Workshop 1: Benchmarking BCI classification methods: a hands-on introduction

Organizers
Pedro L. C. Rodrigues, Marco Congedo
GIPSA-lab, Grenoble, France

Sylvain Chevallier
Université de Versailles St-Quentin, Vélizy, France

Date
Pre-conference workshops take place on Monday, September 16, 2019

Location
Stremayrgasse 16 | 8010 Graz | Austria

Registration
via Eventbrite

Abstract
The goal of this workshop is to give a hands-on introduction to the "Mother of All BCI Benchmarks" (MOABB) framework [1]. MOABB offers a solution to the common problem of lack of reproducibility in BCI research and EEG studies in general. Following Open Science guiding principles, MOABB eases the comparison of different classification methods over multiple publicly available datasets and facilitates the diffusion of BCI datasets in the community. MOABB is built on top of major Python libraries for EEG signal processing: MNE-Python, Scikit-Learn and PyRiemann.


The morning session is dedicated to short talks on MOABB and Python EEG processing tools and to setting up participants' laptop with the proper tools. The afternoon is a hands-on session, where participants will write simple scripts in Jupyter notebook to benchmark existing algorithms and will have the opportunity to integrate their own algorithms or datasets in this open ecosystem.

[1] - Vinay Jayaram, Alexandre Barachant, "MOABB: Trustworthy algorithm benchmarking for BCIs" (2018)


Workshop 2: How do we learn to use a BCI? Current state of knowledge, prospects of improvement using an interdisciplinary approach

Organizers
Marie-Constance Corsi, Fabrizio De Vico Fallani
Inria Paris, Aramis project-team, Institut du Cerveau et de la Moelle Epinière

Camille Jeunet
CCLE Lab, Univ. Toulouse / CNRS

Fabien Lotte
Inria Bordeaux Sud-Ouest / LaBRI, Potioc team

Date
Monday, September 16, 2019

Location
Stremayrgasse 16 | 8010 Graz | Austria

Registration
via Eventbrite

Abstract
Despite the extensive work led to improve their reliability and efficiency, Mental-Imagery BCIs (MI-BCI) are still barely used outside laboratories, notably because a large proportion of users seems to be unable to control them reliably enough. Indeed, controlling an MI-BCI requires the acquisition of specific skills, and therefore a proper training. It has been shown that current training procedures are inadequate, and that they should be improved. Nonetheless, the design of relevant training procedures requires a deep understanding of the processes underlying MI-BCI performance and learning - an understanding that remains to be acquired. This workshop aims at bringing together researchers interested in this topic. Notably, studies in psychology, neuroscience or computer science, aiming at modelling MI-BCI performance and learning, will be presented. We will also discuss how we may benefit from an interdisciplinary approach and from the works led by other communities (e.g., in neurofeedback) to improve MI-BCI reliability.

Format
The duration of the satellite will be ~4 hours, which will be split into two parts. The first block will deal with psychological and neurophysiological factors that can influence BCI learning. Another block will be dedicated to computational modelling. There will be 7 talks and two panels discussion.

Panel Discussion
The panel will be formed by the speakers, and discussions will be guided by a selection of pre-arranged questions and questions from the audience.

List of Invited Speakers
Erik Aarnoutse, University Medical Center Utrecht, The Netherlands (confirmed)
Camille Benaroch, Inria, France (confirmed)
Marie-Constance Corsi, Inria-ICM, France (confirmed)
Jason Farquhar, Donders Institute, The Netherlands (confirmed)
Silvia Kober, University of Graz, Austria (confirmed)
Andrea Kübler, University of Wuerzburg, Germany (confirmed)
Guilherme Wood, University of Graz, Austria (confirmed)


Workshop 3: Standards for Neurotechnologies and Brain-Machine Interfacing

Organizers
Ricardo Chavarriaga
École polytechnique fédérale de Lausanne, Switzerland

Date
Monday, September 16, 2019

Location
Stremayrgasse 16 | 8010 Graz | Austria

Registration
via Eventbrite

Abstract
Brain-Machine Interfacing (BMI) is going through a very exciting period where the state-of-the-art in research is moving outside research labs to be tested with its intended users. This translation from research prototypes to viable clinical or consumer solutions entails multiple challenges. Furthermore, the possibility of deploying and commercialising BMI-based solutions requires researchers, manufacturers, and regulatory agencies to ensure these devices comply with well-defined criteria on their safety and effectiveness. In consequence, there is an increased interest on defining appropriate metrics to evaluate their performance and developing good practices and standards for BMI development.

Such endeavor is not trivial and requires all stakeholders to join efforts to identify priority areas that require standardization, and to devise incentives for adopting these standards early on at the development process. This workshop aims at discussing these topics and identify important elements to consider for proper standardisation of both clinical and consumer applications. Participants will also get acquainted with the standards development process and identify way in which this process helps to improve research and accelerate technological transfer.

This workshop is technically sponsored by the IEEE Industry connections group on neurotechnologies and the IEEE Brain Initiative. The workshop will be composed of invited presentations from industry and academia complemented with group discussions and hands-on work. We intend to generate a clear picture of current challenges for standardisation of neurotechnologies and possible strategies to overcome them.

List of Speakers
Carole Carey, IEEE EMB Standards Committee
Luigi Bianchi, U. La Sapienza, Chair Working group  IEEE P2731™
Graeme Moffat (video), Chief Scientist, VP of regulatory affairs, Interaxon
Zach McKinney, Scuola Superiore Sant'Anna Pisa, Chair Working group IEEE P2794™
Emil Hewage, BIOS health inc

Relevant Links
IEEE Industry connections group on neurotechnologies
IEEE Brain Initiative
Working group  IEEE P2731™, Standard for a Unified Terminology for Brain-Computer Interfaces
Working group IEEE P2794™, Reporting Standards for Neural Interface Research
 

Opening Cocktail

Organizers
8th Graz BCI Conference 2019 Organizing Committee

Date
Tuesday, September 17, 2019, evening

Location
Stremayrgasse 16 Rooftop | 8010 Graz | Austria

Registration
Not required (free, included in the conference fee)


BCI Award 2019 Ceremony

Organizers
g.tec medical engineering

Date
Tuesday, September 17, 2017, during the opening cocktail

Location
Stremayrgasse 16 | 8010 Graz | Austria

Registration
Not required (free, included in the conference fee)


BCI Science Slam

Organizers
8th Graz BCI Conference 2019 Organizing Committee

Date
Wednesday, September 18, 2019, 6.30 pm

Location
Petersgasse 16 | 8010 Graz | Austria

Registration
Not required (free, included in the conference fee)