Prediction of Time Series Data Based on Transformer with Soft Dynamic Time Wrapping

Kuo Hao Ho, Pei Shu Huang, I-Chen Wu, Feng-Jian Wang

研究成果: Paper同行評審

2 引文 斯高帕斯(Scopus)

摘要

It is a challenge to predict the long-term future data from time series data. This paper proposes to use a Transformer with soft dynamic time wrapping for early stopping criteria, called a soft-DTW Transformer. Our experiment in an open-source dataset HouseTwenty shows that the average prediction error rate with soft-DTW Transformer is 27.79%, greatly reduced from 45.70% for using SVR, a common time series method.

原文American English
DOIs
出版狀態Published - 28 9月 2020
事件7th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020 - Taoyuan, Taiwan
持續時間: 28 9月 202030 9月 2020

Conference

Conference7th IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2020
國家/地區Taiwan
城市Taoyuan
期間28/09/2030/09/20

指紋

深入研究「Prediction of Time Series Data Based on Transformer with Soft Dynamic Time Wrapping」主題。共同形成了獨特的指紋。

引用此