Neural network time series prediction based on multilayer perceptron

Abstract

Until recently, the statistical approach was the main technique in solving the prediction problem. In the framework of static models, the tasks of forecasting, the identification of hidden periodicity in data, analysis of dependencies, risk assessment in decision making, and others are solved. The general disadvantage of statistical models is the complexity of choosing the type of the model and selecting its parameters. Computing intelligence methods, among which artificial neural networks should be considered at first, can serve as alternative to statistical methods. The ability of the neural network to comprehensively process information follows from their ability to generalize and isolate hidden dependencies between input and output data. Significant advantage of neural networks is that they are capable of learning and generalizing the accumulated knowledge. The article proposes a method of neural networks training in solving the problem of prediction of the time series. Most of the predictive tasks of the time series are characterized by high levels of nonlinearity and non-stationary, noisiness, irregular trends, jumps, abnormal emissions. In these conditions, rigid statistical assumptions about the properties of the time series often limit the possibilities of classical forecasting methods. The alternative methods to statistical methods can be the methods of computational intelligence, which include artificial neural networks. The simulation results confirmed that the proposed method of training the neural network can significantly improve the prediction accuracy of the time series.

Application of Neural Network Technologies In the Dental Caries Forecast

“…To build a neural network, we used a high-level Python programming language with the NumPay extension. The following software products were used during the work: Pandas, TensorFlow, Keras, Scikit-learn, Matplotlib, Jupyter Notebook [15].…”

“…During the work, we created a neural network containing five neurons in the input layer (based on the number of available dental indices), one hidden fully connected layer and an output layer with four neurons. The number of synaptic weights and neurons in the hidden layer was determined according to the Kolmogorov -Arnold -Hecht -Nielsen theorem [15]. A ReLU was selected as the activation function for the input layer, and the softmax logistic function -for activation of the output layer.…”

Forecasting volumes of electricity sales using a multilayer neural network

“…У роботі [9] розглядається задача прогнозування споживання електричної енергії у Львівській області за допомогою штучних нейронних мереж. Наведені переваги нейронних мереж з неітераційним навчанням та комбінований режим їх використання для здійснення прогнозів.…”

Assessment of the level of business readiness for digitalization using marketing and neural network technologies

“…This publication has the opportunity to give a detailed presentation of the results of combining the foundations of marketing and neural network modeling in the subject plane of the study of business readiness for digital transformations of housekeeping and sales. Since the task to be solved should be attributed to the regression analysis tasks, it is, therefore, advisable to use the following types of neural networks, namely, multilayer perceptron and radial basis networks (Rudenko et al, 2019).…”