[Comp-neuro] Postdoctoral fellow in AI, and real time signal processing for Brain Computer Interface clinical application at CEA, Grenoble and Paris-Saclay, France

Tetiana AKSENOVA 218551 tetiana.aksenova at cea.fr
Thu Nov 14 17:03:22 CET 2019


Postdoctoral fellow in AI, and real time signal processing for Brain Computer Interface clinical application
The post-doctoral fellowship will be carried out within the frame of the multidisciplinary project "Brain Computer Interface" (BCI) at CEA-LETI-CLINATEC, Grenoble, France, in collaboration with the Data Intelligence Service from CEA-LIST (Paris-Saclay), France. The goal of the BCI project is the proof of concept that it is possible to control complex effectors thanks to brain activity decoding. Motor BCI raises the hope that limb mobility may be restored for severely motor-impaired patients to regain autonomy, providing them with control over orthosis or prostheses.
The project is based on the recording of neuronal activity at the level of cerebral motor cortex (ElectroCorticoGrams, ECoG) with innovative wireless WIMAGINE® implant dedicated to the long term clinical use. A clinical research protocol « BCI and Tetraplegia » at CLINATEC® includes several tetraplegic subjects and is in progress. In this general frame, the project of partners CEA-LETI-CLINATEC and CEA-LIST "Enabling out-of-laboratory neuroprosthetics for severely motor-impaired patients using artificial intelligence", is supported by Programme Transversal de Compétences « Simulation Numérique » of CEA.
The particular objective of the project is moving toward neuroprosthetics out-of-the-lab applications. This goal entails solving major challenges: increase number of Degrees of Freedom (DoF), improving accuracy and robustness of neural signal decoding to ensure usability of neuroprosthetics for real life tasks from one side, and providing a BCI system for constrained execution environments offered by portable devices from another side. One direction to improve decoding performances is to use recent advances in artificial neural networks. To ensure that the decoding algorithm is compatible with constrained environments, including the restrained CPU and memory costs such that real-time signal processing and decoding remains feasible, various strategies could be investigated.
Missions of post-doctoral fellow will include:
­          The experiment design and set up for real life tasks of using of neuroprosthesis by tetraplegic subject;
­          Design of innovative ANN decoding algorithms, the test and the comparison to conventional methods;
­          Optimization and implementation for real time application, integration to the Clinatec BCI platform;

A unique clinical trial ECoG database supports the project.
Initial contract duration is 12 months with possible prolongation (24 months at max), initial 12 months in CEA / DRT / LETI / CLINATEC, Grenoble and the next ones in CEA / DRT / List / DM2I / SID / LI3A, Saclay.
Profile of candidate: PhD or equivalent with strong knowledge in Machine learning, Deep learning, real time Signal processing (high dimensional data flow), with strong skills in Python, matlab.
Application: The candidates should send a CV, the names of 2 referees, and a cover letter to Dr. Tetiana AKSENOVA, tetiana.aksenova at cea.fr<mailto:tetiana.aksenova at cea.fr>, Dr. Cedric GOUY-PAILLER, cedric.gouy-pailler at cea.fr, and Dr. Pierre BLANCHART, pierre.blanchart at cea.fr. The selected candidates will be interviewed for an expected start in March 2019.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.tnb.ua.ac.be/pipermail/comp-neuro/attachments/20191114/c002701f/attachment.html>


More information about the Comp-neuro mailing list