scholarly journals Application of neural networks to the analysis of consumer opinions

2019 ◽  
Vol 13 ◽  
pp. 310-314
Author(s):  
Roman Mysan ◽  
Ivan Loichuk ◽  
Małgorzata Plechawska-Wójcik
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Optimization ◽  
Optimization Methods ◽  
User Feedback ◽  
Text Data ◽  
Neural Network Optimization ◽  
The Neural Network ◽  
Test Application

This paper presents an analysis of the possibilities of using neural networks to classify text data in the form of comments. Moreover, results of research of two neural network optimization methods: Adam and Gradient are presented. The aim of the work is to conduct research on the behavior of the neural network depending on the change of parameters and the amount of data used to teach the neural network. To achieve the goal, a test application was created. It uses a neural network to display the overall assessment of the accommodation facility based on the added user feedback.

OF PREDICTING THE RISK OF DEVELOPMENT OF MYOPIA IN YOUNG PEOPLE ON THE BASIS OF THE USE OF RADIAL NEURAL NETWORKS

2020 ◽  
pp. 92-97
Author(s):  
Игорь Эдуардович Есауленко ◽  
Юлия Владимировна Татаркова ◽  
Татьяна Николаевна Петрова ◽  
Олег Валериевич Судаков ◽  
Александр Юрьевич Гончаров
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Young People ◽  
Automated System ◽  
Neural Network Optimization ◽  
The Neural Network ◽  
Medical Institutions ◽  
Network Technologies ◽  
Medical University ◽  
Method Of Correlation

В статье рассматривается один из подходов к анализу и управлению рисками развития патологии глаз и его придаточного аппарата у лиц молодого возраста, основанный на нейросетевых технологиях. В работе приводится одна из возможных классификаций рисков, а также выделены области прогнозирования рисков, в которых применение нейронных сетей представляется наиболее эффективным. Выделены преимущества и недостатки нейронных сетей для задач прогнозирования и классификации характера течения миопии. Показывается преимущество их применения для приведения категориальных признаков к представлению, с которыми эффективно способна работать нейронная сеть. На основе сравнительного анализа выбраны функции активации для каждой группы риска миопии и алгоритм оптимизации нейронной сети. Подробно описаны метод для отбора признаков на основе работы построенной модели и основанный на поведении модели метод корреляционного анализа, который позволит решить характерную для нейронных сетей проблему неопределенности. Анализ оценки вероятности совершения ошибок первого и второго рода позволил сделать вывод о высокой обобщающей способности предлагаемого подхода. На основе оптимизированной нейронной сети была разработана автоматизированная система прогнозирования риска развития миопии в молодежной среде. Установлено, что предложенный авторами подход к оценке риска миопии у студентов медицинского вуза показал высокую прогностическую способность и может служить основой для создания информационной системы экспресс-диагностики патологии глаз и его придаточного аппарата у лиц молодого возраста. Внедрение разработанной системы позволит медицинским учреждениям повысить оперативность и точность предварительной диагностики пациентов The article discusses one of the approaches to the analysis and risk management of eye pathology and the adnexa in young people, based on neural network technologies. The paper presents one of the possible classifications of risks, and also identifies areas of risk prediction in which the use of neural networks seems to be most effective. The advantages of the disadvantages of neural networks for predicting and classifying the nature of the course of myopia are highlighted. The advantage of their use is shown to bring categorical features to a representation with which a neural network is effectively able to work. Based on a comparative analysis, the activation functions for each myopia risk group and the neural network optimization algorithm were selected. The method for selecting features based on the work of the constructed model and the method of correlation analysis based on the model’s behavior, which will solve the problem of uncertainty characteristic of neural networks, are described in detail. An analysis of the assessment of the probability of making mistakes of the first and second kind made it possible to conclude that the proposed approach is highly generalizing. Based on the optimized neural network, an automated system for predicting the risk of myopia in the youth environment was developed. It was established that the approach proposed by the authors to assess the risk of myopia in students of a medical university has shown high prognostic ability and can serve as the basis for creating an information system for the rapid diagnosis of eye pathology and its adnexa in young people. Implementation of the developed system will allow medical institutions to increase the efficiency and accuracy of preliminary diagnosis of patients

Swarm-Based Nature-Inspired Metaheuristics for Neural Network Optimization

2018 ◽  
pp. 23-53
Author(s):  
Swathi Jamjala Narayanan ◽  
Boominathan Perumal ◽  
Jayant G. Rohra
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Optimization ◽  
Network Architectures ◽  
Neural Network Optimization ◽  
Local Optima ◽  
Gradient Based ◽  
Neural Network Architectures ◽  
Nature Inspired Algorithms ◽  
Nature Inspired Metaheuristics

Nature-inspired algorithms have been productively applied to train neural network architectures. There exist other mechanisms like gradient descent, second order methods, Levenberg-Marquardt methods etc. to optimize the parameters of neural networks. Compared to gradient-based methods, nature-inspired algorithms are found to be less sensitive towards the initial weights set and also it is less likely to become trapped in local optima. Despite these benefits, some nature-inspired algorithms also suffer from stagnation when applied to neural networks. The other challenge when applying nature inspired techniques for neural networks would be in handling large dimensional and correlated weight space. Hence, there arises a need for scalable nature inspired algorithms for high dimensional neural network optimization. In this chapter, the characteristics of nature inspired techniques towards optimizing neural network architectures along with its applicability, advantages and limitations/challenges are studied.

