Adaptive Segmentation of Multivariate Time Series with FastICA and G-G Clustering

被引：0

作者：

Wang L. ^{[1
,2
]}

Li Z.-Z. ^{[1
,2
]}

机构：

[1] School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing

[2] Key Laboratory of Knowledge Automation of Industrial Processes of Ministry of Education, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing

来源：

Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2023年 / 51卷 / 05期

基金：

中国国家自然科学基金;

关键词：

adaptive segmentation; fast independent component analysis; Gath-Geva clustering; minimum description length; multivariate time series;

D O I：

10.12263/DZXB.20220649

中图分类号：

学科分类号：

摘要：

The existing segmentation methods detect the statistical or shape changes of multivariate time series, and perform crisp segmentation on the location of change points. However, these methods fail to estimate the length of the transition interval between two segments, cannot accurately segment multivariate time series with high dimension, strong noise, and need to set parameters in advance. To address such matters, an adaptive multivariate time series segmentation method based on FastICA (Fast Independent Component Analysis) and G-G (Gath-Geva) clustering is proposed. In this method, the key features of multivariate time series are extracted via FastICA, and DW (Durbin-Watson) criterion is used to automatically select main components with high signal-to-noise ratio. According to the minimum description length (MDL), an adaptive multivariate time series segmentation model based on G-G clustering is designed, which is able to perform soft segmentation of multivariate time series. The experimental analysis is carried out on real datasets in many different fields. Compared with state-of-art benchmarks, the average F1 and MAE (Mean Absolute Error) of the proposed method on the above-mentioned datasets improve 8.4%~16.8% and 3.06%~6.56%, respectively. © 2023 Chinese Institute of Electronics. All rights reserved.

引用

页码：1235 / 1244

页数：9

共 29 条

[1] MAYA S, YAMAGUCHI A, NISHINO K, Et al., Lag-aware multivariate time-series segmentation, Proceedings of the 2020 SIAM International Conference on Data Mining, pp. 622-630, (2020)
[2] XU J, ZHOU J, TAN P N, Et al., Spatio-temporal multi-task learning via tensor decomposition, IEEE Transactions on Knowledge and Data Engineering, 33, 6, pp. 2764-2775, (2019)
[3] CHE Z, PURUSHOTHAM S, CHO K, Et al., Recurrent neural networks for multivariate time series with missing values, Scientific Reports, 8, 1, pp. 1-12, (2018)
[4] KEOGH E, CHU S, HRT D, Et al., An online algorithm for segmenting time series, Proceedings 2001 IEEE International Conference on Data Mining, pp. 289-296, (2001)
[5] CHUNG F L, FU T C, NG V, Et al., An evolutionary approach to pattern-based time series segmentation, IEEE Transactions on Evolutionary Computation, 8, 5, pp. 471-489, (2004)
[6] LIU S, YAMADA M, COLLIER N, Et al., Change-point detection in time-series data by relative density-ratio estimation, Neural Networks, 43, pp. 72-83, (2013)
[7] WANG P, WANG H, WANG W., Finding semantics in time series, Proceedings of the 2011 ACM SIGMOD International Conference on Management of Data, pp. 385-396, (2011)
[8] LI L, MCCANN J, POLLARD N S, Et al., Dynammo: mining and summarization of coevolving sequences with missing values, Proceedings of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 507-516, (2009)
[9] HALLAC D, NYSTRUP P, BOYD S., Greedy gaussian segmentation of multivariate time series, Advances in Data Analysis and Classification, 13, 3, pp. 727-751, (2018)
[10] MATSUBARA Y, SAKURAI Y, FALOUTSOS C., Auto-plait: automatic mining of co-evolving time sequences, Proceedings of the 2014 ACM SIGMOD International Conference on Management of Data, pp. 193-204, (2014)

← 1 2 3 →