DTWBI-package {DTWBI}R Documentation

Imputation of Time Series Based on Dynamic Time Warping


Functions to impute large gaps within time series based on Dynamic Time Warping methods. It contains all required functions to create large missing consecutive values within time series and to fill them, according to the paper Phan et al. (2017), <DOI:10.1016/j.patrec.2017.08.019>. Performance criteria are added to compare similarity between two signals (query and reference).


Index of help topics:

DTWBI-package           Imputation of Time Series Based on Dynamic Time
DTWBI_univariate        DTWBI algorithm for univariate signals
compute.fa2             FA2
compute.fb              Fractional Bias (FB)
compute.fsd             Fraction of Standard Deviation (FSD)
compute.nmae            Normalized Mean Absolute Error (NMAE)
compute.rmse            Root Mean Square Error (RMSE)
compute.sim             Similarity
dataDTWBI               Six univariate signals as example for DTWBI
dist_afbdtw             Adaptive Feature Based Dynamic Time Warping
gapCreation             Gap creation
local.derivative.ddtw   Local derivative estimate to compute DDTW
minCost                 DTW-based methods for univariate signals


Camille Dezecache, T. T. Hong Phan, Emilie Poisson-Caillault

Maintainer: Emilie Poisson-Caillault <emilie.poisson@univ-littoral.fr>


Thi-Thu-Hong Phan, Emilie Poisson-Caillault, Alain Lefebvre, Andre Bigand. Dynamic time warping- based imputation for univariate time series data. Pattern Recognition Letters, Elsevier, 2017, <DOI:10.1016/j.patrec.2017.08.019>. <hal-01609256>


# Load package dataset

# Create a query and a reference signal
query <- dataDTWBI$query
ref <- dataDTWBI$query

# Create a gap within query (10% of signal size)
query <- gapCreation(query, rate = 0.1)
data <- query$output_vector
begin_gap <- query$begin_gap
size_gap <- query$gap_size

# Fill gap using DTWBI algorithm
results_DTWBI <- DTWBI_univariate(data, t_gap = begin_gap, T_gap = size_gap)

# Plot
plot(ref, type = "l")
lines(results_DTWBI$output_vector, col = "red", lty = "dashed")

# Compute the similarity of imputed vector and reference
compute.sim(ref, results_DTWBI$output_vector)

[Package DTWBI version 1.1 Index]