Number Of Neurons In Layer Research Articles

A Study of Feature Construction Based on Least Squares and RBF Neural Networks in Sports Training Behaviour Prediction.

This paper examines the problem of athletes' training in sports, exploring the methods and means by which athletes can perform difficult movements in which they normally make minor training errors in order to achieve better competition results and placements. To this end, we test the explanatory and predictive effects of a theoretical model starting with planned behaviour and then use exercise planning, self-efficacy, and support as variables to develop a partial least squares regression model of sports to improve the explanation and prediction of sporting athletes' intentions and behaviour. An improved RBF network-based method for player behaviour prediction is proposed. On the basis of the RBF analysis, the number of layers and the number of neurons in the hidden layer of the network are adjusted and optimised, respectively, to improve its generalisation and learning abilities, and the athlete behaviour prediction model is given. The results demonstrate the advantages of the improved algorithm, which in turn provides a more scientific approach to the current basketball training.

Applying artificial neural-network model to predict psychiatric symptoms.

IntroductionMental disorders result in mental disabilities and discomfort in the affected person as they affect both thinking and behavior. Therefore, more vulnerable people must first be identified to improve the psychological level of society.AimThis study aims to determine the importance of gender, employment, education, place of residence, and age in predicting mental disorders using artificial neural network modeling.MethodsThe pattern held between variables in this study will be identified using multilayer feed-forward back-propagation neural networks with five inputs and 10 outputs. To determine the neural network with the least sum of square errors, we evaluated the performance of all neural networks with varying algorithms and different numbers of neurons in the hidden layer. Data were analyzed for 380 people aged 10–82 years using the SPSS software.ResultsThe optimal neural network model was effective in predicting mental disorders. In this model, the variables of the place of residence, education, age, gender, and employment were important in fitting the optimal model with 34.08, 20.11, 18.93, 14.55, and 12.33%, respectively. The accuracy rate for the neural network model was 99.2%.ConclusionTo achieve further results in improving mental health problems, it is better to focus more on employed, rural, and younger people with a non-tertiary education level.

Optimasi Neural Network Dengan Menggunakan Algoritma Genetika Untuk Prediksi Jumlah Kunjungan Wisatawan

West Nusa Tenggara is one of the tourist attractions in Indonesia which has a certain attraction for tourists. With the increase in tourism in NTB, it is necessary to make adequate efforts to maintain tourist objects and attractions. In an effort to maintain a tourist attraction, the NTB provincial tourism office needs to analyze and predict the arrival of local and international tourists. The current analysis and prediction process is still being carried out by collecting data from each tourist attraction entrance. The processed data produces predictions of tourist arrivals, both local and international, where the data processing process takes a long time and requires high human resources. To overcome these problems, it is done by applying computational predictions. Computational predictions can minimize the prediction time and human resources required. The method used is a neural network algorithm with optimized parameters using a genetic algorithm. The optimized parameters are the hidden layer, the number of neurons in the input layer, momentum and others. The data used is time series data from 1997 to 2018. From the neural network experiment, the parameters of the number of neurons in the input layer xt-7 are determined, the number of neurons in the hidden layer 10, the training cycle value is 400, the learning rate value is 0.3 and the momentum value is 0.2. From the experiment, the RMSE value of 0.050 was obtained. While the RMSE value for the neural network algorithm parameters optimized using the genetic algorithm is 0.044. Because of this, it can be stated genetic algorithm with neural network can be used to determine the hidden layer and the number of hidden nodes, the right features, momentum, initialize, and optimize the weight of the neural network. So that the application of the genetic algorithm to optimize the parameter values of the neural network algorithm is better than the application of the neural network algorithm without optimization.

