Continuous Cnn For Nonuniform Time Series
Hui Shi, Yang Zhang, Hao Wu, Shiyu Chang, Kaizhi Qian, Mark Hasegawa-Johnson, Jishen Zhao
Abstract
CNN for time series data implicitly assumes that the data are uniformly sampled, whereas many event-based and multi-modal data are nonuniform or have heterogeneous sampling rates. Directly applying regular CNN to nonuniform time series is ungrounded, because it is unable to recognize and extract common patterns from the nonuniform input signals. In this paper, we propose the Continuous CNN (CCNN), which estimates the inherent continuous inputs by interpolation, and performs continuous convolution on the continuous input. The interpolation and convolution kernels are learned in an end-to-end manner, and are able to learn useful patterns despite the nonuniform sampling rate. Results of several experiments verify that CCNN achieves a better performance on nonuniform data, and learns meaningful continuous kernels. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>
BibTeX
@inproceedings{icassp2021_continuouscnnfor,
title = {Continuous Cnn For Nonuniform Time Series},
author = {Hui Shi and Yang Zhang and Hao Wu and Shiyu Chang and Kaizhi Qian and Mark Hasegawa-Johnson and Jishen Zhao},
booktitle = {ICASSP 2021},
year = {2021}
}