Research on methods of filling missing data for multivariate time series
2017
Multivariate time series (MTS) exist in many applications. Due to all kinds of interference factors, missing data in MTS is inevitable. Aiming at this problem, a filling method based on least squares support vector machine (LSSVM) is proposed. Firstly, for the series containing missing data, similar series are searched, and its results are viewed as the training set. Secondly, to make use of the correlation among the variables in MTS, LSSVM is trained. Thirdly, LSSVM is used to fill missing data. Finally, experiments are conducted to check the validity of the proposed method. The results show it can obtain good filling effect, even when the length of the missing data segment is relative large.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
12
References
1
Citations
NaN
KQI