Imaging Time-Series to Improve Classification and Imputation
arXiv:1506.00327
Abstract
Inspired by recent successes of deep learning in computer vision, we propose a novel framework for encoding time series as different types of images, namely, Gramian Angular Summation/Difference Fields (GASF/GADF) and Markov Transition Fields (MTF). This enables the use of techniques from computer vision for time series classification and imputation. We used Tiled Convolutional Neural Networks (tiled CNNs) on 20 standard datasets to learn high-level features from the individual and compound GASF-GADF-MTF images. Our approaches achieve highly competitive results when compared to nine of the current best time series classification approaches. Inspired by the bijection property of GASF on 0/1 rescaled data, we train Denoised Auto-encoders (DA) on the GASF images of four standard and one synthesized compound dataset. The imputation MSE on test data is reduced by 12.18%-48.02% when compared to using the raw data. An analysis of the features and weights learned via tiled CNNs and DAs explains why the approaches work.
Accepted by IJCAI-2015 ML track
References in corpus (1)
Cited by in corpus (12)
- Deep learning for time series classification: a review
- Forecasting with time series imaging
- Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline
- CLPVG: Circular limited penetrable visibility graph as a new network model for time series
- Gramian Angular Fields for leveraging pretrained computer vision models with anomalous diffusion trajectories
- Financial Trading Decisions based on Deep Fuzzy Self-Organizing Map
- DeConFuse : A Deep Convolutional Transform based Unsupervised Fusion Framework
- Representation Learning with Deconvolution for Multivariate Time Series Classification and Visualization
- Predicting the Future is like Completing a Painting!
- Timage -- A Robust Time Series Classification Pipeline
- Semi-supervised multiscale dual-encoding method for faulty traffic data detection
- Social Impressions of the NAO Robot and its Impact on Physiology