Postdoc Position in Amsterdam, The Netherlands
on
Evolutionary Machine Learning to Enable Robot Buddies to Recognize Emotions of
Childhood Cancer Patients
http://www.cwi.nl/jobs/postdoc-evolutionary-machine-learning-enable-robot-buddies-recognize-emotions-of-childhood-canc
Description
-----------
Children treated for cancer in a hospital often experience high levels of stress
and anxiety. Not only are they faced with a life-threatening disease, they also
find themselves in a strange environment, surrounded by doctors, nurses and
other medical personnel. Moreover, during various types of treatment, close
family may not be in close proximity, e.g., due to exposure risks in case of
radiation treatment, or simply because parents cannot guarantee 24/7 presence.
CWI has a position for a postdoc in a recently acquired project that unites and
advances the state-of-the-art in automated human-robot interaction design and
machine learning to provide children with a humanoid robot companion in the form
of a NAO robot that is capable of being there when humans cannot and that can
address a child’s distress, pain and fear to minimize medical traumatic stress.
This is of key importance, e.g., to ensure successful, uneventful treatment, to
lower risks associated with involving relatives and clinicians (e.g., radiation
exposure), and to reduce significant adverse psychological reactions (e.g.,
post-traumatic stress) to the entire experience.
The focus of this postdoc position is on perception by use of computational
intelligence (and signal processing) techniques to transform basic sensor input
(i.e., audio- and video feeds) into higher-order knowledge to be processed by
the cognitive-affective control architecture. To ensure sufficiently reliable
signal input for accurate real-world machine-perception, we will use external
sensors of a higher quality than those on the NAO robot, such as high-quality,
reliable cameras and (directional) microphones. Furthermore, perception and
cognition will be done on a separate, modern computer. The goal of this project
is to equip the software platform that controls the NAO robot buddies with three
forms of perception: speech recognition, face recognition, and emotion
recognition. Especially the latter category is of importance to this project. To
this end, novel machine learning methods are to be developed by combining the
state of the art in different fields of computational intelligence, especially
evolutionary computation and machine learning, in order to be able to recognize
a set of emotions, in real time.
This project concerns not only fundamental and innovative research, but also a
real-world application as this research will be brought into real-world practice
already during the project by having NAO robots interact with children that are
being treated at the Academic Medical Center (AMC) pediatric oncology department
and the Princes Máxima Center (PMC) for pediatric oncology.
This postdoc position is available within the project titled “Improving
Childhood Cancer Care when Parents Cannot be There – Reducing Medical Traumatic
Stress in Childhood Cancer Patients by Bonding with a Robot Companion”, funded
by STW, KWF, and TKI. This project is a collaboration between 4 academic
partners: the CWI, Delft University of Technology, the Academic Medical Center
(AMC), and the Princess Máxima Center for Pediatric Oncology (PMC), and 4
industry partners: ASolutions, Cancer Health Coach, Mediq Apotheken, and Focal
Meditech. The appointment of the postdoc in this vacancy position will be at CWI
and he/she will be at various locations of project partners on average one day a
week (predominantly AMC). The research team includes in total 2 Ph.D.-students
and a postdoc and is coached by senior researchers from CWI, TU Delft, AMC, and
PMC.
Requirements
------------
Candidates are required to have a Ph.D. degree in computer science, artificial
intelligence, mathematics, physics, or similar areas with relevant experience.
If you are obtaining your Ph.D. degree before March 1, 2017, you are also
invited to respond. Applicants are moreover required to have substantial
programming skills, including excellent knowledge of at least one of the
following programming languages: C, C++, Java (C/C++ highly desired), and are
expected to have an excellent command of English. Candidates that additionally
have previous experience with programming robot platforms (in particular the NAO
platform) will be preferred.
It is essential that you have a clear interest in working both on fundamental
research as well as on applying this research, in collaboration with academic
partners and company partners. Candidates should be willing to cooperate with
experts across different disciplines (including computer science, medicine, and
psychology).
Terms and conditions
--------------------
The terms of employment are in accordance with the Dutch Collective Labour
Agreement for Research Centres ("CAO-onderzoeksinstellingen"). The gross monthly
salary for an employee on a full time basis, depending on relevant work
experience, ranges from € 3,355 to € 4,772. The appointment will be for a period
of 24 months.
Employees are also entitled to a holiday allowance of 8% of the gross annual
salary and a year-end bonus of 8.33%. CWI offers attractive working conditions,
including flexible scheduling.
Please visit our website for more information about our terms of employment:
www.cwi.nl/terms-of-employment
Application & Information:
--------------------------
Applications can be sent before 1 January 2017. To apply,
please visit this link:
http://www.cwi.nl/jobs/postdoc-evolutionary-machine-learning-enable-robot-buddies-recognize-emotions-of-childhood-canc
Applications MUST include
1) a motivation letter,
2) a detailed resume, and
3) a list of B.Sc. and M.Sc. grades.
For residents outside the EER-area, a Toefl English language test might be
required.
For more information about the vacancy, please contact dr. Peter A.N. Bosman,
email [log in to unmask],
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Dr. Peter A.N. Bosman
Senior Researcher
Centrum Wiskunde & Informatica (CWI)
(Centre for Mathematics and Computer Science)
P.O. Box 94079
1090 GB Amsterdam
The Netherlands
[log in to unmask]
http://homepages.cwi.nl/~bosman
-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
|