Time Series Data Augmentation for Neural Networks by Time Warping with a Discriminative Teacher

2020/04/19 by Brian Kenji Iwana, Seiichi Uchida, Iwana, Brian Kenji +1 · 3 citations
Computer Science · #Anomaly Detection Techniques and Applications #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Music and Audio Processing #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2004.08780

openalex publication_date 2020/04/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Neural networks have become a powerful tool in pattern recognition and part of their success is due to generalization from using large datasets. However, unlike other domains, time series classification datasets are often small. In order to address this problem, we propose a novel time series data augmentation called guided warping. While many data augmentation methods are based on random transformations, guided warping exploits the element alignment properties of Dynamic Time Warping (DTW) and shapeDTW, a high-level DTW method based on shape descriptors, to deterministically warp sample patterns. In this way, the time series are mixed by warping the features of a sample pattern to match the time steps of a reference pattern. Furthermore, we introduce a discriminative teacher in order to serve as a directed reference for the guided warping. We evaluate the method on all 85 datasets in the 2015 UCR Time Series Archive with a deep convolutional neural network (CNN) and a recurrent neural network (RNN). The code with an easy to use implementation can be found at https://github.com/uchidalab/time_series_augmentation .

Citations

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep learning in neural networks: An overview
• Gradient-based learning applied to document recognition
• ImageNet Large Scale Visual Recognition Challenge
• Dynamic programming algorithm optimization for spoken word recognition
• Minimum prediction residual principle applied to speech recognition
• Learning Multiple Layers of Features from Tiny Images

Cited by

• Learning Time-Scale Invariant Population-Level Neural Representations
• DS-Diffusion: Data Style-Guided Diffusion Model for Time-Series Generation
• Invariant Features for Global Crop Type Classification

Related

• DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification
• Bridging Neural Networks and Dynamic Time Warping for Adaptive Time Series Classification
• Temporal Transformer Networks: Joint Learning of Invariant and\n Discriminative Time Warping
• Data augmentation using synthetic data for time series classification with deep residual networks
• Attention to Warp: Deep Metric Learning for Multivariate Time Series