Postdoctoral Researcher: Brain Computer Interfacing for ALS Patients
Radboud University - Faculty of Social Sciences
We are looking for a postdoctoral researcher with a strong background in signal processing and machine learning, evidenced by a PhD degree in this domain. The field in which you obtained your Master’s degree should preferably be one of the engineering sciences or neuroscience. You must be able to work in a highly multidisciplinary team, being able to communicate not only with BCI experts, but also with commercial and medical partners. Furthermore, you must be able to manage your own project and at the same time contribute to the supervision of, for example, PhD students.
BCIs have been around for quite some time, but until now the full potential of the technology has not been realised due to poor information transfer rates, long training times, and inconvenient hardware. The Noise Tag BCI recently developed by our team overcomes these problems: there is no training required, fewer and dry electrodes (meaning a trendy ’wearable’ EEG cap) can be used, the method has robustness (e.g. against movement) and high accuracy. This patented technology is based on broadband evoked potentials and has already been used successfully when in 2016 the team won the assistive technology challenge at the Dublin symposium for ALS. The primary application of the technology will be for patients with locked-in syndrome, such as those in late stages of ALS, where the lack of means to communicate is a serious problem. The BCI technology has huge potential to improve their quality of life by restoring communication and interaction with their environment.
You will be responsible for the integration of various methods and their optimisation, delivering a clean and clear MATLAB prototype that will be turned into production code.
What we expect from you
- you have a strong background in signal processing and machine learning in the context of electrophysiological (EEG) data;
- you have preferably experience with and knowledge of canonical correlation analysis, reconvolution, and template matching classification;
- you have experience with developing and debugging MATLAB code and are able to write and elaborate clean and well-documented modular programs;
- you have worked on online, real-time processing projects with data streaming;
- you are able to formalise methods mathematically and to communicate them in a clear way, as demonstrated by first-authored articles;
- you can bridge the distance between fundamental concepts and theories, on the one hand, and practical implementation and evaluation of these concepts, on the other;
- you can think out of the box, distinguish main lines from details, and provide structure to your work;
- you have excellent multidisciplinary team working and communication skills;
- you have some expertise in other programming languages (e.g. C, Python, Java) and platforms (Unity, IOS).