Data augmentation using synthetic data for time series classification with deep residual networks

Abstract

Data augmentation in deep neural networks is the process of generating artificial data in order to reduce the variance of the classifier with the goal to reduce the number of errors. This idea has been shown to improve deep neural network's generalization capabilities in many computer vision tasks such as image recognition and object localization. Apart from these applications, deep Convolutional Neural Networks (CNNs) have also recently gained popularity in the Time Series Classification (TSC) community. However, unlike in image recognition problems, data augmentation techniques have not yet been investigated thoroughly for the TSC task. This is surprising as the accuracy of deep learning models for TSC could potentially be improved, especially for small datasets that exhibit overfitting, when a data augmentation method is adopted. In this paper, we fill this gap by investigating the application of a recently proposed data augmentation technique based on the Dynamic Time Warping distance, for a deep learning model for TSC. To evaluate the potential of augmenting the training set, we performed extensive experiments using the UCR TSC benchmark. Our preliminary experiments reveal that data augmentation can drastically increase deep CNN's accuracy on some datasets and significantly improve the deep model's accuracy when the method is used in an ensemble approach.

arXiv commentAccepted at AALTD'18 workshop in ECML/PKDD

References in corpus (2)

• Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification
• Data Augmentation for Brain-Computer Interfaces: Analysis on Event-Related Potentials Data

Cited by in corpus (17)

• Deep learning for time series classification: a review
• An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
• Transfer learning for time series classification
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• Label-Only Membership Inference Attacks
• Deep Neural Network Ensembles for Time Series Classification
• RobustTAD: Robust Time Series Anomaly Detection via Decomposition and Convolutional Neural Networks
• Fractal interpolation in the context of prediction accuracy optimization
• Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher
• IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition
• Deep learning for time series classification
• DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification
• Style Transfer with Time Series: Generating Synthetic Financial Data
• Short-Term Stock Price-Trend Prediction Using Meta-Learning
• Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification
• DTWSSE: Data Augmentation with a Siamese Encoder for Time Series
• ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness