English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

While one-dimensional convolutional neural networks (1D-CNNs) have beenempirically proven effective in time series classification tasks, we find thatthere remain undesirable outcomes that could arise in their application,motivating us to further investigate and understand their underlyingmechanisms. In this work, we propose a Temporal Convolutional Explorer (TCE) toempirically explore the learning behavior of 1D-CNNs from the perspective ofthe frequency domain. Our TCE analysis highlights that deeper 1D-CNNs tend todistract the focus from the low-frequency components leading to the accuracydegradation phenomenon, and the disturbing convolution is the driving factor.Then, we leverage our findings to the practical application and propose aregulatory framework, which can easily be integrated into existing 1D-CNNs. Itaims to rectify the suboptimal learning behavior by enabling the network toselectively bypass the specified disturbing convolutions. Finally, throughcomprehensive experiments on widely-used UCR, UEA, and UCI benchmarks, wedemonstrate that 1) TCE's insight into 1D-CNN's learning behavior; 2) ourregulatory framework enables state-of-the-art 1D-CNNs to get improvedperformances with less consumption of memory and computational overhead.

Temporal Convolutional Explorer Helps Understand 1D-CNN's Learning Behavior in Time Series Classification from Frequency Domain