), particle swarm optimization (PSO), artificial bee colony (ABC), and backtracking search algorithm (BSA) and some modern developed techniques, e.g., the lightning search algorithm (LSA) and whale optimization algorithm (WOA), and many more. The entire set of such techniques is classified as algorithms based on a population where the initial population is randomly created. Input parameters are initialized within the specified range, and they can provide optimal solutions. This paper emphasizes enhancing the neural network via optimization algorithms by manipulating its tuned parameters or training parameters to obtain the best structure network pattern to dissolve the problems in the best way. This paper includes some results for improving the ANN performance by PSO, GA, ABC, and BSA optimization techniques, respectively, to search for optimal parameters, e.g., the number of neurons in the hidden layers and learning rate. The obtained neural net is used for solving energy management problems in the virtual power plant system.

Application of Keras neural network in the era of big data

The experiment uses crawler tools to obtain data, and the data is preprocessed to find missing values and eliminate invalid data, meanwhile, the model is constructed by information entropy and ID3 algorithm so as to select the desired amount of features, and then basic modeling and data filtering is performed to train and evaluate the model for the first time, finally, in order to get a more ideal model, this experiment The optimal model is obtained by changing the number of hidden layers and neurons of the neural network to build a high-level neural network API neural network model written by pure python - Keras neural network model. The results show that when the model defines a 2-layer neural network and the number of neurons in the hidden layer is fourteen, the accuracy of the model is the highest, and the accuracy of the test set is as high as ninety-one percent.

Application of neural network to simulate the behavior of hospitalizations and their costs under the effects of various polluting gases in the city of São Paulo.

This work aims to obtain an artificial neural network to simulate hospitalizations for respiratory diseases influenced by pollutant gaseous such as CO, PM10, PM2.5, NO2, O3, and SO2 emitted from 2011 to 2017, in the city of São Paulo. The hospitalization costs were also be calculated. MLP and RBF neural networks have been tested by varying the number of neurons in the hidden layer and the type of equation of the output function. The following pollutants and its concentration range were collected considering the supervision of Alto Tiete station set, in several neighborhoods in the city of São Paulo, from in the period 2011 to 2017: 28–63 µg/m3 of PM2.5, 52–110 µg/m3 of PM10, 49–135 µg/m3 of O3, 0.8–2.6 ppm CO, 41–98 µg/m3 of NO2, and 3–16 µg/m3 of SO2. Results showed that a RBF neural network with 6 input neurons, 13 hidden layer neurons, and 1 output neuron, using BFGS algorithm and a Gaussian function to neuronal activation, was the best fitted to the experimental datasets. So, knowing the monthly concentration of gaseous pollutions was possible to predict the hospitalization of 1464 to 3483 ± 510 patients, with costs between 570,447 and 1,357,151 ± 198,171 USD per month. This way, it is possible to use this neural network to predict the costs of hospitalizing patients for respiratory diseases and to contribute to the decision-making of how much the government should spend on health care.

Prediction of greenhouse tomato yield using artificial neural networks combined with sensitivity analysis

In this paper, artificial neural networks (ANNs) combined with sensitivity analysis was applied to predict greenhouse tomato yield (Lycopersicon esculentum Mill.) and bring out the most influencing inputs on tomato production. The models were created using data randomly collected by a face-to-face survey from 25 greenhouse tomato farms in Biskra Province, Algeria. Results showed that total energy inputs were 94 748.2 MJ.ha−1 while energy ratio was 1.055 indicating a relatively low energy efficiency. Different ANN models were tested by varying the number of neurons in the hidden layer from 1 to 40. Based on statistics criteria, the best structure found is 12–34–1. This ANN model was used to estimate tomato yield using the energy inputs. Then, the results of ANN model were compared with those from the multiple linear regression (MLR) technique. The results illustrated that ANN provided more accurate predictions than the MLR technique. Sensitivity analysis revealed that insecticides, farmyard manure (FYM), potassium (K2O), nitrogen (N), electricity and fungicides are the most significant inputs in the greenhouse tomato production. In conclusion, ANNs are simple and effective tools for predicting tomato yield and extracting knowledge via sensitivity analysis.

MDF-SA-DDI: predicting drug-drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism.