Comparative Study of Machine-Learning Frameworks for the Elaboration of Feed-Forward Neural Networks by Varying the Complexity of Impedimetric Datasets Synthesized Using Eddy Current Sensors for the Characterization of Bi-Metallic Coins

A suitable framework for the development of artificial neural networks is important because it decides the level of accuracy, which can be reached for a certain dataset and increases the certainty about the reached classification results. In this paper, we conduct a comparative study for the performance of four frameworks, Keras with TensorFlow, Pytorch, TensorFlow, and Cognitive Toolkit (CNTK), for the elaboration of neural networks. The number of neurons in the hidden layer of the neural networks is varied from 8 to 64 to understand its effect on the performance metrics of the frameworks. A test dataset is synthesized using an analytical model and real measured impedance spectra by an eddy current sensor coil on EUR 2 and TRY 1 coins. The dataset has been extended by using a novel method based on interpolation technique to create datasets with different difficulty levels to replicate the scenario with a good imitation of EUR 2 coins and to investigate the limit of the prediction accuracy. It was observed that the compared frameworks have high accuracy performance for a lower level of difficulty in the dataset. As the difficulty in the dataset is raised, there was a drop in the accuracy of CNTK and Keras with TensorFlow depending upon the number of neurons in the hidden layers. It was observed that CNTK has the overall worst accuracy performance with an increase in the difficulty level of the datasets. Therefore, the major comparison was confined to Pytorch and TensorFlow. It was observed for Pytorch and TensorFlow with 32 and 64 neurons in hidden layers that there is a minor drop in the accuracy with an increase in the difficulty level of the dataset and was above 90% until both the coins were 80% closer to each other in terms of electrical and magnetic properties. However, Pytorch with 32 neurons in the hidden layer has a reduction in model size by 70% and 16.3% and predicts the class, 73.6% and 15.6% faster in comparison to TensorFlow and Pytorch with 64 neurons.

Effective Hybrid Soft Computing Approach for Optimum Design of Shallow Foundations

In this study, an effective intelligent system based on artificial neural networks (ANNs) and a modified rat swarm optimizer (MRSO) was developed to predict the ultimate bearing capacity of shallow foundations and their optimum design using the predicted bearing capacity value. To provide the neural network with adequate training and testing data, an extensive literature review was used to compile a database comprising 97 datasets retrieved from load tests both on large-scale and smaller-scale sized footings. To refine the network architecture, several trial and error experiments were performed using various numbers of neurons in the hidden layer. Accordingly, the optimal architecture of the ANN was 5 × 10 × 1. The performance and prediction capacity of the developed model were appraised using the root mean square error (RMSE) and correlation coefficient (R). According to the obtained results, the ANN model with a RMSE value equal to 0.0249 and R value equal to 0.9908 was a reliable, simple and valid computational model for estimating the load bearing capacity of footings. The developed ANN model was applied to a case study of spread footing optimization, and the results revealed that the proposed model is competent to provide better optimal solutions and to outperform traditional existing methods.

Remote Sensing Image Recognition Based on LOG-T-SSA-LSSVM and AE-ELM Network.

Aiming at the influence of different working conditions on recognition accuracy in remote sensing image recognition, this paper adopts hierarchical strategy to construct a network. Firstly, in order to establish the classification relationship between different samples, labeled samples are used for classification. A Logistic-T-distribution-Sparrow Search Algorithm-Least Squares Support Vector Machines (LOG-T-SSA-LSSVM) classification network is proposed. LOG-T-SSA algorithm is used to optimize parameters in LSSVM to establish a better network to achieve accurate classification between sample sets and then identify according to different categories. Through UCI dataset test, the accuracy of LOG-T-SSA-LSSVM network classification is significantly improved compared with that of contrast network. The autoencoder is integrated with Extreme Learning Machine, and the autoencoder is used to realize data compression. The advantages of Extreme Learning Machine (ELM) network, such as less training parameters, fast learning speed, and strong generalization ability, are fully utilized to realize efficient and supervised recognition. Experiments verify that the autoencoder-extreme learning machine (AE-ELM) network has a good recognition effect when the sigmoid activation function is selected and the number of hidden layer neurons are 2000. Finally, after image recognition under different working conditions, it is proved that the recognition accuracy of AE-ELM based on LOG-T-SSA-LSSVM classification is significantly improved compared with traditional ELM network and Particle Swarm Optimization-Extreme Learning Machine (PSO-ELM) network.

Growth of MWCNTs from Azadirachta indica oil for optimization of chromium(VI) removal efficiency using machine learning approach.

