arxivst stuff from arxiv that you should probably bookmark

Time Series Cluster Kernel for Learning Similarities between Multivariate Time Series with Missing Data

Abstract · Apr 3, 2017 20:16 ·

stat-ml cs-lg

Arxiv Abstract

  • Karl Øyvind Mikalsen
  • Filippo Maria Bianchi
  • Cristina Soguero-Ruiz
  • Robert Jenssen

Similarity-based approaches represent a promising direction for time series analysis. However, many such methods rely on parameter tuning and have shortcomings if the time series are multivariate (MTS) and contain missing data. In this paper, we address these challenges within the powerful context of kernel methods by proposing the robust \emph{time series cluster kernel} (TCK). The approach taken is to leverage 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.

Read the paper (pdf) »