Time series cluster kernel for learning similarities between multivariate time series with missing data. (April 2018)

• Record Type: Journal Article
• Authors: Mikalsen, Karl Øyvind; Bianchi, Filippo Maria; Soguero-Ruiz, Cristina; Jenssen, Robert
• Is Part Of: Pattern recognition. Volume 76(2018:Apr.)
• Page Start: 569
• Page End: 581
• Publication Date: 2018-04
• Subjects: Multivariate time series -- Similarity measures -- Kernel methods -- Missing data -- Gaussian mixture models -- Ensemble learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2017.11.030
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: The time series cluster kernel (TCK) for multivariate time series (MTS) is proposed. Gaussian mixture model (GMM) ensemble learning for increased parameter robustness. Robustness to missing data is ensured by extending the GMMs using informative priors. We prove that the TCK is a valid kernel. TCK outperforms established methods on missing data problems. Abstract: Similarity-based approaches represent a promising direction for time series analysis. However, many such methods rely on parameter tuning, and some have shortcomings if the time series are multivariate (MTS), due to dependencies between attributes, or the time series contain missing data. In this paper, we address these challenges within the powerful context of kernel methods by proposing the robust time series cluster kernel (TCK). The approach taken leverages the missing data handling properties of Gaussian mixture models (GMM) augmented with informative prior distributions. An ensemble learning approach is exploited to ensure robustness to parameters by combining the clustering results of many GMM to form the final kernel. We evaluate the TCK on synthetic and real data and compare to other state-of-the-art techniques. The experimental results demonstrate that the TCK is robust to parameter choices, provides competitive results for MTS without missing data and outstanding results for missing data.