Implementasi Algoritma Genetika dan Neural Network Pada Aplikasi Peramalan Produksi Mie

2017 ◽  
Vol 9 (1) ◽  
pp. 37-41
Author(s):  
Adhi Kusnadi ◽  
Jansen Pratama
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Network Optimization ◽  
Test Results ◽  
Accuracy Rate ◽  
Neural Network Optimization ◽  
Production Forecasting ◽  
The Neural Network ◽  
Crossover Probability ◽  
Hidden Layer

Companies that produce products must be able to regulate the amount of production so that it have plan production. Therefore, it is necessary to be able to predict the amount of production. This research aims to create an application that is useful in determining the amount of production. These applications using genetic algorithms and neural network. Genetic algorithm is used to optimize the weights in the neural network. From the test results, this application uses network with 12 inputs, 5 neuron in first hidden layer, 3 neurons in the second hidden layer, and 3 neurons in the last hidden layer. Then for the genetic algorithm parameters used were 10 individuals, 50 generations, crossover probability 0.8 and mutations probability 0.1. Based on the test results, this application has the forecasting’s accuracy rate reaches 86%. Keyword : forecasting, production forecasting, genetic algorithm neural network, optimization.

SCORING MODELING BASED ON NEURAL NETWORKS FOR DETERMINING A BANK BORROWER'S RATING

2020 ◽  
Vol 2020 (10) ◽  
pp. 54-62
Author(s):  
Oleksii VASYLIEV ◽  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Architecture ◽  
Statistical Data ◽  
Activation Function ◽  
Decision Making Process ◽  
Neural Network Architecture ◽  
Acceptable Accuracy ◽  
The Neural Network ◽  
Sigmoid Activation Function

The problem of applying neural networks to calculate ratings used in banking in the decision-making process on granting or not granting loans to borrowers is considered. The task is to determine the rating function of the borrower based on a set of statistical data on the effectiveness of loans provided by the bank. When constructing a regression model to calculate the rating function, it is necessary to know its general form. If so, the task is to calculate the parameters that are included in the expression for the rating function. In contrast to this approach, in the case of using neural networks, there is no need to specify the general form for the rating function. Instead, certain neural network architecture is chosen and parameters are calculated for it on the basis of statistical data. Importantly, the same neural network architecture can be used to process different sets of statistical data. The disadvantages of using neural networks include the need to calculate a large number of parameters. There is also no universal algorithm that would determine the optimal neural network architecture. As an example of the use of neural networks to determine the borrower's rating, a model system is considered, in which the borrower's rating is determined by a known non-analytical rating function. A neural network with two inner layers, which contain, respectively, three and two neurons and have a sigmoid activation function, is used for modeling. It is shown that the use of the neural network allows restoring the borrower's rating function with quite acceptable accuracy.

scholarly journals Discretization and machine learning approximation of BSDEs with a constraint on the Gains-process

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Idris Kharroubi ◽  
Thomas Lim ◽  
Xavier Warin
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Differential Equations ◽  
Numerical Experiments ◽  
Optimization Problem ◽  
Learning Approach ◽  
The Neural Network ◽  
Machine Learning Approach ◽  
Mesh Grid

AbstractWe study the approximation of backward stochastic differential equations (BSDEs for short) with a constraint on the gains process. We first discretize the constraint by applying a so-called facelift operator at times of a grid. We show that this discretely constrained BSDE converges to the continuously constrained one as the mesh grid converges to zero. We then focus on the approximation of the discretely constrained BSDE. For that we adopt a machine learning approach. We show that the facelift can be approximated by an optimization problem over a class of neural networks under constraints on the neural network and its derivative. We then derive an algorithm converging to the discretely constrained BSDE as the number of neurons goes to infinity. We end by numerical experiments.

