BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Topological Data Analysis for Gait Pattern Classification
DTSTART:20260409T100000
DTEND:20260409T110000
DTSTAMP:20260407T205054Z
UID:5e464d3f9af7b904e07d10926d413843d70b3f342bd7822711382ff2
CATEGORIES:Conferences - Seminars
DESCRIPTION:Truong Hoang Manh\, FPT University\, Hanoï\nThe classificati
 on of gait patterns is an important challenge in movement analysis\, as it
  supports clinical assessment and decision-making by enabling diagnosis an
 d severity stratification. In this talk\, I will discuss the potential of 
 Topological Data Analysis (TDA) for gait pattern classification. Unlike co
 nventional approaches that rely on explicit detection of Gait Events (GEs)
  to compute Spatiotemporal Gait Parameters (SGPs)\, TDA characterises the 
 global structure of gait signals directly\, capturing relationships and pa
 tterns in the data without requiring GEs. This is particularly relevant in
  real-world settings\, where GE detection can be diQicult due to heterogen
 eity in walking conditions and gait patterns\, potentially biasing clinica
 lly relevant metrics and\, consequently\, decision-making.\nWithin our dep
 artment\, preliminary results have shown that TDA-based features can achie
 ve classification performance comparable to that of SGPs in fall-risk asse
 ssment. These findings suggest that topology oQers a competitive alternati
 ve for representing gait data\, with the potential to better handle variab
 ility across subjects and pathological\nconditions.\nBuilding on these res
 ults\, we plan to further extend the TDA framework in two directions. Firs
 t\, we aim to investigate time-aware topological methods to better capture
  the\ntemporal structure of gait signals. Second\, we will explore Topolog
 ical Deep Learning (TDL) approaches to reduce reliance on handcrafted desi
 gn choices and potentially\nimprove classification performance. By combini
 ng the robustness of topology with datadriven representation learning\, th
 is work seeks to provide robust tools for the classification of typical an
 d pathological gait patterns.\n 
LOCATION:CM 1 517 https://plan.epfl.ch/?room==CM%201%20517 https://epfl.zo
 om.us/j/64555981838
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR