CALIMERA: A new early time series classification method

被引:6
作者
Bilski, Jakub Michal [1 ]
Jastrzebska, Agnieszka [1 ]
机构
[1] Warsaw Univ Technol, Fac Math & Informat Sci, Ul Koszykowa 75, PL-00662 Warsaw, Poland
关键词
Early time series classification; Calibration; Decision-making; Cost function; CONFIDENCE;
D O I
10.1016/j.ipm.2023.103465
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Early time series classification is a variant of the time series classification task, in which a label must be assigned to the incoming time series as quickly as possible without necessarily screening through the whole sequence. It needs to be realized on the algorithmic level by fusing a decision-making method that detects the right moment to stop and a classifier that assigns a class label. The contribution addressed in this paper is twofold. Firstly, we present a new method for finding the best moment to perform an action (terminate/continue). Secondly, we propose a new learning scheme using classifier calibration to estimate classification accuracy. The new approach, called CALIMERA, is formalized as a cost minimization problem. Using two benchmark methodologies for early time series classification, we have shown that the proposed model achieves better results than the current state-of-the-art. Two most serious competitors of CALIMERA are ECONOMY and TEASER. The empirical comparison showed that the new method achieved a higher accuracy than TEASER for 35 out of 45 datasets and it outperformed ECONOMY in 20 out of 34 datasets.
引用
收藏
页数:15
相关论文
共 41 条
[1]   Early and Revocable Time Series Classification [J].
Achenchabe, Youssef ;
Bondu, Alexis ;
Cornuejols, Antoine ;
Lemaire, Vincent .
2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
[2]  
Achenchabe Y, 2021, Arxiv, DOI arXiv:2104.13257
[3]   Early classification of time series Cost-based optimization criterion and algorithms [J].
Achenchabe, Youssef ;
Bondu, Alexis ;
Cornuejols, Antoine ;
Dachraoui, Asma .
MACHINE LEARNING, 2021, 110 (06) :1481-1504
[4]   TSFEL: Time Series Feature Extraction Library [J].
Barandas, Marilia ;
Folgado, Duarte ;
Fernandes, Leticia ;
Santos, Sara ;
Abreu, Mariana ;
Bota, Patricia ;
Liu, Hui ;
Schultz, Tanja ;
Gamboa, Hugo .
SOFTWAREX, 2020, 11
[5]   On the appropriateness of Platt scaling in classifier calibration [J].
Boeken, Bjorn .
INFORMATION SYSTEMS, 2021, 95
[6]   Early Classification of Time Series as a Non Myopic Sequential Decision Making Problem [J].
Dachraoui, Asma ;
Bondu, Alexis ;
Cornuejols, Antoine .
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2015, PT I, 2015, 9284 :433-447
[7]   MINIROCKET A Very Fast (Almost) Deterministic Transform for Time Series Classification [J].
Dempster, Angus ;
Schmidt, Daniel F. ;
Webb, Geoffrey, I .
KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, :248-257
[8]  
Fauvel K, 2020, AAAI CONF ARTIF INTE, V34, P403
[9]  
Gebel M., 2009, THESIS TU DORTMUND, DOI [10.17877/DE290R-863, DOI 10.17877/DE290R-863]
[10]  
Gu Z.-W., 2021, MEASUREMENT CONTROL, V54, P346, DOI [10.1177/0020294021997494, DOI 10.1177/0020294021997494]