Abstract
In this paper, we propose a novel model for time series prediction in which difference-attention LSTM model and error-correction LSTM model are respectively employed and combined in a cascade way. While difference-attention LSTM model introduces a difference feature to perform attention in traditional LSTM to focus on the obvious changes in time series. Error-correction LSTM model refines the prediction error of difference-attention LSTM model to further improve the prediction accuracy. Finally, we design a training strategy to jointly train the both models simultaneously. With additional difference features and new principle learning framework, our model can improve the prediction accuracy in time series. Experiments on various time series are conducted to demonstrate the effectiveness of our method.
Highlights
Time series prediction is an important issue in machine learning and data mining communities [1], which is critical for many applications, such as in industry and spacecraft where time series are predicted to indicate the health of the equipment
Traditional time series prediction methods are divided into three categories: statistical methods, machine learning methods and deep learning methods
Observing that there are usually abrupt changes in time series which may lead to low prediction accuracy, we propose a new DAEC-LSTM model for time series prediction to explicitly model the changes in the time series
Summary
Time series prediction is an important issue in machine learning and data mining communities [1], which is critical for many applications, such as in industry and spacecraft where time series are predicted to indicate the health of the equipment. LSTM can learn the long-term dependence of time series and are widely applied in time series prediction [7], such as GRU [8], Dual-Memory LSTM [9], LSTM based on evolutionary attention mechanism [10], Phased LSTM [11] and Auto-Encoder Based LSTM [12]. These methods either simplify the LSTM model to improve the prediction speed, or improve the LSTM from the perspective of multidimensional time series prediction.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
