back to list

Ann-Kathrin Seifert wins Three Minute Thesis competition at EUSIPCO 2019

2019/09/18

At this year's European Signal Processing Conference (EUSIPCO) in A Coruña, Spain, Ann-Kathrin Seifert won the Three Minute Thesis Contest by presenting her PhD topic “Signal Processing for Radar-based Medical Gait Analysis”.

From the left: Student Activities Co-Chair Jordi Vilà-Valls, represantative of the company everis (sponsor of the prize), Ann-Kathrin Seifert, EURASIP Director for Tehnical Programs and Membership Jean-Yves Tourneret, EURASIP Presdident Patrick Naylor.

The competition, held for the fifth consecutive time at EUSIPCO, is organised annually by the European Association for Signal Processing (EURASIP). This year, ten doctoral candidates were invited to EUSIPCO in A Coruña on the basis of 3-minute videos submitted in advance. The candidates from different universities had to present their doctoral topic live in three minutes in front of 125 spectators. The audience then voted to select the three winners.

Ann-Kathrin Seifert has been researching radar-based gait detection since October 2015. Using the so-called radar micro-Doppler signatures, abnormalities in the gait can be detected without the need for wearable sensors. The doctoral work of Ann-Kathrin Seifert is supervised by Prof. Dr.-Ing. Abdelhak Zoubir and Prof. Dr. Moeness Amin from Villanova University, PA, USA.

Congratulations, Ann-Kathrin!

The 3MT® is a prestigious international academic competition developed by The University of Queensland, Australia, for PhD students in 2008. Since then, the competition has grown to be held in over 200 universities worldwide and has been used as a trademark for regular competitions.

Recently, radar has been extensively used for indoor human monitoring with applications to elderly care and smart home. In this research, we seek to demonstrate the yet unexploited potential of electromagnetic sensing for medical gait analysis. We aim to show that radar can provide continuous in-home health monitoring and enable timely detection of gait disorders. For this, we develop signal processing methods and machine learning algorithms to automatically detect gait abnormalities based on radar measurements.

Radar micro-Doppler signature of a limping person.
Radar micro-Doppler signature of a limping person.