A Shapelet Transform Classification over Uncertain Time Series
A shapelet is a time-series subsequence that can represent local, phase-independent similarity in shape. Time series classification with subsequences can save computing cost, improve computing speed and improve algorithm accuracy. The shapelet-based approaches for time series classification have an...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
University of Zagreb Faculty of Electrical Engineering and Computing
2019-01-01
|
Series: | Journal of Computing and Information Technology |
Subjects: | |
Online Access: | https://hrcak.srce.hr/file/345602 |
id |
doaj-2823c14c6c874d7084e01e79265188e3 |
---|---|
record_format |
Article |
spelling |
doaj-2823c14c6c874d7084e01e79265188e32020-11-25T02:57:40ZengUniversity of Zagreb Faculty of Electrical Engineering and ComputingJournal of Computing and Information Technology1330-11361846-39082019-01-012731528A Shapelet Transform Classification over Uncertain Time SeriesRuizhe Ma0Liangli Zuo1Li Yan2Georgia State University, USANanjing University of Aeronautics and Astronautics, ChinaNanjing University of Aeronautics and Astronautics, ChinaA shapelet is a time-series subsequence that can represent local, phase-independent similarity in shape. Time series classification with subsequences can save computing cost, improve computing speed and improve algorithm accuracy. The shapelet-based approaches for time series classification have an advantage of interpretability. Concentrating on uncertain time series, this paper tries to apply the shapelet-based method to classify uncertain time series. Due to the high dimensions of time series, the number of the generated candidate shapelets is generally huge. As a result, the calculation amount is large too. To deal with this problem, in this paper, we introduce a piecewise linear representation (PLR) method for uncertain time series based on key points so that the traditional shapelet discovery algorithm can be improved efficiently. We verify our approach with experiments. The experimental results show that the proposed shapelet algorithm can be used for uncertain time series and it can provide classification accuracy well while reducing time cost. https://hrcak.srce.hr/file/345602uncertain time series, classification, shapelet, piecewise linear representation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ruizhe Ma Liangli Zuo Li Yan |
spellingShingle |
Ruizhe Ma Liangli Zuo Li Yan A Shapelet Transform Classification over Uncertain Time Series Journal of Computing and Information Technology uncertain time series, classification, shapelet, piecewise linear representation |
author_facet |
Ruizhe Ma Liangli Zuo Li Yan |
author_sort |
Ruizhe Ma |
title |
A Shapelet Transform Classification over Uncertain Time Series |
title_short |
A Shapelet Transform Classification over Uncertain Time Series |
title_full |
A Shapelet Transform Classification over Uncertain Time Series |
title_fullStr |
A Shapelet Transform Classification over Uncertain Time Series |
title_full_unstemmed |
A Shapelet Transform Classification over Uncertain Time Series |
title_sort |
shapelet transform classification over uncertain time series |
publisher |
University of Zagreb Faculty of Electrical Engineering and Computing |
series |
Journal of Computing and Information Technology |
issn |
1330-1136 1846-3908 |
publishDate |
2019-01-01 |
description |
A shapelet is a time-series subsequence that can represent local, phase-independent similarity in shape. Time series classification with subsequences can save computing cost, improve computing speed and improve algorithm accuracy. The shapelet-based approaches for time series classification have an advantage of interpretability. Concentrating on uncertain time series, this paper tries to apply the shapelet-based method to classify uncertain time series. Due to the high dimensions of time series, the number of the generated candidate shapelets is generally huge. As a result, the calculation amount is large too. To deal with this problem, in this paper, we introduce a piecewise linear representation (PLR) method for uncertain time series based on key points so that the traditional shapelet discovery algorithm can be improved efficiently. We verify our approach with experiments. The experimental results show that the proposed shapelet algorithm can be used for uncertain time series and it can provide classification accuracy well while reducing time cost.
|
topic |
uncertain time series, classification, shapelet, piecewise linear representation |
url |
https://hrcak.srce.hr/file/345602 |
work_keys_str_mv |
AT ruizhema ashapelettransformclassificationoveruncertaintimeseries AT lianglizuo ashapelettransformclassificationoveruncertaintimeseries AT liyan ashapelettransformclassificationoveruncertaintimeseries AT ruizhema shapelettransformclassificationoveruncertaintimeseries AT lianglizuo shapelettransformclassificationoveruncertaintimeseries AT liyan shapelettransformclassificationoveruncertaintimeseries |
_version_ |
1724709889934098432 |