Open AccessTime Series Data Prediction Based on Sequence to Sequence Model
Author(s) -
Chao Yang,
Zhongwen Guo,
Lintao Xian
Publication year - 2019
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/692/1/012047
Subject(s) - sequence (biology) , series (stratigraphy) , computer science , generalization , process (computing) , time sequence , time series , algorithm , data mining , test data , machine learning , mathematics , paleontology , genetics , biology , mathematical analysis , programming language , operating system
Home appliance test is an essential part of the R&D process. However, since home appliance test must be carried out under certain circumstances, it makes the development cycle longer. If it is possible to predicting the home appliance test data, it will improve the efficiency of home appliance development. Sequence to sequence model has been proved that it has a strong ability to map the input sequence and output sequence and it has been widely used in machine translation tasks. In order to solve the home appliance test data prediction problem, we firstly tried to apply sequence to sequence model to predict numerically continuous time series data. Our experiments proved that our model can predict the data of relatively long-time steps when inputting data of relatively short time steps. In our experiment, the mean absolute percentage error of the prediction of our model is about 0.1%. Our approach has a strong generalization ability and performs well in different experimental scenarios. Finally, we believe that the sequence to sequence method performs satisfactorily on prediction problems for continuous time series data. With this model, we can obtain more accurate results than traditional methods and it is meaningful for the R&D of home appliances.