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
  • [21] Boosting for Real-Time Multivariate Time Series Classification
    Wang, Haishuai
    Wu, Jun
    THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 4999 - 5000
  • [22] Multivariate LSTM-FCNs for time series classification
    Karim, Fazle
    Majumdar, Somshubra
    Darabi, Houshang
    Harford, Samuel
    NEURAL NETWORKS, 2019, 116 : 237 - 245
  • [23] Temporal Pattern Mining for Multivariate Time Series Classification
    Dua, Sumeet
    Saini, Sheetal
    Singh, Harpreet
    JOURNAL OF MEDICAL IMAGING AND HEALTH INFORMATICS, 2011, 1 (02) : 164 - 169
  • [24] Multivariate time series classification using kernel matrix
    Sun, Jiancheng
    Niu, Huimin
    Tu, Zongqing
    Wu, Zhinan
    Chen, Si
    ELECTRONICS LETTERS, 2022, 58 (07) : 293 - 295
  • [25] Time Series Classification With Multivariate Convolutional Neural Network
    Liu, Chien-Liang
    Hsaio, Wen-Hoar
    Tu, Yao-Chung
    IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2019, 66 (06) : 4788 - 4797
  • [26] Learning a symbolic representation for multivariate time series classification
    Baydogan, Mustafa Gokce
    Runger, George
    DATA MINING AND KNOWLEDGE DISCOVERY, 2015, 29 (02) : 400 - 422
  • [27] Learning a symbolic representation for multivariate time series classification
    Mustafa Gokce Baydogan
    George Runger
    Data Mining and Knowledge Discovery, 2015, 29 : 400 - 422
  • [28] Multivariate time series prediction via temporal classification
    Liu, B
    Liu, J
    18TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING, PROCEEDINGS, 2002, : 268 - 268
  • [29] Multivariate time series classification with crucial timestamps guidance
    Zhang, Da
    Gao, Junyu
    Li, Xuelong
    EXPERT SYSTEMS WITH APPLICATIONS, 2024, 255
  • [30] Disjoint-CNN for Multivariate Time Series Classification
    Foumani, Seyed Navid Mohammadi
    Tan, Chang Wei
    Salehi, Mahsa
    21ST IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS ICDMW 2021, 2021, : 760 - 769