Abrupt transitions in time series with uncertainties
Most time series techniques tend to ignore data uncertainties, which results in inaccurate conclusions. Here, Goswami et al. represent time series as a sequence of probability density functions, and reliably detect abrupt transitions by identifying communities in probabilistic recurrence networks.
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Publishing Group
2018-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-017-02456-6 |