PhD position on Machine Learning for Gait Analysis
Looking for an excellent PhD candidate to work on the development of new machine learning methods for the modelling of pathological gait to better understand gait deviations and contribute to improve treatment strategies. Apply by July 10.
At: U. Geneva and HUG-GE
Location: Geneva, Switzerland
We are looking for an excellent candidate who will undertake a PhD on the development of new machine learning methods for the modelling of pathological gait to better understand gait deviations and contribute to improve treatment strategies.
The PhD position is part of an interdisciplinary project, funded by the Swiss National Science Foundation (SNSF), which brings together two research teams in biomechanics (Willy Taillard Laboratory of Kinesiology, Medicine Faculty, University of Geneva, headed by Dr Stephane Armand) and machine learning and data mining, (University of applied sciences-Western Switzerland, headed by Prof. Alexandros Kalousis).
The position is funded for three years, with a possibility of extension for one more year. Salary is currently at 45'000CHF for the first year (the standard funding rate SNSF for doctorate students). There will be a possibility to complete the above amount.
The successful candidate will work with patient data as well as with data collected in the context of the project. Large amount of simulated pathological gait on healthy individuals will be collected where different movement constraints are controlled in a systematic manner. He or she will have to develop new learning methods tailored to the spatio-temporal nature of the gait data. One of the immediate research goals is given patient descriptors to predict their gait profile. A number of challenges need to be addressed, such as, the highly structured nature of the data, namely their spatio-temporal dependencies, their high dimensionality, their high variability, both within as well as between subjects. In addition the developed methods should be able to exploit in a meaningful manner the available data, both from the existing patient database as well as those collected from the simulations. We will also seek to develop methods that will guide the simulation experiments focusing on these parts of the data space that are expected to bring the largest improvements in the modelling and learning process.
The ideal candidate will have:
- A very solid background in a combination of mathematics and computer science. Special areas of interest include: statistics, mathematical optimization, mathematical modelling.
- He or she should have completed, or about to complete, an MSc in the above areas.
- A very good understanding of machine learning methods and algorithms; project experience in the area will be a considerable plus.
- Solid expertise in at least one of Matlab or R.
- Strong programming skills in scripting languages, such as perl, python, etc.
- Fluency in English.
- Team work capacity.
- Experiences or interest in the area of biomechanics will be a plus.
Research in the machine learning and data mining lab explores different issues such as: learning in high dimensional settings, dimensionality reduction and feature selection; learning with structured data (multiple kernel learning); metric learning; the exploitation of domain knowledge in the learning process. For a more detailed description the interested candidates may take a look at: cui.unige.ch/~kalousis/
This project will be applied in the field of biomechanics and more specifically in clinical gait analysis.
More information could be found on the cinesiologie.hug-ge.ch/
Candidates should send:
- A two page CV.
- A one page motivation letter explaining why their skills, knowledge and experience make them a particularly suitable candidate for the given position.
- A 500 words research proposal on the project's topic.
- The names and contact details of three referees.
Priority will be given to applications send by the 10nth of July 2013, however applications will be accepted until the position is filled.
The position will be available from the 1st of September 2013 with a possibility for a later start if necessary.