A Generic Framework for Adaptive EEG-Based BCI Training and Operation

Mladenović, Jelena; Mattout, Jérémie; Lotte, Fabien

doi:10.1201/9781351231954-31

Cited by 25 publications

(50 citation statements)

References 59 publications

(81 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The overarching goal is to "influence" the user through optimal machine action in order to fulfill efficiently user's intent. We envision that Active Inference could unify most approaches and paradigms in one adaptive BCI framework, as conceptualized in [25].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Active inference as a unifying, generic and adaptive framework for a P300-based BCI

et al. 2020

Self Cite

View full text Add to dashboard Cite

Objective. Going adaptive is a major challenge for the field of Brain-Computer Interface (BCI). This entails a machine that optimally articulates inference about the user's intentions and its own actions. Adaptation can operate over several dimensions which calls for a generic and flexible framework. Approach. We appeal to one of the most comprehensive computational approach to brain (adaptive) functions: the Active Inference (AI) framework. It entails an explicit (probabilistic) model of the user that the machine interacts with, here involved in a P300-spelling task. This takes the form of a discrete input-output state-space model establishing the link between the machine's (i) observations-a P300 or Error Potential for instance, (ii) representations-of the user intentions to spell or pause, and (iii) actionsto flash, spell or switch-off the application. Main results. Using simulations with real EEG data from 18 subjects, results demonstrate the ability of AI to yield a significant increase in bit rate (17%) over state-of-the-art approaches, such as dynamic stopping. Significance. Thanks to its flexibility, this one model enables to implement optimal (dynamic) stopping but also optimal flashing (i.e. active sampling), automated error correction, and switching off when the user does not look at the screen anymore. Importantly, this approach enables the machine to flexibly arbitrate between all these possible actions. We demonstrate AI as a unifying and generic framework to implement a flexible interaction in a given BCI context.

show abstract

Section: Resultsmentioning

confidence: 99%

“…In this paper, we propose and illustrate an instantiation of the conceptual framework for adaptive BCIs from [25], based on a recent computational model developed in theoretical neuroscience and called Active Inference [26]. It resides on the mentioned perception-action cycles that couple the agent to its environment.…”

Section: A Unifying Frameworkmentioning

confidence: 99%

Active inference as a unifying, generic and adaptive framework for a P300-based BCI

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…First, it suggests that several relevant factors ought perhaps to be considered in order to improve of the clinical efficacy of NF. Second, as we are able to measure some of these factors (using questionnaires or neurophysiological measures) training procedures could be adapted accordingly (Mladenovic et al, 2018).…”

Section: Resultsmentioning

confidence: 99%

Using Recent BCI Literature to Deepen our Understanding of Clinical Neurofeedback: A Short Review

et al. 2018

Self Cite

View full text Add to dashboard Cite

In their recent paper, Alkoby et al. (2017) provide the readership with an extensive and very insightful review of the factors influencing NeuroFeedback (NF) performance. These factors are drawn from both the NF literature and the Brain-Computer Interface (BCI) literature. Our short review aims to complement Alkoby et al.'s review by reporting recent additions to the BCI literature. The object of this paper is to highlight this literature and discuss its potential relevance and usefulness to better understand the processes underlying NF and further improve the design of clinical trials assessing NF efficacy. Indeed, we are convinced that while NF and BCI are fundamentally different in many ways, both the BCI and NF communities could reach compelling achievements by building upon one another. By reviewing the recent BCI literature, we identified three types of factors that influence BCI performance: task-specific, cognitive/motivational and technology-acceptance-related factors. Since BCIs and NF share a common goal (i.e., learning to modulate specific neurophysiological patterns), similar cognitive and neurophysiological processes are likely to be involved during the training process. Thus, the literature on BCI training may help (1) to deepen our understanding of neurofeedback training processes and (2) to understand the variables that influence the clinical efficacy of NF. This may help to properly assess and/or control the influence of these variables during randomized controlled trials.

show abstract

“…As such, to reach optimal performances, it is worth considering adaptive signal processing algorithms, whose parameters are dynamically changed and optimized during online use (Shenoy et al, 2006). There are a number of variants of the above mentioned algorithms that were thus designed so as to optimize online, in an incremental way, the spectral filters, spatial filters, features and classifiers, as new EEG data become available (see (Mladenovic et al, 2017, in press) for a review). While most of these algorithms remain to be tested in ecological conditions outside laboratories, they seem promising to deal with EEG fluctuations due to variation in context, noise and recording conditions that are typically encountered in real-life applications.…”

Section: Adaptationmentioning

confidence: 99%

Brain–Computer Interface Contributions to Neuroergonomics

Lotte

Roy

2019

Neuroergonomics

Self Cite

View full text Add to dashboard Cite

Brain-Computer Interfaces (BCIs) are systems that can translate brain activity patterns into messages or commands for an interactive application. As such the technology used to design them, and in particular to design passive BCIs which are a new means to perform mental state monitoring, can greatly benefit the neuroergonomics field. Therefore, this chapter describes the classical structure of the brain signal processing chain employed in BCIs, notably presenting the typically used preprocessing (spatial and spectral filtering, artefact removal), feature extraction and classification algorithms. It also gives examples of the use of BCI technology for neuroergonomics applications, either offline for evaluation purposes (e.g. cockpit design or stereoscopic displays' assessment), or online for adaptation purposes (e.g. video game difficulty level or air traffic controller display adaptation).

show abstract

A Generic Framework for Adaptive EEG-Based BCI Training and Operation

Cited by 25 publications

References 59 publications

Active inference as a unifying, generic and adaptive framework for a P300-based BCI

Active inference as a unifying, generic and adaptive framework for a P300-based BCI

Using Recent BCI Literature to Deepen our Understanding of Clinical Neurofeedback: A Short Review

Brain–Computer Interface Contributions to Neuroergonomics

Contact Info

Product

Resources

About