DTW-APPROACH FOR UNCORRELATED MULTIVARIATE TIME SERIES IMPUTATION

Thi-Thu-Hong Phan (1) , Alain Lefebvre (2) , Émilie Poisson Caillault (1) , André Bigand (1)

1 LISIC - Laboratoire d'Informatique Signal et Image de la Côte d'Opale
2 IFREMER - Institut Français de Recherche pour l'Exploitation de la Mer

Missing data are inevitable in almost domains of applied sciences. Data analysis with missing values can lead to a loss of efficiency and unreliable results, especially for large missing sub-sequence(s). Some well-known methods for multivariate time series imputation require high correlations between series or their features. In this paper , we propose an approach based on the shape-behaviour relation in low/un-correlated multivariate time series under an assumption of recurrent data. This method involves two main steps. Firstly, we find the most similar sub-sequence to the sub-sequence before (resp. after) a gap based on the shape-features extraction and Dynamic Time Warping algorithms. Secondly, we fill in the gap by the next (resp. previous) sub-sequence of the most similar one on the signal containing missing values. Experimental results show that our approach performs better than several related methods in case of multivariate time series having low/non-correlations and effective information on each signal.

Mots clés: Imputation; Uncorrelated multivariate time series; Missing data; Dynamic Time Warping; Similarity measures

Domaines: Machine Learning [stat.ML]

Thi-Thu-Hong Phan, Alain Lefebvre, Émilie Poisson Caillault, André Bigand. DTW-APPROACH FOR UNCORRELATED MULTIVARIATE TIME SERIES IMPUTATION. IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP 2017), Sep 2017, Tokyo, Japan. pp.1-6, ⟨10.1109/MLSP.2017.8168165⟩. ⟨hal-01609267⟩