BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Topological Data Analysis for Gait Pattern Classification
DTSTART:20260423T100000
DTEND:20260423T110000
DTSTAMP:20260429T200622Z
UID:54317750923a0e43861df88b87fb09bb92aa0eff2150230c9c8f36ba
CATEGORIES:Conferences - Seminars
DESCRIPTION:Elena Botti\, Vrije Universiteit Brussel (VUB)\nThe classific
 ation of gait patterns is an important challenge in movement analysis\, as
  it supports clinical assessment and decision-making by enabling diagnosis
  and severity stratification. In this talk\, I will discuss the potential 
 of Topological Data Analysis (TDA) for gait pattern classification. Unlike
  conventional approaches that rely on explicit detection of Gait Events (G
 Es) to compute Spatiotemporal Gait Parameters (SGPs)\, TDA characterises t
 he global structure of gait signals directly\, capturing relationships and
  patterns in the data without requiring GEs. This is particularly relevant
  in real-world settings\, where GE detection can be diQicult due to hetero
 geneity in walking conditions and gait patterns\, potentially biasing clin
 ically relevant metrics and\, consequently\, decision-making.\nWithin our 
 department\, preliminary results have shown that TDA-based features can ac
 hieve classification performance comparable to that of SGPs in fall-risk a
 ssessment. These findings suggest that topology oQers a competitive altern
 ative for representing gait data\, with the potential to better handle var
 iability across subjects and pathological\nconditions.\nBuilding on these 
 results\, we plan to further extend the TDA framework in two directions. F
 irst\, we aim to investigate time-aware topological methods to better capt
 ure the\ntemporal structure of gait signals. Second\, we will explore Topo
 logical Deep Learning (TDL) approaches to reduce reliance on handcrafted d
 esign choices and potentially\nimprove classification performance. By comb
 ining the robustness of topology with datadriven representation learning\,
  this work seeks to provide robust tools for the classification of typical
  and pathological gait patterns.\n 
LOCATION:CM 1 517 https://plan.epfl.ch/?room==CM%201%20517
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR