Clustering structure analysis in time-series data with density-based clusterability measure
| Autor: | Tomi Raty, Juho Jokinen, Timo Lintonen |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Structure analysis
Computer science 02 engineering and technology computer.software_genre Synthetic data sets Density based Artificial Intelligence Control and Systems Engineering 020204 information systems Assessment methods 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Data mining Time series Cluster analysis computer Information Systems Intuition |
| Zdroj: | Jokinen, J, Raty, T & Lintonen, T 2019, ' Clustering structure analysis in time-series data with density-based clusterability measure ', IEEE/CAA Journal of Automatica Sinica, vol. 6, no. 6, 8894746, pp. 1332-1343 . https://doi.org/10.1109/JAS.2019.1911744 |
| ISSN: | 2329-9274 2329-9266 |
| DOI: | 10.1109/jas.2019.1911744 |
| Popis: | Clustering is used to gain an intuition of the structures in the data. Most of the current clustering algorithms produce a clustering structure even on data that do not possess such structure. In these cases, the algorithms force a structure in the data instead of discovering one. To avoid false structures in the relations of data, a novel clusterability assessment method called density-based clusterability measure is proposed in this paper. It measures the prominence of clustering structure in the data to evaluate whether a cluster analysis could produce a meaningful insight to the relationships in the data. This is especially useful in time-series data since visualizing the structure in time-series data is hard. The performance of the clusterability measure is evaluated against several synthetic data sets and time-series data sets, which illustrate that the density-based clusterability measure can successfully indicate clustering structure of time-series data. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|