Evaluating Explanation Methods for Multivariate Time Series Classification

被引:2
|
作者
Serramazza, Davide Italo [1 ]
Nguyen, Thu Trang [1 ]
Le Nguyen, Thach [1 ]
Ifrim, Georgiana [1 ]
机构
[1] Univ Coll Dublin, Sch Comp Sci, Dublin, Ireland
基金
爱尔兰科学基金会;
关键词
Time Series Classification; Explanation; Evaluation;
D O I
10.1007/978-3-031-49896-1_11
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multivariate time series classification is an important computational task arising in applications where data is recorded over time and over multiple channels. For example, a smartwatch can record the acceleration and orientation of a person's motion, and these signals are recorded as multivariate time series. We can classify this data to understand and predict human movement and various properties such as fitness levels. In many applications classification alone is not enough, we often need to classify but also understand what the model learns (e.g., why was a prediction given, based on what information in the data). The main focus of this paper is on analysing and evaluating explanation methods tailored to Multivariate Time Series Classification (MTSC). We focus on saliency-based explanation methods that can point out the most relevant channels and time series points for the classification decision. We analyse two popular and accurate multivariate time series classifiers, ROCKET and dResNet, as well as two popular explanation methods, SHAP and dCAM. We study these methods on 3 synthetic datasets and 2 real-world datasets and provide a quantitative and qualitative analysis of the explanations provided. We find that flattening the multivariate datasets by concatenating the channels works as well as using multivariate classifiers directly and adaptations of SHAP for MTSC work quite well. Additionally, we also find that the popular synthetic datasets we used are not suitable for time series analysis.
引用
收藏
页码:159 / 175
页数:17
相关论文
共 50 条
  • [31] Multivariate time series classification based on fusion features
    Du, Mingsen
    Wei, Yanxuan
    Hu, Yupeng
    Zheng, Xiangwei
    Ji, Cun
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 248
  • [32] Classification of Multivariate Time Series Using Supervised Isomap
    Weng, Xiaoqing
    Qin, Shimin
    2012 THIRD GLOBAL CONGRESS ON INTELLIGENT SYSTEMS (GCIS 2012), 2012, : 136 - 139
  • [33] Using DenseNet for IoT multivariate time series classification
    Azar, Joseph
    Makhoul, Abdallah
    Couturier, Raphael
    2020 IEEE SYMPOSIUM ON COMPUTERS AND COMMUNICATIONS (ISCC), 2020, : 33 - 38
  • [34] Uncertainty-based Multivariate Time Series Classification
    Zhang X.
    Zhang L.
    Jin B.
    Zhang H.-Z.
    Zidonghua Xuebao/Acta Automatica Sinica, 2023, 49 (04): : 790 - 804
  • [35] ClaRe: Classification and Regression Tool for Multivariate Time Series
    Cachucho, Ricardo
    Paraschiakos, Stylianos
    Liu, Kaihua
    van der Burgh, Benjamin
    Knobbe, Arno
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2018, PT III, 2019, 11053 : 682 - 686
  • [36] A Versatile Approach to Classification of Multivariate Time Series Data
    Zagorecki, Adam
    PROCEEDINGS OF THE 2015 FEDERATED CONFERENCE ON COMPUTER SCIENCE AND INFORMATION SYSTEMS, 2015, 5 : 407 - 410
  • [37] Multivariate time series classification with parametric derivative dynamic time warping
    Gorecki, Tomasz
    Luczak, Maciej
    EXPERT SYSTEMS WITH APPLICATIONS, 2015, 42 (05) : 2305 - 2312
  • [38] Evaluation of interpretability methods for multivariate time series forecasting
    Ozan Ozyegen
    Igor Ilic
    Mucahit Cevik
    Applied Intelligence, 2022, 52 : 4727 - 4743
  • [39] Evaluation of interpretability methods for multivariate time series forecasting
    Ozyegen, Ozan
    Ilic, Igor
    Cevik, Mucahit
    APPLIED INTELLIGENCE, 2022, 52 (05) : 4727 - 4743
  • [40] Self-supervised Classification of Clinical Multivariate Time Series using Time Series Dynamics
    Yehuda, Yakir
    Freedman, Daniel
    Radinsky, Kira
    PROCEEDINGS OF THE 29TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2023, 2023, : 5416 - 5427