Connectionists: doctoral student in movement studies and machine learning

[Elizabeth Thomas]

*Doctoral studies in the application of machine learning techniques to 
the analysis of motor activity*


**

We are seeking to recruit a doctoral student who would like to carry out 
an interdisciplinary study between the areas of signal analyses and 
movement studies. The study of all motor activities from gait to dance 
is done by the gathering of kinetic, kinematic and EMG data. Kinematic 
data is obtained from the displacement of markers placed on the 
subjects. Kinetic signals provide information on the foot-ground 
pressure during movements. Finally EMG data is from the electric 
activity of muscles. As with many biological signals, the analysis of 
these signals presents us with an important challenge due to their 
complexity, high variability and noise. The linear techniques which are 
currently most frequently employed are not sufficiently developed for 
the analyses of such ‘noisy’ data. We propose therefore the development 
of several techniques from machine learning for the analysis of these 
signals.

The PhD student interested in these studies will learn how to use 
techniques like neural networks and kernel methods. He/She would also 
learn to use the systems available in the lab for the analyses of 
movement such as SMART, the Kistler force platform and the Biopac EMG.

The thesis will be done under the co-direction of Robert French 
(Directeur de Recherche, CNRS, LEAD, ( 0380399065, 
robert.french at u-bourgogne.fr) and Elizabeth Thomas (maître de 
conférence, INSERM U887, 0380396784, elizabeth.thomas at u-bourgogne.fr 
<mailto:elizabeth.thomas at u-bourgogne.fr>). Candidates interested in the 
grant will have to undergo a competitive interview in Paris in June 2008.

More information on Robert French can be seen on

http://www.u-bourgogne.fr/lead/people/rfrench.html

All interested candidates may send a CV to Robert French and Elizabeth 
Thomas.