The main objective of the present study is to develop artificial neural networks (ANN) to predict the adsorption efficiency of multi-walled carbon nanotubes (MWCNTs) on Cr(VI) removal. Polydisperse MWCNTs were synthesized at 750°C on alumina supported Fe-Co-Mo catalyst using CVD (chemical vapor deposition)-assisted spray pyrolysis of Azadirachta indica (Neem) oil under inert Argon (Ar) atmosphere. Growth of MCWNTs with inner diameters between 9 and 14nm was corroborated by scanning electron microscopy (SEM), high resolution transmission electron microscopy (HRTEM), X-ray diffraction analysis (XRD), and Raman spectral evidence assessments. The metal-ion adsorbent capacity (Cr-VI) of the as such prepared MWCNTs was examined for industrial purposes. Different parameters such as adsorption isotherms, kinetics, and thermodynamic parameters were analyzed for the removal of metal ions with MWCNTs. The results of isotherm, kinetic, and thermodynamic study indicated that the process suited well with Langmuir isotherm, pseudo second-order kinetics, and followed endothermic reaction, respectively. The effects of parameters such as adsorbent dosage, concentration of chromium ion (Cr-VI), pH, and contact time were studied to optimize the maximum removal of Cr(VI). In order to optimize the process conditionsusing Artificial Neural Networks, Box-Behnken design (BBD)was used to design the batch adsorption experiments, and the resulting datasets were used as the input for ANN. To predict the adsorption efficiency, various ANN architectures were examined using different training algorithms, number of neurons in the hidden layer, and the transfer function for the hidden and output layers. A neural network structure with Levenberg-Marquardt (LM) training algorithm, 14 hidden neurons, and tangent sigmoid transfer function at the hidden layer and logarithmic sigmoid transfer function at the output layer furnished the best level of prediction results. Comparing with experimental data, the optimal model capitulated mean square error (MSE),and correlation coefficient (R2) of 0.0324 and 0.99512, respectively. The results showed that ANN is well-organized in predicting the adsorption efficiency of MWCNTs for Cr(VI) metal ion removal process.

Multiple IoT based Network Attacks Discrimination by Multilayer Feedforward Neural Networks

In this paper a new neural model for detection of multiple network IoT-based attacks, such as DDoS TCP, UDP, and HHTP flood, is presented. It consists of feedforward multilayer network with back propagation. A general algorithm for its optimization during training is proposed, leading to proper number of neurons in the hidden layers. The Scaled Gradient Descent algorithm and the Adam optimization are studied with better classification results, obtained by the developed classifiers, using the latter. Tangent hyperbolic function appears to be proper selection for the hidden neurons. Two sets of features, gathered from aggregated records of the network traffic, are tested, containing 8 and 10 components. While more accurate results are obtained for the 10-feature set, the 8-feature set offers twice lower training time and seems applicable for real-world applications. The detection rate for 7 of 10 different network attacks, primarily various types of floods, is higher than 90% and for 3 of them – mainly reconnaissance and keylogging activities with low intensity of the generated traffic, deviates between 57% and 68%. The classifier is considered applicable for industrial implementation.

Using machine-learning technique for estrus onset detection in dairy cows from acceleration and location data acquired by a neck-tag

To promote reproductive performance in dairy cows, the timely and accurate detection of estrus onset associated with ovulation time is necessary. However, poor heat detection by manual inspection and incompetent monitoring ability via the current automated estrus discrimination methods, lead to an unsatisfactory pregnancy rate. The aim of this study was to evaluate the potential of machine learning technique based on acceleration and location data to identify the onset of estrus in dairy cows. Measurements were obtained from 296 lactating cows housed in a free-stall barn for 8 months. A total of 325 estrus events were used for modelling and testing, consisting of 2768 1-h estrus time windows and 20,632 1-h non-estrus time windows. The backpropagation neural network (BPNN) algorithm with optimized parameter combination of the number of hidden layer neurons and learning rate were investigated to automatically detect estrus onset from seven behavioral metrics, which were: duration of standing, duration of lying, duration of walking, steps, displacement, switching times between standing and walking, and number of standing mounts. The study showed that the accuracy, precision, sensitivity, specificity and F1 score of the BPNN algorithm were up to 95.46%, 72.80%, 98.29%, 95.08%, 83.65%, respectively, enabling automated estrus identification. Compared to the support vector machine (SVM) and logistic regression (LR) algorithms, the perception capability of the proposed method of estrus onset was comparable in performance to manual inspection as assessed by mean, standard deviation, absolute value of the difference, and consistency, making it an excellent alternative to replace laborious visual observation.