One of the main problems with the joint use of multiple drugs is that it may cause adverse drug interactions and side effects that damage the body. Therefore, it is important to predict potential drug interactions. However, most of the available prediction methods can only predict whether two drugs interact or not, whereas few methods can predict interaction events between two drugs. Accurately predicting interaction events of two drugs is more useful for researchers to study the mechanism of the interaction of two drugs. In the present study, we propose a novel method, MDF-SA-DDI, which predicts drug-drug interaction (DDI) events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism. MDF-SA-DDI is mainly composed of two parts: multi-source drug fusion and multi-source feature fusion. First, we combine two drugs in four different ways and input the combined drug feature representation into four different drug fusion networks (Siamese network, convolutional neural network and two auto-encoders) to obtain the latent feature vectors of the drug pairs, in which the two auto-encoders have the same structure, and their main difference is the number of neurons in the input layer of the two auto-encoders. Then, we use transformer blocks that include self-attention mechanism to perform latent feature fusion. We conducted experiments on three different tasks with two datasets. On the small dataset, the area under the precision-recall-curve (AUPR) and F1 scores of our method on task 1 reached 0.9737 and 0.8878, respectively, which were better than the state-of-the-art method. On the large dataset, the AUPR and F1 scores of our method on task 1 reached 0.9773 and 0.9117, respectively. In task 2 and task 3 of two datasets, our method also achieved the same or better performance as the state-of-the-art method. More importantly, the case studies on five DDI events are conducted and achieved satisfactory performance. The source codes and data are available at https://github.com/ShenggengLin/MDF-SA-DDI.

A non-tuned machine learning method to simulate ice-seabed interaction process in clay

Exploitation of oil and gas in the Arctic area is expected to expand in the coming years. These hydrocarbons are transferred through subsea pipelines from offshore to onshore; however, the marine pipelines are threatened by traveling icebergs where the seabed may be gouged by the moving masses in warmer months. Subsea trenching and backfilling are usually utilized to bury the subsea pipelines for physical protection against the ice scouring. Regarding the stress-based design methods, deformations and forces are generally the controlling design factors for the subsea assets. In this study, the subgouge clay displacements and the reaction forces were simulated using a non-tuned self-adaptive machine learning (ML) entitled “self-adaptive extreme learning machine” (SAELM). Initially, fifteen SAELM models were defined by means of the parameters affecting the ice-scoured features. Subsequently, 70% and 30% of the constructed dataset were respectively applied to train and test the ML models. After that, the optimum number of hidden layer neurons and the best activation function were selected for the SAELM network. By conducting a comprehensive sensitivity analysis, the premium SAELM models and the most influencing input parameters in estimation of the subgouge clay characteristics were introduced. Regarding the performed analyses, the horizontal load factor and the gouge depth ratio were identified as the most influential parameters to model the reaction forces, whereas the soil depth had a significant impact for simulation of the ice-induced clay deformations. Finally, a set of SAELM-based equations were presented to estimate the subgouge clay parameters.

Artificial Intelligence to Analyze the Cortical Thickness Through Age.

In this study, Artificial Intelligence was used to analyze a dataset containing the cortical thickness from 1,100 healthy individuals. This dataset had the cortical thickness from 31 regions in the left hemisphere of the brain as well as from 31 regions in the right hemisphere. Then, 62 artificial neural networks were trained and validated to estimate the number of neurons in the hidden layer. These neural networks were used to create a model for the cortical thickness through age for each region in the brain. Using the artificial neural networks and kernels with seven points, numerical differentiation was used to compute the derivative of the cortical thickness with respect to age. The derivative was computed to estimate the cortical thickness speed. Finally, color bands were created for each region in the brain to identify a positive derivative, that is, a part of life with an increase in cortical thickness. Likewise, the color bands were used to identify a negative derivative, that is, a lifetime period with a cortical thickness reduction. Regions of the brain with similar derivatives were organized and displayed in clusters. Computer simulations showed that some regions exhibit abrupt changes in cortical thickness at specific periods of life. The simulations also illustrated that some regions in the left hemisphere do not follow the pattern of the same region in the right hemisphere. Finally, it was concluded that each region in the brain must be dynamically modeled. One advantage of using artificial neural networks is that they can learn and model non-linear and complex relationships. Also, artificial neural networks are immune to noise in the samples and can handle unseen data. That is, the models based on artificial neural networks can predict the behavior of samples that were not used for training. Furthermore, several studies have shown that artificial neural networks are capable of deriving information from imprecise data. Because of these advantages, the results obtained in this study by the artificial neural networks provide valuable information to analyze and model the cortical thickness.

