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

Underwater acoustic recognition for ship-radiated signals has high practicalapplication value due to the ability to recognize non-line-of-sight targets.However, due to the difficulty of data acquisition, the collected signals arescarce in quantity and mainly composed of mechanical periodic noise. Accordingto the experiments, we observe that the repeatability of periodic signals leadsto a double-descent phenomenon, which indicates a significant local bias towardrepeated samples. To address this issue, we propose a strategy based oncross-entropy to prune excessively similar segments in training data.Furthermore, to compensate for the reduction of training data, we generatenoisy samples and apply smoothness-inducing regularization based on KLdivergence to mitigate overfitting. Experiments show that our proposed datapruning and regularization strategy can bring stable benefits and our frameworksignificantly outperforms the state-of-the-art in low-resource scenarios.

Advancing underwater acoustic target recognition via adaptive data pruning and smoothness-inducing regularization