An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks

Abstract

In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.

References in corpus (11)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Deep Learning in Neural Networks: An Overview
• Conditional Generative Adversarial Nets
• ADADELTA: An Adaptive Learning Rate Method
• WaveNet: A Generative Model for Raw Audio
• Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networks
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• Optimal Hyperparameters for Deep LSTM-Networks for Sequence Labeling Tasks
• Insights into LSTM Fully Convolutional Networks for Time Series Classification
• Augmentation Scheme for Dealing with Imbalanced Network Traffic Classification Using Deep Learning

Cited by in corpus (40)

• Data Augmentation techniques in time series domain: A survey and taxonomy
• A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU
• Generative Adversarial Networks for Labeled Acceleration Data Augmentation for Structural Damage Detection
• Enabling hand gesture customization on wrist-worn devices
• Biological neurons act as generalization filters in reservoir computing
• Filling time-series gaps using image techniques: Multidimensional context autoencoder approach for building energy data imputation
• Label-efficient Time Series Representation Learning: A Review
• LSTM networks provide efficient cyanobacterial blooms forecasting even with incomplete spatio-temporal data
• Lifelong Adaptive Machine Learning for Sensor-based Human Activity Recognition Using Prototypical Networks
• A Shapelet-based Framework for Unsupervised Multivariate Time Series Representation Learning
• Adaptive Weighting Scheme for Automatic Time-Series Data Augmentation
• Data Augmentation of Time-Series Data in Human Movement Biomechanics: A Scoping Review
• Designing thermal radiation metamaterials via hybrid adversarial autoencoder and Bayesian optimization
• Predicting atmospheric turbulence for secure quantum communications in free space
• Analysis of the first Genetic Engineering Attribution Challenge
• Fractal interpolation in the context of prediction accuracy optimization
• Machine learning-based classification for Single Photon Space Debris Light Curves
• StyleTime: Style Transfer for Synthetic Time Series Generation
• Data Augmentation Methods of Dynamic Model Identification for Harbor Maneuvers using Feedforward Neural Network
• Non-contrastive representation learning for intervals from well logs
• AI Hazard Management: A framework for the systematic management of root causes for AI risks
• Dynamic Compositional Graph Convolutional Network for Efficient Composite Human Motion Prediction
• DTW-Merge: A Novel Data Augmentation Technique for Time Series Classification
• RHiOTS: A Framework for Evaluating Hierarchical Time Series Forecasting Algorithms
• Generation of Probabilistic Synthetic Data for Serious Games: A Case Study on Cyberbullying
• Improving Rehabilitative Assessment with Statistical and Shape Preserving Surrogate Data and Singular Spectrum Analysis
• On Mini-Batch Training with Varying Length Time Series
• Improving Astronomical Time-series Classification via Data Augmentation with Generative Adversarial Networks
• Synthetic Data Generation for Augmenting Small Samples
• Data augmentation through multivariate scenario forecasting in Data Centers using Generative Adversarial Networks
• Graph Structure Based Data Augmentation Method
• Evaluating data augmentation for financial time series classification
• An Empirical Evaluation of Multivariate Time Series Classification with Input Transformation across Different Dimensions
• MMformer with Adaptive Transferable Attention: Advancing Multivariate Time Series Forecasting for Environmental Applications
• ATCN: Resource-Efficient Processing of Time Series on Edge
• Fidelitous Augmentation of Human Accelerometric Data for Deep Learning
• Transformer-based Self-supervised Multimodal Representation Learning for Wearable Emotion Recognition
• Meta-Learning to Improve Pre-Training
• Deep Learning-Based Detection of the Acute Respiratory Distress Syndrome: What Are the Models Learning?
• Data science and AI in FinTech: An overview