TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data

Sun, Chenxi; Hong, Shenda; Song, Moxian; Chou, Yen-Hsiu; Sun, Yongyue; Cai, Derun; Li, Hongyan

doi:10.24963/ijcai.2021/414

TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data

Chenxi Sun, Shenda Hong, Moxian Song, Yen-Hsiu Chou, Yongyue Sun, Derun Cai, Hongyan Li

Download BibTeX Cite

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. Main Track. Pages 3010-3016.

https://doi.org/10.24963/ijcai.2021/414

Keywords

Machine Learning: Time-series; Data Streams
Machine Learning Applications: Bio/Medicine
Data Mining: Classification

Abstract

Prediction based on Irregularly Sampled Time Series (ISTS) is of wide concern in real-world applications. For more accurate prediction, methods had better grasp more data characteristics. Different from ordinary time series, ISTS is characterized by irregular time intervals of intra-series and different sampling rates of inter-series. However, existing methods have suboptimal predictions due to artificially introducing new dependencies in a time series and biasedly learning relations among time series when modeling these two characteristics. In this work, we propose a novel Time Encoding (TE) mechanism. TE can embed the time information as time vectors in the complex domain. It has the properties of absolute distance and relative distance under different sampling rates, which helps to represent two irregularities. Meanwhile, we create a new model named Time Encoding Echo State Network (TE-ESN). It is the first ESNs-based model that can process ISTS data. Besides, TE-ESN incorporates long short-term memories and series fusion to grasp horizontal and vertical relations. Experiments on one chaos system and three real-world datasets show that TE-ESN performs better than all baselines and has better reservoir property.

Chenxi Sun, Shenda Hong, Moxian Song, Yen-Hsiu Chou, Yongyue Sun, Derun Cai, and Hongyan Li. 2021. TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data. In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. IJCAI, 3010–3016. https://doi.org/10.24963/ijcai.2021/414

@inproceedings{ijcai2021p414,
  title     = {TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data},
  author    = {Sun, Chenxi and Hong, Shenda and Song, Moxian and Chou, Yen-Hsiu and Sun, Yongyue and Cai, Derun and Li, Hongyan},
  booktitle = {Proceedings of the Thirtieth International Joint Conference on
               Artificial Intelligence, {IJCAI-21}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {Prof. Zhi-Hua Zhou},
  pages     = {3010--3016},
  year      = {2021},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2021/414},
  url       = {https://doi.org/10.24963/ijcai.2021/414},
}

TY  - CPAPER
TI  - TE-ESN: Time Encoding Echo State Network for Prediction Based on Irregularly Sampled Time Series Data
AU  - Sun, Chenxi
AU  - Hong, Shenda
AU  - Song, Moxian
AU  - Chou, Yen-Hsiu
AU  - Sun, Yongyue
AU  - Cai, Derun
AU  - Li, Hongyan
T2  - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2021
SP  - 3010
EP  - 3016
DO  - 10.24963/ijcai.2021/414
UR  - https://doi.org/10.24963/ijcai.2021/414
ER  -