A Comparative Study of Multiple Regression and Machine Learning Techniques for Prediction of Nanofluid Heat Transfer

Abstract The aim of this article is to introduce and discuss prediction power of the multiple regression technique, artificial neural network (ANN), and adaptive neuro-fuzzy interface system (ANFIS) methods for predicting the forced convection heat transfer characteristics of a turbulent nanofluid flow in a pipe. Water and Al2O3 mixture is used as the nanofluid. Utilizing fluent software, numerical computations were performed with volume fraction ranging between 0.3% and 5%, particle diameter ranging between 20 and 140 nm, and Reynolds number ranging between 7000 and 21,000. Based on the computationally obtained results, a correlation is developed for the Nusselt number using the multiple regression method. Also, based on the computational fluid dynamics results, different ANN architectures with different number of neurons in the hidden layers and several training algorithms (Levenberg–Marquardt, Bayesian regularization, scaled conjugate gradient) are tested to find the best ANN architecture. In addition, ANFIS is also used to predict the Nusselt number. In the ANFIS, number of clusters, exponential factor, and membership function (MF) type are optimized. The results obtained from multiple regression correlation, ANN, and ANFIS were compared. According to the obtained results, ANFIS is a powerful tool with a R2 of 0.9987 for predictions.

METHOD OF NEURAL NETWORK DETECTION OF ANOMALIES IN DATA OF WASTE-FREE PRODUCTION AUDIT

The paper presents a method for the detection of anomalies in waste-free production audit data based on the neural network model of Gauss-Bernoulli of the forward only restricted Cauchy machine (FORCM). The purpose of the work is to increase the efficiency of audit data analysis of waste-free production on the basis of the neural network model of anomalies detection without the use of the marked data that simplifies audit.
 To achieve this goal, the following tasks have been set and solved: offered model of generalized multiple transformations of audit data in the form of a two-layer neural network. Cauchy offered neural network model of Gauss-Bernoulli of the forward only restricted Cauchy machine possesses a heteroassociative memory; works real data; has no restrictions for storage capacity; provide high accuracy of detection of anomalies; uses Cauchy's distribution that increases the speed of convergence of a method of parametrical identification. To increase the speed of Gauss-Bernoulli parametric identification of a forward only restricted Cauchy machine, a parametric identification algorithm was developed to be implemented on a GPU using CUDA technology. The offered algorithm allows increasing training speed by approximately proportional to the product of numbers of neurons in the hidden layer and power of a training set.
 The experiments confirmed the operability of the developed software and allow to recommend it for use in practice in a subsystem of the automated analysis of DSS of audit for detection of anomalies.

Prediction of Total Electron Content (TEC) using Neural Network over Anomaly Crest Region Bhopal

In the present work neural network has been developed for the prediction of Vertical Total Electron Content (VTEC) over Bhopal (23.2°N, 77.4°E & MLAT 14.2°N), an equatorial anomaly crest region. The study is based on the VTEC data recorded by a multi-frequency multi-constellation GNSS receiver installed at Bhopal during May 2016 to August 2017. Neural Network (NN) consists of artificial neurons that are used to learn data patterns adjusting weights between input, hidden and output layers by computational modelling. In order to obtain the optimal number of neurons in the hidden layer, the performance of four systems of neural network have been tested. Out of which, the fourth neural network has been used to predict VTEC with 7 input neurons in the present study. The number of hidden layer neurons is a factor that affects the performance of the trained networks. The input layer of the network includes the year, day of the year, hour of the day, geographic latitude, geographic longitude, SSN and IRI NmF2. We have compared the TEC obtained from the neural network prediction (NN TEC), GPS derived TEC (GPS TEC) and TEC from IRI-2016 model (IRI TEC) and analysis has been made. We observed that the Root Mean Square Error (RMSE) decreases with increase in the number of hidden layer neurons. The RMSE comes out to be lowest (1.96 TECU), when the number of hidden layer neurons are 41.The TEC predicted from the NN model and estimated from GPS receiver have same trend at 01:00 and 07:00 UT. The modelled NN TEC values are in good agreement with GPS TEC values for all seasons and 0.99 correlation coefficient was calculated for summer months, but IRI TEC always underestimates GPS TEC in all seasons. The NN model excellently predicted the TEC values of August 2017 by putting the credentials of August 2016 and only 0.55–32.16% relative errors were estimated between them whereas it reaches up to 93.86% with IRI TEC. Thus, the result shows that the proposed NN model can predict the diurnal and seasonal GPS TEC more accurate than IRI over anomaly crest region Bhopal. However, the inclusion of IRI-NmF2 as input layer neuron increases the network performance.

