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

2018-08-07 · Hassan Ismail Fawaz, Germain Forestier, Jonathan Weber, Lhassane Idoumghar, Pierre-Alain Muller

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.

📄 PDF Abstract BibTeX arXiv:1808.02455

Code (2)

hfawaz/aaltd18 공식 구현 tf

neuralprophet/synthetic_prophet pytorch

Tasks

Data AugmentationDynamic Time WarpingGeneral ClassificationTime SeriesTime Series Analysis Time Series Classification

OATS: Online Data Augmentation for Time Series Foundation Models

2026-01-26 · Junwei Deng, Chang Xu, Jiaqi W. Ma, Ming Jin 외 arxiv

Time Series Foundation Models (TSFMs) are a powerful paradigm for time series analysis and are often enhanced by synthetic data augmentation to improve the training data quality. Existing augmentation methods, however, t…

Time Series Analysis Data Augmentation

Does Synthetic Data Help? Empirical Evidence from Deep Learning Time Series Forecasters

2026-05-07 · Hugo Cazaux, Eyjólfur Ingi Ásgeirsson, Hlynur Stefánsson arxiv

Synthetic data has transformed language model training, yet its role in time series forecasting remains poorly understood. We present a large-scale empirical study: nine experiment groups, 4,218 runs systematically evalu…

Time Series Forecasting

Grasynda: Graph-based Synthetic Time Series Generation

2026-01-27 · Luis Amorim, Moises Santos, Paulo J. Azevedo, Carlos Soares 외 arxiv

Data augmentation is a crucial tool in time series forecasting, especially for deep learning architectures that require a large training sample size to generalize effectively. However, extensive datasets are not always a…

Time Series Forecasting Data Augmentation

TTS-CGAN: A Transformer Time-Series Conditional GAN for Biosignal Data Augmentation

2022-06-28 · Xiaomin Li, Anne Hee Hiong Ngu, Vangelis Metsis

Signal measurement appearing in the form of time series is one of the most common types of data used in medical machine learning applications. Such datasets are often small in size, expensive to collect and annotate, and…

Data Augmentation Time Series Time Series Analysis

Generating Synthetic Time Series Data for Cyber-Physical Systems

2024-04-12 · Alexander Sommers, Somayeh Bakhtiari Ramezani, Logan Cummins, Sudip Mittal 외

Data augmentation is an important facilitator of deep learning applications in the time series domain. A gap is identified in the literature, demonstrating sparse exploration of the transformer, the dominant sequence mod…

Data Augmentation Time Series