A vacant PhD Position in Grenoble, France:
Title:
Joint analysis of eye-movements and EEGs using coupled hidden Markov and
topic models
Doctoral School:
Mathematics, Information Sciences and Technologies, and Computer
Science, University of Grenoble (MSTII).
Supervisors:
Anne Guérin-Dugué(1), Marianne Clausel(2a) and Jean-Baptiste Durand(2b)
E-mail: mailto:[log in to unmask],
mailto:[log in to unmask], mailto:[log in to unmask]
Location of PhD: GIPSA-lab or Laboratoire Jean Kuntzmann
(1) GIPSA-lab / Dépt. DIS, 11 rue des Mathématiques, Saint Martin
dHères. +33 (0)4 76 57 43 73
(2) Laboratoire Jean Kuntzmann, Saint Martin dHères. (a) +33(0)4 76 63
56 93 / (b) +33(0)4 76 63 57 09
Scientific background:
Recently, GIPSA-lab has developed computational models of information
search in web-like materials, using data from both eye-tracking to get
eye movements during the search and electroencephalograms (EEGs) to
analyze the related neural activities. These joint datasets were
obtained from experiments, in which subjects had to make some kinds of
press reviews (Frey et al., 2013). In such information seeking tasks,
reading process and decision making are closely related. Two kinds of
decision are expected: A positive decision if the meaning of the text
matches with the goal of information search, and a negative decision
otherwise. Statistical analysis of such data aims at: deciphering
underlying cognitive phases in the cognitive process, characterize these
phases with eye movements and EEG properties, explain the phase changes
by the local text properties and quantify the individual variability of
the phase properties, as well as the variability due to different texts.
Hidden Markov models (HMMs) have been used
on eye movement series to infer phases in the reading process that can
be interpreted as steps in the cognitive processes leading to decision
see for example Simola et al. (2008). In HMMs, each phase is associated
with a state of the Markov chain. The states are observed indirectly
through eye-movements.
However, the characteristics of eye movements within each phase tend to
be poorly discriminated. As a result, high uncertainty in the phase
changes arises, and it can be difficult to relate phases to known
patterns in EEGs. HMMs were also used for the analysis of EEGs
(Obermaier et al., 2001) but coupling eye movements, EEGs and text
properties in a coherent model is an unaddressed challenge.
Tasks:
The aim of the PhD is to develop an integrated model coupling EEG and
eye movements within one single HMM for better identification of the
phases. Coupled HMMs are based on several dependent Markov chains such
that at each time t, observations only depend on the states at time t
(Zhong & Ghosh, 2001). Here, the coupling should incorporate some delay
between the transitions in both chains, since EEG patterns associated to
cognitive processes may occur with some delay with respect to
eye-movement phases.
To better relate the human reading process to some intrinsic
characteristics of the reviewed text, we propose an interpretation of
our two experimental models based on a well-known hierarchical
generative model, called LDA, used in the data mining context (Blei et
al., 2003) and thereafter extending to the image setting (Fei-Fei &
Perona, 2005). We want to model human data mining for text or image as
a variant of LDA, modifying in a convenient way the generative process
and involving a random choice of the cognitive phase. The main goal is
to take into account the fact that, in a text, a given word can be
either read or not. The same question can also be raised in the image
setting since a region of interest corresponding to a specific visual
word can be explored or not. For this, a joint database with eye
movements and EEG signals has been also recording during a visual search
task according to a similar design as the information seeking task.
Prerequisites:
A master or engineer degree is required, and an applicant with a strong
background in probability and statistics or machine learning, as well a
strong interest in cognitive science.
Skills in Matlab, C++ or python would be appreciated.
Funding:
This PhD is supported by a 3-year Persyval Fellowship,
http://persyval-lab.org/research/action/adm ,
according to French standards (about 1,400 euros net/month), starting
01.10.2015 at the earliest.
Context:
The research will be undertaken in the context of an interdisciplinary
project involving three research laboratories (GIPSA-lab, LJK, and LPNC)
from the University of Grenoble Alpes. The consortium has scientific
expertise on statistics, information processing, and cognitive sciences,
providing a stimulating scientific environment for this thesis. Last but
not least, Grenoble is a very pleasant place to study and work. Grenoble
is rated each year as the best place in France for studying.
References:
D. Blei, A. Ng, and M. Jordan. Latent Dirichlet allocation. Journal of
Machine Learning Research, 3, 9931022 (January 2003).
L. Fei-Fei and P. Perona. A Bayesian hierarchical model for learning
natural scene categories. IEEE Computer vision and Pattern Recognition
(2005)
A. Frey, G. Ionescu, B. Lemaire, F. Lopez Orozco, T. Baccino and A.
Guérin-Dugué. Decision-making in information seeking on texts: an
Eye-Fixation-Related Potentials investigation. Frontiers in Systems
Neuroscience, 7, pp.Article 39 (2013).
B. Obermaier, C. Guger, C. Neuper and G. Pfurtscheller. Hidden Markov
models for online classification of single trial EEG data. Pattern
Recognition Letters, 22, 1299-1309 (2001).
J. Simola, J. Salojärvi and I. Kojo. Using hidden Markov model to
uncover processing states from eye movements in information search
tasks. Cognitive Systems Research 9(4), 237-251 (October 2008)
S. Zhong and J. Ghosh. A New Formulation of Coupled Hidden Markov
Models, Technical report, Dept. of Electrical and Computer Eng., Univ.
of Texas at Austin (2001)
--
Laboratoire Jean Kuntzmann
51 rue des Mathematiques
B.P.53
38041 Grenoble cedex 9, France
Tel. +33 (0)4 76 63 57 09 (tour IRMA)
+33 (0)4 76 61 53 38 (Montbonnot)
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|