Journal
IEEE ACCESS
Volume 10, Issue -, Pages 100700-100724Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2022.3207765
Keywords
Time series analysis; Artificial intelligence; Machine learning; Data analysis; Time measurement; Time series analysis; Data models; Explainable artificial intelligence; time series classification; interpretable machine learning; temporal data analysis
Categories
Funding
- European Community H 2020 Programme [871042, 834756, 952026, 952215]
- European coordinated research on long-term ICT and ICT-based scientific challenges (CHIST-ERA) [CHIST-ERA-19-XAI-010]
- Italian Ministry of University and Research (MUR)
- Austrian Science Fund (FWF) [5205]
- Engineering and Physical Sciences Research Council (EPSRC) [EP/V055712/1]
- National Science Center (NCN) [2020/02/Y/ST6/00064]
- Estonian Research Council (ETAg) [SLTAT21096]
- Bulgarian National Science Fund (BNSF) [KP-06-AOO2/5]
- Federal Ministry of Education and Research [Bundesministerium fur Bildung und Forschung (BMBF)] [13N16242]
- Stiftung Kessler C CO fur Bildung und Kultur
- Aalen University of Applied Sciences
Ask authors/readers for more resources
This article presents a comprehensive literature review on Explainable AI (XAI) for time series classification, categorizes the research field into different methods, and identifies future research directions.
Time series data is increasingly used in a wide range of fields, and it is often relied on in crucial applications and high-stakes decision-making. For instance, sensors generate time series data to recognize different types of anomalies through automatic decision-making systems. Typically, these systems are realized with machine learning models that achieve top-tier performance on time series classification tasks. Unfortunately, the logic behind their prediction is opaque and hard to understand from a human standpoint. Recently, we observed a consistent increase in the development of explanation methods for time series classification justifying the need to structure and review the field. In this work, we (a) present the first extensive literature review on Explainable AI (XAI) for time series classification, (b) categorize the research field through a taxonomy subdividing the methods into time points-based, subsequences-based and instance-based, and (c) identify open research directions regarding the type of explanations and the evaluation of explanations and interpretability.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available