{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/imaging-time-series-to-improve-classification","title":"Imaging Time-Series to Improve Classification and Imputation","arxiv_id":"1506.00327","date":"2015-06-01","proceeding":null,"authors":["Zhiguang Wang","Tim Oates"],"abstract":"Inspired by recent successes of deep learning in computer vision, we propose\na novel framework for encoding time series as different types of images,\nnamely, Gramian Angular Summation/Difference Fields (GASF/GADF) and Markov\nTransition Fields (MTF). This enables the use of techniques from computer\nvision for time series classification and imputation. We used Tiled\nConvolutional Neural Networks (tiled CNNs) on 20 standard datasets to learn\nhigh-level features from the individual and compound GASF-GADF-MTF images. Our\napproaches achieve highly competitive results when compared to nine of the\ncurrent best time series classification approaches. Inspired by the bijection\nproperty of GASF on 0/1 rescaled data, we train Denoised Auto-encoders (DA) on\nthe GASF images of four standard and one synthesized compound dataset. The\nimputation MSE on test data is reduced by 12.18%-48.02% when compared to using\nthe raw data. An analysis of the features and weights learned via tiled CNNs\nand DAs explains why the approaches work.","url_abs":"http://arxiv.org/abs/1506.00327v1","url_pdf":"http://arxiv.org/pdf/1506.00327v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"imaging-time-series-to-improve-classification","repo_url":"https://github.com/AlxndrMlk/Timeseries","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"imaging-time-series-to-improve-classification","repo_url":"https://github.com/LurreMcFly/ERP-PREDICTION-CONTEST","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"imaging-time-series-to-improve-classification","repo_url":"https://github.com/cauchyturing/UCR_Time_Series_Classification_Deep_Learning_Baseline","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"imaging-time-series-to-improve-classification","repo_url":"https://github.com/vc1492a/tidd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"imputation","task_name":"Imputation"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.00327","atlas_url":"https://app.syntology.ai/?focus=1506.00327","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}