Abstract
Incomplete data, i.e., data with missing and/or unknown values, is an ubiquitous problem in a broad range of applications within fields such as signal processing, machine learning, and scientific computing. Matrix completion is an imputation strategy where the unknown values are filled in by a low-rank matrix model that is computed from the available data only. We apply a matrix-completion based strategy for imputation in recurrence plots constructed from incomplete time series.
| Original language | English |
|---|---|
| Publication status | Published - 28 Mar 2024 |
| Event | 43rd Benelux Meeting on Systems and Control - Floreal, Blankenberge, Belgium Duration: 26 Mar 2024 → 28 Mar 2024 https://www.beneluxmeeting.nl/2024/ |
Conference
| Conference | 43rd Benelux Meeting on Systems and Control |
|---|---|
| Abbreviated title | BMSC |
| Country/Territory | Belgium |
| City | Blankenberge |
| Period | 26/03/24 → 28/03/24 |
| Internet address |
Keywords
- recurrence plots
- matrix completion
- time series analysis