{"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/classification-of-time-series-images-using","title":"Classification of Time-Series Images Using Deep Convolutional Neural Networks","arxiv_id":"1710.00886","date":"2017-10-02","proceeding":null,"authors":["Nima Hatami","Yann Gavet","Johan Debayle"],"abstract":"Convolutional Neural Networks (CNN) has achieved a great success in image\nrecognition task by automatically learning a hierarchical feature\nrepresentation from raw data. While the majority of Time-Series Classification\n(TSC) literature is focused on 1D signals, this paper uses Recurrence Plots\n(RP) to transform time-series into 2D texture images and then take advantage of\nthe deep CNN classifier. Image representation of time-series introduces\ndifferent feature types that are not available for 1D signals, and therefore\nTSC can be treated as texture image recognition task. CNN model also allows\nlearning different levels of representations together with a classifier,\njointly and automatically. Therefore, using RP and CNN in a unified framework\nis expected to boost the recognition rate of TSC. Experimental results on the\nUCR time-series classification archive demonstrate competitive accuracy of the\nproposed approach, compared not only to the existing deep architectures, but\nalso to the state-of-the art TSC algorithms.","url_abs":"http://arxiv.org/abs/1710.00886v2","url_pdf":"http://arxiv.org/pdf/1710.00886v2.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":"classification-of-time-series-images-using","repo_url":"https://github.com/lauraperge/blackbox-trading-CNN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"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":{"atlas_url":"https://app.syntology.ai/?focus=1710.00886","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}