Neural Data Augmentation Techniques for Time Series Data and its Benefits

Sarkar, Anindya and Sunder Raj, Anirudh and Sesha Iyengar, Raghu (2020) Neural Data Augmentation Techniques for Time Series Data and its Benefits. In: 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020, 14 December 2020through 17 December 2020, Virtual, Miami.

Text
Neural_Data_Augmentation_Techniques_for_Time_Series_Data_and_its_Benefits.pdf - Published Version
Available under License Creative Commons Attribution.
Download (1MB)

Abstract

Exploring adversarial attacks and studying their effects on machine learning algorithms has been of interest to researchers. Deep neural networks working with time series data have received lesser interest compared to their image counterparts in this context. In a recent finding, it has been revealed that current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks. In this paper, we introduce neural data augmentation techniques and show that classifier trained with such augmented data obtains state-of-the-art classification accuracy as well as adversarial accuracy against Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM) on various time series benchmarks. © 2020 IEEE.

[error in script]

IITH Creators: