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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep neural networks (DNNs) that tackle the time series classification (TSC)task have provided a promising framework in signal processing. In real-worldapplications, as a data-driven model, DNNs are suffered from insufficient data.Few-shot learning has been studied to deal with this limitation. In this paper,we propose a novel few-shot learning framework through data augmentation, whichinvolves transformation through the time-frequency domain and the generation ofsynthetic images through random erasing. Additionally, we develop asequence-spectrogram neural network (SSNN). This neural network model composesof two sub-networks: one utilizing 1D residual blocks to extract features fromthe input sequence while the other one employing 2D residual blocks to extractfeatures from the spectrogram representation. In the experiments, comparisonstudies of different existing DNN models with/without data augmentation areconducted on an amyotrophic lateral sclerosis (ALS) dataset and a wind turbinefault (WTF) dataset. The experimental results manifest that our proposed methodachieves 93.75% F1 score and 93.33% accuracy on the ALS datasets while 95.48%F1 score and 95.59% accuracy on the WTF datasets. Our methodology demonstratesits applicability of addressing the few-shot problems for time seriesclassification.

Few-shot Learning using Data Augmentation and Time-Frequency Transformation for Time Series Classification