{"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/efficient-matrix-profile-computation-using","title":"Efficient Matrix Profile Computation Using Different Distance Functions","arxiv_id":"1901.05708","date":"2019-01-17","proceeding":null,"authors":["Reza Akbarinia","Bertrand Cloez"],"abstract":"Matrix profile has been recently proposed as a promising technique to the\nproblem of all-pairs-similarity search on time series. Efficient algorithms\nhave been proposed for computing it, e.g., STAMP, STOMP and SCRIMP++. All these\nalgorithms use the z-normalized Euclidean distance to measure the distance\nbetween subsequences. However, as we observed, for some datasets other\nEuclidean measurements are more useful for knowledge discovery from time\nseries. In this paper, we propose efficient algorithms for computing matrix\nprofile for a general class of Euclidean distances. We first propose a simple\nbut efficient algorithm called AAMP for computing matrix profile with the\n\"pure\" (non-normalized) Euclidean distance. Then, we extend our algorithm for\nthe p-norm distance. We also propose an algorithm, called ACAMP, that uses the\nsame principle as AAMP, but for the case of z-normalized Euclidean distance. We\nimplemented our algorithms, and evaluated their performance through\nexperimentation. The experiments show excellent performance results. For\nexample, they show that AAMP is very efficient for computing matrix profile for\nnon-normalized Euclidean distances. The results also show that the ACAMP\nalgorithm is significantly faster than SCRIMP++ (the state of the art matrix\nprofile algorithm) for the case of z-normalized Euclidean distance.","url_abs":"http://arxiv.org/abs/1901.05708v1","url_pdf":"http://arxiv.org/pdf/1901.05708v1.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":"efficient-matrix-profile-computation-using","repo_url":"https://github.com/StanislavParovoy/stumpy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"efficient-matrix-profile-computation-using","repo_url":"https://github.com/TDAmeritrade/stumpy","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"efficient-matrix-profile-computation-using","repo_url":"https://github.com/MindSpore-scientific-2/code-10/tree/main/Profiling-Pareto-Front","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"efficient-matrix-profile-computation-using","repo_url":"https://github.com/MindSpore-scientific-2/code-8/tree/main/Profiling-Pareto-Front","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}