Imaging Time-Series to Improve Classification and Imputation
This work addresses time series analysis problems for researchers and practitioners, offering a novel image-based approach that is incremental in applying existing vision methods to a new domain.
The authors tackled time series classification and imputation by encoding time series as images (GASF/GADF/MTF) to leverage computer vision techniques, achieving competitive classification results on 20 datasets and reducing imputation MSE by 12.18%-48.02% compared to raw data.
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.