What’s wrong with us? Roadblocks and pitfalls in designing BCI applications
A half-day wokshop at the
Put yourself in the spotlight!! We’ll allocate time for selected presenters to briefly expose their ideas (3 min, one slide). Thought-provoking, controversial points are more than welcome. If you’re interested write us an email.
Research in brain-computer interfaces has achieved impressive progress towards implementing assistive technologies for restoration or substitution of lost motor capabilities, as well a supporting technologies for able-bodied subjects. Notwithstanding this progress, effective translation of these interfaces from proof-of concept prototypes into reliable applications remains elusive. As a matter of fact, current systems cannot be used independently for long periods of time by their intended end-users.
Multiple factors that impair achieving this goal have already been identified. However, it is not clear how do they affect the overall BCI performance or how should they be tackled. This is worsened by the publication bias where only positive results are disseminated, preventing the research community of learning from its errors. This workshop is intended as a space to discuss these limiting factors. In particular we will encourage researchers to share their attempts to overcome them, even those that have failed.
The workshop will be composed of several invited presentations (15 min) plus short spotlight presentations (3 min) from the attendance, complemented with plenty of time for discussions. We intend as outcome to have a set of guidelines of concrete research avenues that may take BCIs closer to real applications, usable by their intended end-users.
Examples of Roadblocks and Pitfalls:
- On the one hand, user-requirements are barely taken into account in the design. On the other hand, subject-specific tailoring of the system may require a large amount of resources, limiting the possibility of successful transfer into marketable applications.
- Design and evaluation of BCI system go beyond the decoding of neural signals and should take into account all components of the brain-machine interactions. Including, but not limited to feedback, human factors, learning strategies, etc.
- Real application environments are much noisier, dynamic and much more stimulating for the user, leading to drastic changes in EEG signals as compared to lab environment or BCI calibration environments. This makes many lab-based BCI fail in real-life contexts.
- The human is often considered as a static, compliant entity that always perform what the experimenter wants in a precise, consistent way. In reality, subject’s behaviour is determined by his/her understanding of the task, abilities, motivation, etc.
- There is a lack of clear metrics to assess the effective performance of a BCI system. It is generally acknowledged that these metrics should comprise both machine and human factors altogether (e.g. decoding accuracy and usability), but it is not clear how to weight them.
- Experimental work is performed in small populations, limiting the possibility of drawing conclusions that can be applied to a large population Control subjects -typically graduate students- don’t match the intended user population
- The highly multidisciplinary nature of BCI research makes it very difficult for researchers in the field to know enough of each discipline involved to avoid all methodological flaws associated to each of them (e.g., statistical flaws or protocol design with confounding factors). This leads to a number of BCI publications with biases, confounding factors, and contradictory results which may slow down progress in the field.
The workshop is aimed at both novice and experienced researchers on BMI, as well as researchers in cognitive neuroscience and psychology.
Participant are kindly asked to provide us by mail a short description (1 slide) about his/her research and up to 3 major points he/she wants to see addressed in this workshop beforehand. Selected contributions will be presented during the workshop as spotlights to trigger targeted discussion among participants.
- Daly, I. et al. On the control of brain-computer interfaces by users with cerebral palsy. Clin Neurophysiol, 2013, 124, 1787-1797
- Kübler, A. et al. The user-centered design as novel perspective for evaluating the usability of BCI-controlled applications. PLoS One, 2014, 9, e112392
- Lotte,F. et al., C. Flaws in current human training protocols for spontaneous Brain-Computer Interfaces: lessons learned from instructional design. Front Hum Neurosci, 2013, 7, 568