Data Augmentation for Time Series Classification using Convolutional Neural Networks

By Arthur Le Guennec, Simon Malinowski, Romain Tavenard. 2016

451 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e467404d68c8c2f45bae0e4bdfda12fc7df65cce

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Temporal Convolutional Neural Network for the Classification of Satellite Image Time Series (2018, methodology): “Data augmentation techniques have also been developed for time series including window slicing, window warping and weighted averaged time series [50], [51], [52].”
Time Series Data Augmentation for Deep Learning: A Survey (2020, methodology): “Window cropping or slicing has been mentioned in [Le Guennec et al., 2016].”
MOMENT: A Family of Open Time-series Foundation Models (2024, methodology): “…5 unsupervised representation learning methods (TS2Vec (Yue et al., 2022), TST (Zerveas et al., 2021), TS-TCC (Eldele et al., 2021), TNC (Tonekaboni et al., 2021), and T-Loss (Franceschi et al., 2019)), 8 supervised deep learning (CNN (Zebik et al., 2017), Encoder (Serr`a et al., 2018), FCN…”
HS-CNN: a CNN with hybrid convolution scale for EEG motor imagery classification (2020, methodology): “Performance of the proposed data augmentation method We have also evaluated the performance of the proposed data augmentation method and compared it with the existing data augmentation methods including window sliding [26, 52, 53] and noise adding [55, 56].”
Predicting mortgage default using convolutional neural networks (2018, background): “Le Guennec et al. (2016) explore the possibilities of training a CNN in a semi-supervised manner using time series from other datasets.”
BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series (2019, methodology): “[Le Guennec et al., 2016] proposed a data augmentation method, ‘window warping’ for time series data.”
Data augmentation of wearable sensor data for parkinson’s disease monitoring using convolutional neural networks (2017, background): “augmentation is needed [6]. Data augmentation is an indispensable preprocessing step for achieving peak performance in DL approaches (e.g. [9, 12]). For augmenting time-series data, Le Guennec et al. [14] used window slicing and window warping methods, which extracts multiple small-size windows from”