A Comparison of Multivariate Time Series Clustering Methods

• Iago Vázquez ^[1] ; José Ramón Villar ^[2] ; Javier Sedano ^[1] ; Svetlana Simić ^[3]
  1. [1] Instituto Tecnológico de Castilla y León

     Instituto Tecnológico de Castilla y León

     Burgos, España

     
  2. [2] Universidad de Oviedo

     Universidad de Oviedo

     Oviedo, España

     
  3. [3] University of Novi Sad

     University of Novi Sad

     RS.VO.6.3194359, Serbia

     

  Mostrar afiliaciones +
• Localización: 15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020): Burgos, Spain ; September 2020 / coord. por Álvaro Herrero Cosío , Carlos Cambra Baseca , Daniel Urda Muñoz , Javier Sedano Franco , Héctor Quintián Pardo , Emilio Santiago Corchado Rodríguez , 2021, ISBN 978-3-030-57802-2, págs. 571-579
• Idioma: inglés
• Texto completo no disponible (Saber más ...)
• Resumen

  • Big Data and the IoT explosion has made clustering Multivariate Time Series (MTS) one of the most effervescent research fields. From Bio-informatics to Business and Management, MTS are becoming more and more interesting as they allow to match events the co-occur in time but that is hardly noticeable. In this paper, we compare four clustering methods retrieved from the literature analyzing their performance on five publicly available data sets. These methods make use of different TS representation and distance measurement functions. Results show that Dynamic Time Warping is still competitive; APCA+DTW and Compression-based dissimilarity obtained the best results on the different data sets.