A PhD studentship is currently available in our laboratory on Hand and
finger biomechanics
(Biomechanics team, control system department, Gipsa-lab Laboratory UMR
CNRS 5216).
http://www.gipsa-lab.inpg.fr/ http://www.gipsa-lab.inpg.fr/index.php?id=551
Theme: Today, there exists a variety of interfaces that allow human
users to interact with
computerized systems (mice, keyboards, pens, dials, and touch-sensitive
surfaces).
The main objective of this subject is to elaborate a methodology that
directly senses and decodes
human muscular activity rather than relying on physical device actuation
or user actions that are externally visible or audible.
Advances in muscular sensing and processing technologies provide us with
the unprecedented
opportunity to potentially interface directly with human muscle
activity. Difficulty in sEMG processing
arises from the fact that skin surface electrodes do not record signal
only from individual muscles,
instead some mixture of signals from many muscles is sensed (cross
talk). Moreover, the number of
recorded raw signals is fewer like the number of underlying sources.
Hence, for pattern classification,
a decomposition technique has to be used in sEMG.
The research challenges will concern: (1) the development of an
equipment which must be easy to set up,
to configure and unobtrusive; (2) the hand gesture identification
providing available assessment of sEMG
recordings; and (3) the use of current biomechanical models for
neuromuscular control together with blind
source separation algorithms and some techniques for sEMG signal
decomposition, processing and classification.
Experimental tasks are planed. An approach based on spatial
time-frequency distribution will be applied to s
eparate nonstationnary sEMG signals. After relevant extraction,
classification will be achieved with an
adaptive neural network (SVM)
SALARY
Funding for three years is available from the French Government.
The PhD will be supported by all the resources available in the
GIPSA-Lab laboratory.
Please also send a copy of your CV to franck.quaine@gipsa-lab.inpg.fr.
Closing date 20 Mai 2009.
finger biomechanics
(Biomechanics team, control system department, Gipsa-lab Laboratory UMR
CNRS 5216).
http://www.gipsa-lab.inpg.fr/ http://www.gipsa-lab.inpg.fr/index.php?id=551
Theme: Today, there exists a variety of interfaces that allow human
users to interact with
computerized systems (mice, keyboards, pens, dials, and touch-sensitive
surfaces).
The main objective of this subject is to elaborate a methodology that
directly senses and decodes
human muscular activity rather than relying on physical device actuation
or user actions that are externally visible or audible.
Advances in muscular sensing and processing technologies provide us with
the unprecedented
opportunity to potentially interface directly with human muscle
activity. Difficulty in sEMG processing
arises from the fact that skin surface electrodes do not record signal
only from individual muscles,
instead some mixture of signals from many muscles is sensed (cross
talk). Moreover, the number of
recorded raw signals is fewer like the number of underlying sources.
Hence, for pattern classification,
a decomposition technique has to be used in sEMG.
The research challenges will concern: (1) the development of an
equipment which must be easy to set up,
to configure and unobtrusive; (2) the hand gesture identification
providing available assessment of sEMG
recordings; and (3) the use of current biomechanical models for
neuromuscular control together with blind
source separation algorithms and some techniques for sEMG signal
decomposition, processing and classification.
Experimental tasks are planed. An approach based on spatial
time-frequency distribution will be applied to s
eparate nonstationnary sEMG signals. After relevant extraction,
classification will be achieved with an
adaptive neural network (SVM)
SALARY
Funding for three years is available from the French Government.
The PhD will be supported by all the resources available in the
GIPSA-Lab laboratory.
Please also send a copy of your CV to franck.quaine@gipsa-lab.inpg.fr.
Closing date 20 Mai 2009.