Thesis Director: Prof. B. T. A. Lecampion,
\r\nMechanics doctoral program
\r\nThesis Nr. 11652
\r\n
\r\nTo take part in the public defense, please contact directly the speaker
The MARVEL Junior Seminar series is continuing in hybrid mode, in order to maintain in-person contacts and allow off-campus attendees to follow the seminars remotely! The MARVEL Junior Seminars aim to intensify interactions between the MARVEL Junior scientists belonging to different research groups. The seminar consists of two 25-minute presentations, followed by time for discussion.
\r\n
\r\nZacharie Waysenson
\r\nLaboratoire de Physique de l’École Normale Supérieure, Sorbonne Université
\r\n
\r\nMaria Andolfatto
\r\nLaboratory for Materials Simulations, PSI
The classification 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 (GEs) to compute Spatiotemporal Gait Parameters (SGPs), TDA characterises the 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 heterogeneity in walking conditions and gait patterns, potentially biasing clinically relevant metrics and, consequently, decision-making.
\r\nWithin our department, preliminary results have shown that TDA-based features can achieve classification performance comparable to that of SGPs in fall-risk assessment. These findings suggest that topology oQers a competitive alternative for representing gait data, with the potential to better handle variability across subjects and pathological
\r\nconditions.
\r\nBuilding on these results, we plan to further extend the TDA framework in two directions. First, we aim to investigate time-aware topological methods to better capture the
\r\ntemporal structure of gait signals. Second, we will explore Topological Deep Learning (TDL) approaches to reduce reliance on handcrafted design choices and potentially
\r\nimprove classification performance. By combining the robustness of topology with datadriven representation learning, this work seeks to provide robust tools for the classification of typical and pathological gait patterns.
\r\n
Empa – the Swiss Federal Laboratories for Materials Science and Technology – focuses on developing materials and technologies that address societal challenges and enable sustainable innovation. Positioned at the interface between cutting-edge research and application, Empa translates advances in materials science into solutions with tangible impact for industry and society.
\r\nThis talk provides an overview of key Empa activities across energy, mobility, health and the built environment, highlighting examples such as circular materials, advanced manufacturing, functional surfaces, and energy systems. Emphasis is also placed on interdisciplinary initiatives and technology transfer platforms like NEST, move, the Coating Competence Center, or the Climate Solutions Hub which accelerate the transfer of research into scalable applications.
\r\nBuilding on these examples, closer collaborations with the EPFL School of Engineering (STI), e.g. at the intersection of materials, intelligent systems, and advanced engineering are foreseen.
\r\n
\r\nBio:
\r\nTanja Zimmermann has a Master in Wood Science and Technology from the University of Hamburg and a Master of Advanced Studies in Secondary and Higher education from ETH Zürich. She received her PhD from the University of Hamburg in 2007. Tanja Zimmermann built up the cellulose nanocomposites research topic at Empa as group leader and later as head of the laboratory \"Applied Wood Materials\". She became a member of the Directorate of Empa in 2017, leading the department \"Functional Materials\" as well as the research focus area of \"Sustainable Construction\" dealing with different materials such as e.g. concrete and asphalt, wood, ceramics, advanced polymer fibers, or energy materials and components. Tanja Zimmermann is an elected member of Academia Europaea and part of various national and international committees and scientific advisory boards. Since June 2022 she has been Director of Empa and Professor for Materials Science at ETH Zurich and EPF Lausanne.
\r\n
Directeur de thèse : Prof. A. Züttel,
\r\nProgramme doctoral en Chimie et génie chimique
\r\nThèse n° 11688
\r\n
\r\nPour participer à la soutenance publique, merci de contacter directement l’intervenant