Design an Artificial Neural Network by MLP Method; Analysis of the Relationship between Demographic Variables, Resilience, COVID-19 and Burnout

In addition to the effect that the COVID-19 pandemic has had on the physical and mental health of individuals, it has also led to a change in the mental and emotional state of many employees. Especially among businesses and private companies, which faced many restrictions due to the special conditions of the pandemic. Therefore, the present study aimed to design an artificial neural network with MLP technique to analyze the relationship between demographic variables, resilience, COVID-19 and burnout in start-ups in Iran. The research method was quantitative. Managers and employees of start-ups formed the statistical population of the study, based on the statistical sample size of the unlimited community, 384 of them were tested. For data gathering, standard questionnaires include of MBI-GS and BRCS and researcher-made questionnaire of stress caused by COVID-19 were used. The validity of the questionnaires was confirmed by a panel of experts and their reliability was confirmed by Cronbach’s alpha coefficient. The number of neurons in the input layer was equal to 10, the number of neurons in the 1st hidden layer was equal to 7, the number of neurons in the output layer was equal to 1, and the number of epochs was equal to 500. 70% of the data were used for training and 30% for testing. In the designed artificial neural network, all experiment data except one were correctly predicted and the obtained MAE error was less than 0.012%. Finally, he precision and correction of the presented model was confirmed by the obtained results.

ПРОГНОЗНАЯ МОДЕЛЬ ЭЛЕКТРОПОТРЕБЛЕНИЯ НА ОСНОВЕ ПОЛНОСВЯЗНОЙ НЕЙРОННОЙ СЕТИ

The relevance The relevance of electricity consumption forecasting on the basis of fully connected feed-forward neural networks (FNN) to improve the validity of applications for electricity is considered. Aim of research Synthesis of predictive model of electricity consumption in the form of four-layer fully connected feed-forward neural network, linking the volume of production and the predicted electricity consumption is performed. Research methods The algorithm of the predictive model development includes: formation and initial statistical processing of initial data; determination of FNN structure hyperparameters — total number of layers, number of neurons in layers, activation function, training rate coefficient; selection of optimization method; training, checking model adequacy. Results The analytical expression for the description of the forecast model based on FNN is given. The synthesized forecast model makes it possible to increase the validity of electric power applications of enterprises.

Research on Intelligent Identification of PD Patterns Based on the Fingerprint Features

Five-electrode configurations were designed to simulate the distribution inhomogeneity of electric field intensities in the air-insulating medium, and the characteristic data waveforms of partial discharge generated by different electrode configurations under the excitation of power frequency AC voltage were carefully collected in this paper. Furthermore, the feature vectors of the corresponding fingerprint, contained in partial discharge data, were extracted by rigorous mathematical algorithms, and the artificial neural network was employed to realize the pattern recognition of partial discharge caused by the inhomogeneity of electric field intensity with different electrode configurations. The results indicate that the J4 value in the space of 7 feature quantities is 1905.6, and the recognition rate is 100% when the hidden layer neuron of the network is 19. However, the J5 value of 9 feature quantities is 1589.9, and the purpose of recognition has been achieved when the number of hidden layer neurons of the network is 6. Increasing the number of hidden layer neurons will only waste computing resources. Of course, PD information collection mode, feature quantity selection, optimal feature space composition, network structure and classification algorithm are the key to realizing PD fault intelligence identification.

Comparison of MLP and RBF Neural Networks in the Task of Classifying the Diameters of Water Pipes

Hydraulic calculations of water distribution systems are currently performed using computer programs. In addition to the basic calculation procedure, modules responsible for evaluating the obtained calculation results are introduced more and more often into the programs. This article presents the results of research on artificial neural networks with a radial base function (RBF) and a multilayer perceptron (MLP), aimed at determining whether they can be used to model the relationship between the variables describing the computational section of the water distribution system and the diameter of the water pipe. The classification capabilities of the RBF and MLP networks were analyzed according to the number of neurons in the hidden layer of the network. A comparative analysis of RBF networks with multilayer perceptron (MLP) networks was performed. The results showed that the MLP networks have much better classification properties and are better suited for the task of assessing the selected diameters of the water pipes.

LSTM with particle Swam optimization for sales forecasting

• Propose a sale forecasting approach based on LSTM with PSO for E-commerce companies. • The number of hidden neurons and iterations in LSTM are optimized by PSO. • We compare the proposed approach with 9 competing approaches. • Evaluated on the real datasets from an E-commerce company and 3 benchmark datasets. • Proposed models achieved good results in forecasting accuracy. Sales volume forecasting is of great significance to E-commerce companies. Accurate sales forecasting enables managers to make reasonable resource allocation in advance. In this paper, we propose a novel approach based on Long Short-Term Memory with Particle Swam Optimization (LSTM-PSO) for sale forecasting in E-commerce companies. In the proposed approach, the number of hidden neurons in different LSTM layers, and the number of iterations for training are optimized by Particle Swam Optimization metaheuristic. In the experiments, we compare the proposed approach with 9 competing approaches. The effectiveness of the proposed approach is evaluated on the real datasets from an E-commerce company as well as on the publicly available benchmark datasets. In the experiments, neural network design, activation functions, methods of regularization, and the training method of neural network are also analyzed. Experiment results show that the proposed PSO-LSTM models achieved good results in forecasting accuracy.

A Novel Method for Solving Nonlinear Schrödinger Equation with a Potential by Deep Learning

The improved physical information neural network algorithm has been proven to be used to study integrable systems. In this paper, the improved physical information neural network algorithm is used to study the defocusing nonlinear Schrödinger (NLS) equation with time-varying potential, and the rogue wave solution of the equation is obtained. At the same time, the influence of the number of network layers, neurons and the number of sampling points on the network performance is studied. Experiments show that the number of hidden layers and the number of neurons in each hidden layer affect the relative L2-norm error. With fixed configuration points, the relative norm error does not decrease with the increase in the number of boundary data points, which indicates that in this case, the number of boundary data points has no obvious influence on the error. Through the experiment, the rogue wave solution of the defocusing NLS equation is successfully captured by IPINN method for the first time. The experimental results of this paper are also compared with the results obtained by the physical information neural network method and show that the improved algorithm has higher accuracy. The results of this paper will be contributed to the generalization of deep learning algorithms for solving defocusing NLS equations with time-varying potential.

ARTIFICIAL NEURAL NETWORKS TO PREDICT EFFICIENCIES IN SEMI-MECHANIZED BEAN (Phaseolus vulgaris L.) HARVEST

Bean is among the most consumed and produced crops in Brazil. Given the high demand for food, the search for technologies and controllers to increase the efficiency of agricultural systems has grown. This study aimed to model artificial neural network (ANN) architectures to predict mechanical efficiencies in the semi-mechanized bean harvest. We used a multilayer perceptron network with three inputs (harvest moisture, threshing rotor rotation, and feed rate), two hidden layers of neurons, and one output (efficiency). We evaluated the efficiency in the header, separation on the threshing rotor, cleaning of sieves, and the total efficiency of the machine. ANN was processed by a scripted algorithm to model the network, alternate the number of neurons in hidden layers, as well as to select, test, and validate ANN with less error. ANN was validated by comparing its results with the experimental data. The architectures selected to predict efficiencies were 3-8-15-1 for the header, 3-9-7-1 for the thresher and separation, 3-5-11-1 for cleaning, and 3-15-10-1 for the total operation. ANN predicted satisfactory results with errors below 1% and a high hit rate, thus being valid to predict the efficiencies in the semi-mechanized bean harvest.

