Training artificial neural networks for time series prediction using asymmetric cost functions

2002 ◽  
Author(s):  
S.F. Crone
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Time Series Prediction ◽  
Cost Functions ◽  
Asymmetric Cost ◽  
Artificial Neural

Artificial Neural Networks for Time Series Prediction

2016 ◽  
pp. 117-150
Author(s):  
Esteban Tlelo-Cuautle ◽  
José de Jesús Rangel-Magdaleno ◽  
Luis Gerardo De la Fraga
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Time Series Prediction ◽  
Artificial Neural

Heterogeneous Space-Time Artificial Neural Networks for Space-Time Series Prediction

2017 ◽  
Vol 22 (1) ◽  
pp. 183-201 ◽  
Author(s):  
Min Deng ◽  
Wentao Yang ◽  
Qiliang Liu ◽  
Rui Jin ◽  
Feng Xu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Time Series Prediction ◽  
Space Time ◽  
Artificial Neural

Applications of Artificial Neural Networks to Time Series Prediction

2018 ◽  
pp. 9-1-9-18
Author(s):  
Yuansong Liao ◽  
John Moody ◽  
Lizhong Wu
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Time Series Prediction ◽  
Artificial Neural

scholarly journals Prediction of hierarchical time series using structured regularization and its application to artificial neural networks

PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0242099
Author(s):  
Tomokaze Shiratori ◽  
Ken Kobayashi ◽  
Yuichi Takano
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Prediction Model ◽  
Time Series Prediction ◽  
Structured Regularization ◽  
Coherent Forecasts ◽  
Artificial Neural ◽  
Real World Datasets ◽  
Upper Level

This paper discusses the prediction of hierarchical time series, where each upper-level time series is calculated by summing appropriate lower-level time series. Forecasts for such hierarchical time series should be coherent, meaning that the forecast for an upper-level time series equals the sum of forecasts for corresponding lower-level time series. Previous methods for making coherent forecasts consist of two phases: first computing base (incoherent) forecasts and then reconciling those forecasts based on their inherent hierarchical structure. To improve time series predictions, we propose a structured regularization method for completing both phases simultaneously. The proposed method is based on a prediction model for bottom-level time series and uses a structured regularization term to incorporate upper-level forecasts into the prediction model. We also develop a backpropagation algorithm specialized for applying our method to artificial neural networks for time series prediction. Experimental results using synthetic and real-world datasets demonstrate that our method is comparable in terms of prediction accuracy and computational efficiency to other methods for time series prediction.

scholarly journals Time Series Prediction with Artificial Neural Networks: An Analysis Using Brazilian Soybean Production

Agriculture ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 475
Author(s):  
Emerson Rodolfo Abraham ◽  
João Gilberto Mendes dos Reis ◽  
Oduvaldo Vendrametto ◽  
Pedro Luiz de Oliveira Costa Neto ◽  
Rodrigo Carlo Toloi ◽  
...  
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Artificial Neural Networks ◽  
Time Series Prediction ◽  
Economic Value ◽  
Human Consumption ◽  
Production Volume ◽  
Soybean Production ◽  
Production Area ◽  
Artificial Neural

Food production to meet human demand has been a challenge to society. Nowadays, one of the main sources of feeding is soybean. Considering agriculture food crops, soybean is sixth by production volume and the fourth by both production area and economic value. The grain can be used directly to human consumption, but it is highly used as a source of protein for animal production that corresponds 75% of the total, or as oil and derived food products. Brazil and the US are the most important players responsible for more than 70% of world production. Therefore, a reliable forecasting is essential for decision-makers to plan adequate policies to this important commodity and to establish the necessary logistical resources. In this sense, this study aims to predict soybean harvest area, yield, and production using Artificial Neural Networks (ANN) and compare with classical methods of Time Series Analysis. To this end, we collected data from a time series (1961–2016) regarding soybean production in Brazil. The results reveal that ANN is the best approach to predict soybean harvest area and production while classical linear function remains more effective to predict soybean yield. Moreover, ANN presents as a reliable model to predict time series and can help the stakeholders to anticipate the world soybean offer.

Sign in / Sign up

Export Citation Format

Share Document