错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

AnomGait: Data-Driven Extraction of Movement Features Using Contrastive Learning

  • André Böni,
  • Theo Maffei,
  • Alain Ryser,
  • Mathilde Legrand,
  • Deepak K. Ravi,
  • Meret Branscheidt,
  • Julia E. Vogt,
  • Andreas R. Luft,
  • Chris Awai Easthope

摘要

To describe movement patterns in gait, interpretable handcrafted features such as step length and step width are typically used. Current movement analysis tools allow the generation of rich, high-dimensional data for each individual, which is then, however, again reduced to traditional, single-dimension parameters. We here apply contrastive learning to high-dimensional gait data sets from neurological patients and healthy individuals and attempt to distill data-driven features to improve separation.