Application of neural networks in predictions of brake wear particulate matter emission

2021 ◽  
pp. 095440702110363
Author(s):  
Saša Vasiljević ◽  
Jasna Glišović ◽  
Nadica Stojanović ◽  
Ivan Grujić
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Particulate Matter ◽  
Traffic Control ◽  
World Health ◽  
Vehicle Speed ◽  
System Pressure ◽  
The Neural Network ◽  
Vehicle Systems ◽  
Brake Wear

According to the World Health Organization, air pollution with PM10 and PM2.5 (PM-particulate matter) is a significant problem that can have serious consequences for human health. Vehicles, as one of the main sources of PM10 and PM2.5 emissions, pollute the air and the environment both by creating particles by burning fuel in the engine, and by wearing of various elements in some vehicle systems. In this paper, the authors conducted the prediction of the formation of PM10 and PM2.5 particles generated by the wear of the braking system using a neural network (Artificial Neural Networks (ANN)). In this case, the neural network model was created based on the generated particles that were measured experimentally, while the validity of the created neural network was checked by means of a comparative analysis of the experimentally measured amount of particles and the prediction results. The experimental results were obtained by testing on an inertial braking dynamometer, where braking was performed in several modes, that is under different braking parameters (simulated vehicle speed, brake system pressure, temperature, braking time, braking torque). During braking, the concentration of PM10 and PM2.5 particles was measured simultaneously. The total of 196 measurements were performed and these data were used for training, validation, and verification of the neural network. When it comes to simulation, a comparison of two types of neural networks was performed with one output and with two outputs. For each type, network training was conducted using three different algorithms of backpropagation methods. For each neural network, a comparison of the obtained experimental and simulation results was performed. More accurate prediction results were obtained by the single-output neural network for both particulate sizes, while the smallest error was found in the case of a trained neural network using the Levenberg-Marquardt backward propagation algorithm. The aim of creating such a prediction model is to prove that by using neural networks it is possible to predict the emission of particles generated by brake wear, which can be further used for modern traffic systems such as traffic control. In addition, this wear algorithm could be applied on other vehicle systems, such as a clutch or tires.

scholarly journals A Neural Network Decomposition Algorithm for Mapping on Crossbar-Based Computing Systems

Electronics ◽  
2020 ◽  
Vol 9 (9) ◽  
pp. 1526 ◽  
Author(s):  
Choongmin Kim ◽  
Jacob A. Abraham ◽  
Woochul Kang ◽  
Jaeyong Chung
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Predictive Performance ◽  
Fixed Number ◽  
Decomposition Algorithm ◽  
Computing Systems ◽  
Network Decomposition ◽  
Von Neumann ◽  
Analog Computing ◽  
The Neural Network

Crossbar-based neuromorphic computing to accelerate neural networks is a popular alternative to conventional von Neumann computing systems. It is also referred as processing-in-memory and in-situ analog computing. The crossbars have a fixed number of synapses per neuron and it is necessary to decompose neurons to map networks onto the crossbars. This paper proposes the k-spare decomposition algorithm that can trade off the predictive performance against the neuron usage during the mapping. The proposed algorithm performs a two-level hierarchical decomposition. In the first global decomposition, it decomposes the neural network such that each crossbar has k spare neurons. These neurons are used to improve the accuracy of the partially mapped network in the subsequent local decomposition. Our experimental results using modern convolutional neural networks show that the proposed method can improve the accuracy substantially within about 10% extra neurons.

Greedy based convolutional neural network optimization for detecting apnea

2020 ◽  
Vol 197 ◽  
pp. 105640 ◽  
Author(s):  
Sheikh Shanawaz Mostafa ◽  
Darío Baptista ◽  
Antonio G. Ravelo-García ◽  
Gabriel Juliá-Serdá ◽  
Fernando Morgado-Dias
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Network Optimization ◽  
Neural Network Optimization

Classification of Alloys with an Artificial Neural Network and Multivariate Calibration of Glow-Discharge Emission Spectra

1991 ◽  
Vol 45 (10) ◽  
pp. 1706-1716 ◽  
Author(s):  
Mark Glick ◽  
Gary M. Hieftje
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Glow Discharge ◽  
Multivariate Calibration ◽  
Emission Spectra ◽  
K Nearest Neighbor ◽  
The Neural Network ◽  
Calibration Sets ◽  
Artificial Neural

Artificial neural networks were constructed for the classification of metal alloys based on their elemental constituents. Glow discharge-atomic emission spectra obtained with a photodiode array spectrometer were used in multivariate calibrations for 7 elements in 37 Ni-based alloys (different types) and 15 Fe-based alloys. Subsets of the two major classes formed calibration sets for stepwise multiple linear regression. The remaining samples were used to validate the calibration models. Reference data from the calibration sets were then pooled into a single set to train neural networks with different architectures and different training parameters. After the neural networks learned to discriminate correctly among alloy classes in the training set, their ability to classify samples in the testing set was measured. In general, the neural network approach performed slightly better than the K-nearest neighbor method, but it suffered from a hidden classification mechanism and nonunique solutions. The neural network methodology is discussed and compared with conventional sample-classification techniques, and multivariate calibration of glow discharge spectra is compared with conventional univariate calibration.

Sign in / Sign up

Export Citation Format

Share Document