Ganganalyse bei geriatrischen Patienten mittels mobiler Sensorsysteme und Algorithmen des maschinellen Lernens

Drittmittelfinanzierte Einzelförderung

Details zum Projekt

Prof. Dr. Björn Eskofier
Prof. Dr. Jochen Klucken

Malte Ollenschläger

Beteiligte FAU-Organisationseinheiten:
Lehrstuhl für Informatik 14 (Maschinelles Lernen und Datenanalytik)
Molekular-Neurologische Abteilung in der Neurologischen Klinik

Mittelgeber: Industrie (AGAPLESION gAG)
Projektstart: 15.01.2018
Projektende: 15.01.2021


Maschinelles Lernen und Datenanalytik
Lehrstuhl für Informatik 14 (Maschinelles Lernen und Datenanalytik)

Abstract (fachliche Beschreibung):

Walking is a key element of human mobility and independence. For persons aged 70 or above, the number of falls per year increases drastically. Physiological consequences are bone fractures, traumas or death. In conjunction with psychological consequences, such as post-fall anxiety, falls lead to a decreased quality of life. Most falls could be prevented if an early detection of fall risk was available, thus maintaining a high quality of life.

This project will focus on assessing gait in geriatric patients using sensor-based gait analysis. Inertial sensors will be used to measure risk-of-fall related gait parameters for geriatric patients at hospitals of AGAPLESION gAG (AGAPLESION DIAKONIEKLINIKUM HAMBURG and AGAPLESION MARKUS KRANKENHAUS in Frankfurt am Main). The acquired data will be processed at the Machine Learning and Data Analytics Lab of FAU. The machine-learning algorithms that will be developed, will help to improve diagnostics and to measure therapeutic success.


Externe Partner


Zuletzt aktualisiert 2019-28-02 um 11:19