{"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/explaining-the-unique-nature-of-individual","title":"Explaining the Unique Nature of Individual Gait Patterns with Deep Learning","arxiv_id":"1808.04308","date":"2018-08-13","proceeding":null,"authors":["Fabian Horst","Sebastian Lapuschkin","Wojciech Samek","Klaus-Robert Müller","Wolfgang I. Schöllhorn"],"abstract":"Machine learning (ML) techniques such as (deep) artificial neural networks\n(DNN) are solving very successfully a plethora of tasks and provide new\npredictive models for complex physical, chemical, biological and social\nsystems. However, in most cases this comes with the disadvantage of acting as a\nblack box, rarely providing information about what made them arrive at a\nparticular prediction. This black box aspect of ML techniques can be\nproblematic especially in medical diagnoses, so far hampering a clinical\nacceptance. The present paper studies the uniqueness of individual gait\npatterns in clinical biomechanics using DNNs. By attributing portions of the\nmodel predictions back to the input variables (ground reaction forces and\nfull-body joint angles), the Layer-Wise Relevance Propagation (LRP) technique\nreliably demonstrates which variables at what time windows of the gait cycle\nare most relevant for the characterisation of gait patterns from a certain\nindividual. By measuring the time-resolved contribution of each input variable\nto the prediction of ML techniques such as DNNs, our method describes the first\ngeneral framework that enables to understand and interpret non-linear ML\nmethods in (biomechanical) gait analysis and thereby supplies a powerful tool\nfor analysis, diagnosis and treatment of human gait.","url_abs":"http://arxiv.org/abs/1808.04308v2","url_pdf":"http://arxiv.org/pdf/1808.04308v2.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":"explaining-the-unique-nature-of-individual","repo_url":"https://github.com/sebastian-lapuschkin/interpretable-deep-gait","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[],"methods":[],"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}