[Eeglablist] Postdoc in Machine Learning Methods for Real-Time Artefact Rejection in EEG Data

[Tobias Andersen]

The Technical University of Denmark invites applicants for a two-year Postdoc position in machine learning for artifact classification in EEG data. The position should be filled by 1 December, but the needs of the candidate will be taken into account in this regard.

Around 50 million people worldwide have epilepsy and ~80% live in low and middle-income countries (LMICs). An electroencephalogram (EEG) is the gold standard to confirm epilepsy diagnosis; however many LMIC regions have no access to such tool, so 75% of their patients are not treated. Current EEG devices cannot serve this market due to high costs, lack of specialists and stable grid power. We want to build EEG services tailored to the needs and available resources in LMICs by developing inexpensive mobile-based EEG equipment and AI enhanced epilepsy tele-neurodiagnostic services for use by inexperienced EEG operators.

The quality of EEG recordings is influenced by several factors: the quality of the recording device, the impedance between the electrode and the scalp and non-neural artefactual signal components caused mainly by eye-movements, eye-blinks and contraction of head muscles. The occurrence of these non-neural artefacts is difficult to estimate online especially for an inexperienced operator and requires continuous monitoring of the recorded signal. In order to aid the inexperienced operator, we will develop an online, near real-time quality control (QC) algorithm based on our previous work. The QC algorithm will feed into a front end that supplies the operator with the magnitude of each type of artefact and, importantly, whether the amount is critical for the quality of the data.

Responsibilities and tasks
Your role in the project is to develop, implement and test the QC algorithm. The development will take into account that the QC algorithm will be implemented on an inexpensive platform with limited processing power. The implementation should consist of well-organised and documented code that can be used by the other partners in the project. Testing the algorithm will include technical tests as well as user tests with inexperienced EEG operators.

The project is funded by the Eurostars program and you will join a collaborative effort between DTU Compute, The Epilepsy Hospital Filadelfia (https://urldefense.com/v3/__http://www.filadelfia.dk/en__;!!Mih3wA!R-MoeQ1rznewrCn8K0SioOhRR4snCvSQpu7m8Supv_ppLCjviQi-xhzWyracfkDd-9b1tA$ ) as well as two private companies, Brain Capture (https://urldefense.com/v3/__https://braincapture.dk/__;!!Mih3wA!R-MoeQ1rznewrCn8K0SioOhRR4snCvSQpu7m8Supv_ppLCjviQi-xhzWyracfkBD6UBRZA$ ) and Epilog (https://urldefense.com/v3/__https://www.epilog.care/__;!!Mih3wA!R-MoeQ1rznewrCn8K0SioOhRR4snCvSQpu7m8Supv_ppLCjviQi-xhzWyracfkBlJFS95g$ ).

Qualifications
The right candidate will have a PhD degree, submitted a PhD thesis for defence or equivalent.
Programming experience and experience with applied machine learning are essential qualifications. Experience in working with EEG data and user tests will also be useful but these skills can be acquired during the project.
It is important that your are interested in working at the interface between applied technical science and business development. It is also important that you are motivated by the idea of using applied machine learning to make a difference in the health care available to people living in low and middle income countries.

Salary and terms of employment
The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. The allowance will be agreed upon with the relevant union. The period of employment is 18 months.
You can read more about career paths at DTU here<https://urldefense.com/v3/__http://www.dtu.dk/english/about/job-and-career/working-at-dtu/career-paths__;!!Mih3wA!R-MoeQ1rznewrCn8K0SioOhRR4snCvSQpu7m8Supv_ppLCjviQi-xhzWyracfkDCyapZCw$ >.

Application procedure
To apply, please read the full job advertisement at https://urldefense.com/v3/__http://www.career.dtu.dk__;!!Mih3wA!R-MoeQ1rznewrCn8K0SioOhRR4snCvSQpu7m8Supv_ppLCjviQi-xhzWyracfkBjmlucBQ$ <https://urldefense.com/v3/__http://www.career.dtu.dk/__;!!Mih3wA!R-MoeQ1rznewrCn8K0SioOhRR4snCvSQpu7m8Supv_ppLCjviQi-xhzWyracfkBa8zlTAQ$ >
Application deadline: 15 November 2020.

Further information
Further information may be obtained from Associate Professor Tobias Andersen, toban at dtu.dk<mailto:toban at dtu.dk>