FN Archimer Export Format
PT C
TI DTW-Approach for uncorrelated multivariate time series imputation
BT 
AF PHAN, THI-THU-HONG
   POISSON CAILLAULT, Emilie
   BIGAND, Andre
   LEFEBVRE, Alain
AS 1:1,2;2:1;3:1;4:3;
FF 1:;2:;3:;4:PDG-ODE-LITTORAL-LERBL;
C1 Univ Littoral Cote dOpale, EA LISIC 4491, F-62228 Calais, France.
   Vietnam Natl Univ Agr, Dept Comp Sci Hanoi, Hanoi, Vietnam.
   IFREMER, LER BL, F-62321 Boulogne Sur Mer, France.
C2 UNIV LITTORAL COTE D'OPALE, FRANCE
   UNIV NATL VIETNAM, VIETNAM
   IFREMER, FRANCE
SI BOULOGNE
SE PDG-ODE-LITTORAL-LERBL
IN WOS Ifremer jusqu'en 2018
   copubli-france
   copubli-univ-france
   copubli-int-hors-europe
   copubli-sud
UR https://archimer.ifremer.fr/doc/00429/54082/55378.pdf
LA English
DT Proceedings paper
DE ;Imputation;Uncorrelated multivariate time series;Missing data;Dynamic Time Warping;Similarity measures
AB 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. 
PY 2017
CT Proceedings of the 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP). 2017. 6 p.
DI 10.1109/MLSP.2017.8168165
ID 54082
ER

EF