Data Augmentation with Suboptimal Warping for Time-Series Classification
In this paper, a novel data augmentation method for time-series classification is proposed. In the introduced method, a new time-series is obtained in warped space between suboptimally aligned input examples of different lengths. Specifically, the alignment is carried out constraining the warping pa...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-12-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/20/1/98 |
id |
doaj-fd18350f6ab8459cb8d0b02d0af8e6b9 |
---|---|
record_format |
Article |
spelling |
doaj-fd18350f6ab8459cb8d0b02d0af8e6b92020-11-25T01:49:49ZengMDPI AGSensors1424-82202019-12-012019810.3390/s20010098s20010098Data Augmentation with Suboptimal Warping for Time-Series ClassificationKrzysztof Kamycki0Tomasz Kapuscinski1Mariusz Oszust2Department of Computer and Control Engineering, Rzeszow University of Technology, W. Pola 2, 35-959 Rzeszow, PolandDepartment of Computer and Control Engineering, Rzeszow University of Technology, W. Pola 2, 35-959 Rzeszow, PolandDepartment of Computer and Control Engineering, Rzeszow University of Technology, W. Pola 2, 35-959 Rzeszow, PolandIn this paper, a novel data augmentation method for time-series classification is proposed. In the introduced method, a new time-series is obtained in warped space between suboptimally aligned input examples of different lengths. Specifically, the alignment is carried out constraining the warping path and reducing its flexibility. It is shown that the resultant synthetic time-series can form new class boundaries and enrich the training dataset. In this work, the comparative evaluation of the proposed augmentation method against related techniques on representative multivariate time-series datasets is presented. The performance of methods is examined using the nearest neighbor classifier with the dynamic time warping (NN-DTW), LogDet divergence-based metric learning with triplet constraints (LDMLT), and the recently introduced time-series cluster kernel (NN-TCK). The impact of the augmentation on the classification performance is investigated, taking into account entire datasets and cases with a small number of training examples. The extensive evaluation reveals that the introduced method outperforms related augmentation algorithms in terms of the obtained classification accuracy.https://www.mdpi.com/1424-8220/20/1/98multivariate time-seriesdata augmentationtime-series classificationmachine learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Krzysztof Kamycki Tomasz Kapuscinski Mariusz Oszust |
spellingShingle |
Krzysztof Kamycki Tomasz Kapuscinski Mariusz Oszust Data Augmentation with Suboptimal Warping for Time-Series Classification Sensors multivariate time-series data augmentation time-series classification machine learning |
author_facet |
Krzysztof Kamycki Tomasz Kapuscinski Mariusz Oszust |
author_sort |
Krzysztof Kamycki |
title |
Data Augmentation with Suboptimal Warping for Time-Series Classification |
title_short |
Data Augmentation with Suboptimal Warping for Time-Series Classification |
title_full |
Data Augmentation with Suboptimal Warping for Time-Series Classification |
title_fullStr |
Data Augmentation with Suboptimal Warping for Time-Series Classification |
title_full_unstemmed |
Data Augmentation with Suboptimal Warping for Time-Series Classification |
title_sort |
data augmentation with suboptimal warping for time-series classification |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2019-12-01 |
description |
In this paper, a novel data augmentation method for time-series classification is proposed. In the introduced method, a new time-series is obtained in warped space between suboptimally aligned input examples of different lengths. Specifically, the alignment is carried out constraining the warping path and reducing its flexibility. It is shown that the resultant synthetic time-series can form new class boundaries and enrich the training dataset. In this work, the comparative evaluation of the proposed augmentation method against related techniques on representative multivariate time-series datasets is presented. The performance of methods is examined using the nearest neighbor classifier with the dynamic time warping (NN-DTW), LogDet divergence-based metric learning with triplet constraints (LDMLT), and the recently introduced time-series cluster kernel (NN-TCK). The impact of the augmentation on the classification performance is investigated, taking into account entire datasets and cases with a small number of training examples. The extensive evaluation reveals that the introduced method outperforms related augmentation algorithms in terms of the obtained classification accuracy. |
topic |
multivariate time-series data augmentation time-series classification machine learning |
url |
https://www.mdpi.com/1424-8220/20/1/98 |
work_keys_str_mv |
AT krzysztofkamycki dataaugmentationwithsuboptimalwarpingfortimeseriesclassification AT tomaszkapuscinski dataaugmentationwithsuboptimalwarpingfortimeseriesclassification AT mariuszoszust dataaugmentationwithsuboptimalwarpingfortimeseriesclassification |
_version_ |
1725004649018163200 |