Artificial neural network applied on sintered BaTiO3-ceramic density

It is very important to determine microstructure parameters of consolidated ceramic samples, because it opens new frontiers for further microelectronics miniaturization and integrations. Therefore, controlling, predicting and designing the ceramic materials? properties are the objectives in ceramic materials consolidating process, within the science of sintering. In order to calculate the precise values of desired microstructure parameter at the level of the grains? coating layers based on the measurements on the bulk samples, we applied the artificial neural networks, as a powerful mathematical tool for mapping input-output data. Input signals are propagated forward, as well as the adjustable coefficients that contribute the calculated output signal, denoted as error, which is propagated backwards and replaced by examined parameter. In our previous research, we used neural networks to calculate different electrophysical parameters at the nano level of the grain boundary, like relative capacitance, breakdown voltage or tangent loss, and now we extend the research on sintered material?s density calculation. Errors on the network output were substituted by different consolidated samples density values measured on the bulk, thus enabling the calculation of precise material?s density values between the layers. We performed the neural network theoretical experiments for different number of neurons in hidden layers, according to experimental ceramics material?s density of ?=5.4x103[kg/m3], but it opens the possibility for neural networks application within other density values, as well.

Neural Approximators for Variable-Order Fractional Calculus Operators (VO-FC)

The paper presents research on the approximation of variable-order fractional operators by recurrent neural networks. The research focuses on two basic variable-order fractional operators, i.e., integrator and differentiator. The study includes variations of the order of each fractional operator. The recurrent neural network architecture based on GRU (Gated Recurrent Unit) cells functioned as a neural approximation for selected fractional operators. The paper investigates the impact of the number of neurons in the hidden layer, treated as a hyperparameter, on the quality of modeling error. Training of the established recurrent neural network was performed on synthetic data sets. Data for training was prepared based on the modified Grünwald-Letnikov definition of variable-order fractional operators suitable for convenient numerical computing without memory effects. The research presented in this paper showed that recurrent network architecture based on GRU-type cells can satisfactorily approximate targeted simple yet functional variable-order fractional operators with minor modeling errors. In addition, the research also compares the presented solution with basic and recurrent neural networks that utilize Tapped Delay Lines (TDL) in their structure. The presented solution is a novel approach to the approximation of VO-FC operators. It has the advantage of automatic selection of neural approximator parameters by optimization based on data customized for specific requirements.

Artificial Neural Network for Predicting Silicon Content in the Hot Metal Produced in a Blast Furnace Fueled by Metallurgical Coke

The main production route for cast iron and steel is through the blast furnace. The silicon content in cast iron is an important indicator of the thermal condition of a blast furnace. High silicon contents indicate an increase in the furnace's thermal input and, in some cases, may indicate an excess of coke in the reactor. As coke costs predominate in the production of cast iron, tighter control of the silicon content therefore has economic advantages. The main objective of this article was to design an artificial neural network to predict the silicon content in hot metal, varying the number of neurons in the hidden layer by 10, 20, 25, 30, 40, 50, 75, 100, 125 , 150, 170 and 200 neurons. In general, all neural networks showed excellent results, with the network with 30 neurons showing the best results among the 12 modeled networks. The validation of the models was confirmed using the Mean Square Error (MSE) and Pearson's correlation coefficient. The cross-validation technique was used to re-evaluate the performance of neural networks. In short, neural networks can be used in practical operations due to the excellent correlations between the real values ​​and those calculated by the neural network.

Distribution Feeder Parameter Estimation Without Synchronized Phasor Measurement by Using Radial Basis Function Neural Networks and Multi-Run Optimization Method

In practice, the performance of distribution feeder parameter estimation is limited by the measurement conditions in distribution networks. An accurate mathematical model that considers limited phasor measurements in distribution networks is necessary to estimate feeder parameters. This paper presents a set of modified parameter estimation models for unbalanced three-phase distribution feeders that only require the measurements of voltage amplitudes and power flows. To simplify the calculation process and improve the estimated results, a method combined with a radial basis function neural network (RBFNN) and multi-run optimization method (MRO), namely RBFNN-MRO, is proposed to calculate the parameters of distribution feeders. The relationship between the feeder parameters and the measurement data from the two terminals of the feeder can be mapped perfectly using the RBFNN. Furthermore, the random errors in the measurement device were eliminated using the proposed RBFNN-MRO algorithm. The RBFNN-MRO algorithm can limit the number of neurons in the hidden layer and substantially reduce the training time for each RBFNN. The feasibility of the proposed method was verified using four IEEE test systems. The proposed RBFNN-MRO and RBFNN methods were compared using the maximum absolute percentage error (MAPE) curves. The results reveal that the proposed RBFNN-MRO method has excellent potential for improving the accuracy of feeder parameter estimation even without synchronized phasor measurement.