{"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/fast-and-accurate-time-series-classification","title":"Fast and Accurate Time Series Classification with WEASEL","arxiv_id":"1701.07681","date":"2017-01-26","proceeding":null,"authors":["Patrick Schäfer","Ulf Leser"],"abstract":"Time series (TS) occur in many scientific and commercial applications,\nranging from earth surveillance to industry automation to the smart grids. An\nimportant type of TS analysis is classification, which can, for instance,\nimprove energy load forecasting in smart grids by detecting the types of\nelectronic devices based on their energy consumption profiles recorded by\nautomatic sensors. Such sensor-driven applications are very often characterized\nby (a) very long TS and (b) very large TS datasets needing classification.\nHowever, current methods to time series classification (TSC) cannot cope with\nsuch data volumes at acceptable accuracy; they are either scalable but offer\nonly inferior classification quality, or they achieve state-of-the-art\nclassification quality but cannot scale to large data volumes.\n  In this paper, we present WEASEL (Word ExtrAction for time SEries\ncLassification), a novel TSC method which is both scalable and accurate. Like\nother state-of-the-art TSC methods, WEASEL transforms time series into feature\nvectors, using a sliding-window approach, which are then analyzed through a\nmachine learning classifier. The novelty of WEASEL lies in its specific method\nfor deriving features, resulting in a much smaller yet much more discriminative\nfeature set. On the popular UCR benchmark of 85 TS datasets, WEASEL is more\naccurate than the best current non-ensemble algorithms at orders-of-magnitude\nlower classification and training times, and it is almost as accurate as\nensemble classifiers, whose computational complexity makes them inapplicable\neven for mid-size datasets. The outstanding robustness of WEASEL is also\nconfirmed by experiments on two real smart grid datasets, where it\nout-of-the-box achieves almost the same accuracy as highly tuned,\ndomain-specific methods.","url_abs":"http://arxiv.org/abs/1701.07681v1","url_pdf":"http://arxiv.org/pdf/1701.07681v1.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":"fast-and-accurate-time-series-classification","repo_url":"https://github.com/sktime/sktime","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"load-forecasting","task_name":"Load Forecasting"},{"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":[{"method_slug":"ts","method_name":"TS"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}