Modeling Prediction and Research on Leaf Moisturizing Effect of Tobacco Redrying

This paper studies the influence of the process parameter setting of the hot-air leaf moisturizer on the quality index of the exit leaf during the secondary leaf conditioning of threshing and redrying, and establishes the corresponding prediction model. According to the characteristics of the characteristic process data of the secondary moisturizing, the prediction models of BP neural network and cyclic neural network are established. Call the current popular neural network writing framework TensorFlow’s high-level API interface to build the neural network structure. Gradually optimize the activation function, optimizer, number of hidden layer neurons and other key parameters in the neural network structure to make the prediction results of the test set reach the best state. By inputting the parameters of the front steam nozzle pressure, the front-end water flow rate, the hot air temperature, the return air temperature, the temperature of the feed blade, and the water combination of the feed blade, two key tobacco leaf evaluation indicators are predicted for the outlet leaf moisture and temperature. Based on the mean square error, root mean square error, and average absolute error of the prediction results as quantitative indicators, the three indicators of BP neural network are 7.17, 2.68, 1.83, and the three indicators of cyclic neural network are 4.70, 2.16, 1.74. It is concluded that the cyclic neural network has the best prediction effect. It has certain reference value for the tobacco factory to adjust the process parameters of the secondary leaf conditioning according to different conditions.

The cerebellar anatomy of red junglefowl and white leghorn chickens: insights into the effects of domestication on the cerebellum.

Domestication is the process by which wild organisms become adapted for human use. Many phenotypic changes are associated with animal domestication, including decreases in brain and brain region sizes. In contrast with this general pattern, the chicken has a larger cerebellum compared with the wild red junglefowl, but what neuroanatomical changes are responsible for this difference have yet to be investigated. Here, we quantified cell layer volumes, neuron numbers and neuron sizes in the cerebella of chickens and junglefowl. Chickens have larger, more folded cerebella with more and larger granule cells than junglefowl, but neuron numbers and cerebellar folding were proportional to cerebellum size. However, chickens do have relatively larger granule cell layer volumes and relatively larger granule cells than junglefowl. Thus, the chicken cerebellum can be considered a scaled-up version of the junglefowl cerebellum, but with enlarged granule cells. The combination of scaling neuron number and disproportionate enlargement of cell bodies partially supports a recent theory that domestication does not affect neuronal density within brain regions. Whether the neuroanatomical changes we observed are typical of domestication or not requires similar quantitative analyses in other domesticated species and across multiple brain regions.

A robust methodology for optimizing the topology and the learning parameters of an ANN for accurate predictions of laser-cut edges surface roughness

The Feed-Forward and Backpropagation Artificial Neural Networks (FFBP-ANN) are generally employed for cut surfaces quality characteristics predictions. However, the determination of the neurons on the hidden layer and the training parameters’ values are tasks requiring many trials according to the Full-Factorial Approach (FFA). Therefore, in this work, a methodology is presented for the optimization of an FFBP-NN and the application of the Taguchi Design of Experiments (TDE). Nine combinations of four variables were examined, having three levels each, according to the L9 (34) orthogonal array. The number of neurons in the hidden layer (N), the learning rate (mu), the increment factor (mu+) and the decrement factor (mu-) are employed as variables. In addition, Mean Squared Error (MSE) and overall regression index (Rall) was decided as the objective functions. Thus, TDE diminishes the FFBP-ANN arrangements to nine from eighty-one of FFA. The optimized FFBP-ANN predicts the surface roughness in various cut depths during laser cutting of thin thermoplastic plates.

A low-cost and efficient electronic nose system for quantification of multiple indoor air contaminants utilizing HC and PLSR

A novel quantification technique is presented for electronic nose (E-nose), which is based on a double-step strategy combined with hierarchical classifier (HC) and partial least squares regression (PLSR). With the tree structure of HC, the complexity of classifier training process can be reduced in the case of unbalanced samples. For each level of the class hierarchy, the extreme learning machine-based artificial neural network (ELM-ANN) is applied for classification. In order to improve the classification performance of ELM-ANN, the multiple time-domain features are selected as training inputs, and a novel optimization method of the number of hidden layer neurons is given. To validate the effectiveness of the presented quantification technique, an E-nose system is designed to quantify the gases including six toxic gases (hydrogen sulfide, carbon monoxide, ammonia, toluene, formaldehyde, acetone) and three kinds of binary gas mixtures. This presented hierarchical classifier has demonstrated outstanding performance for the identification of target gases, such as the macro-averaged precision for unlabeled data is improved from 80% to 92% compared with non-hierarchical classifiers. Furthermore, an excellent performance of concentration estimation is obtained utilizing PLSR, where average values of the coefficient of determination for training and test samples are equal to 0.957 and 0.927, respectively. Overall, our work demonstrates that the proposed approach is applicable in E-nose-based odor quantification.