TY - GEN

T1 - Multivariate Time Series Analysis

T2 - 9th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2022

AU - Younis, Raneen

AU - Zerr, Sergej

AU - Ahmadi, Zahra

N1 - Funding Information: This work was supported by German Federal Ministry of Education and Research (BMBF) under grant agreement No. 01IS19063A (project HAISEM-Lab, 2019-2022), and the European Union’s Horizon 2020 research and innovation program under grant agreement No. 833635 (project ROXANNE: Real-time network, text, and speaker analytics for combating organized crime, 2019-2022).

PY - 2022

Y1 - 2022

N2 - Deep neural networks, especially the Convolutional Neural Network (CNN) models, have shown promising results in multivariate time series data analysis. However, the predictions of these data-driven black-box models are tough to interpret from a human perspective, making it questionable to trust and rely on the predictions made by these models, specifically for time series data with the append-only feature. This paper proposes a new approach to interpret the CNN outputs by extracting and clustering the activated time series sequences learned from a trained network. These sequences show the representative features for each output label and form interpretable representations from the original time series data. Our approach is the first framework to identify each signal's role and dependencies, consider all possible combinations of signals in the multivariate time-series input, and visualize the data representative features. Our experiments on the Baydogan's archive indicate remarkable improvements in the interpretability of the network predictions and relation identification of each input signal to the output label and the channels of the network layers. Furthermore, the conducted experiments confirm that the extracted patterns are representative of the multivariate input and changing them results in a drastic reduction in the prediction accuracy.

AB - Deep neural networks, especially the Convolutional Neural Network (CNN) models, have shown promising results in multivariate time series data analysis. However, the predictions of these data-driven black-box models are tough to interpret from a human perspective, making it questionable to trust and rely on the predictions made by these models, specifically for time series data with the append-only feature. This paper proposes a new approach to interpret the CNN outputs by extracting and clustering the activated time series sequences learned from a trained network. These sequences show the representative features for each output label and form interpretable representations from the original time series data. Our approach is the first framework to identify each signal's role and dependencies, consider all possible combinations of signals in the multivariate time-series input, and visualize the data representative features. Our experiments on the Baydogan's archive indicate remarkable improvements in the interpretability of the network predictions and relation identification of each input signal to the output label and the channels of the network layers. Furthermore, the conducted experiments confirm that the extracted patterns are representative of the multivariate input and changing them results in a drastic reduction in the prediction accuracy.

KW - classification

KW - interpretability

KW - neural networks

KW - time series

UR - http://www.scopus.com/inward/record.url?scp=85148536963&partnerID=8YFLogxK

U2 - 10.1109/DSAA54385.2022.10032335

DO - 10.1109/DSAA54385.2022.10032335

M3 - Conference contribution

AN - SCOPUS:85148536963

SN - 978-1-6654-7331-6

BT - 2022 IEEE 9th International Conference on Data Science and Advanced Analytics

A2 - Huang, Joshua Zhexue

A2 - Pan, Yi

A2 - Hammer, Barbara

A2 - Khan, Muhammad Khurram

A2 - Xie, Xing

A2 - Cui, Laizhong

A2 - He, Yulin

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 October 2022 through 16 October 2022

ER -