Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework

Samuel W. Hincks, Sarah Bratt, Sujit Poudel, Vir Phoha, Robert J.K. Jacob, Daniel C. Dennett, Leanne M Hirshfield

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Implicit Brain-Computer Interfaces (BCI) adapt system settings subtly based on real time measures of brain activation without the user's explicit awareness. For example, measures of the user's cognitive profile might drive a system that alters the timing of notifications in order to minimize user interruption. Here, we consider new avenues for implicit BCI based on recent discoveries in cognitive neuroscience and conduct a series of experiments using BCI's principal non-invasive brain sensors, fNIRS and EEG. We show how Bayesian and systems neuroscience formulations explain the difference in performance of machine learning algorithms trained on brain data in different conditions. These new formulations posit that the brain aims to minimize its long-term surprisal of sensory data and organizes its calculations on two anti-correlated networks. We consider how to use real-time input that portrays a user along these dimensions in designing Bidirectional BCIs, which are Implicit BCIs that aim to optimize the user's state by modulating computer output based on feedback from a brain monitor. We introduce Entropic Brain-Computer Interfacing as a type of Bidirectional BCI which uses physiological measurements of information theoretical dimensions of the user's state to evaluate the digital flow of information to the user's brain, tweaking this output in a feedback loop to the user's benefit.

Original languageEnglish (US)
Title of host publicationPhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems
PublisherSciTePress
Pages23-34
Number of pages12
ISBN (Electronic)9789897582684
StatePublished - 2017
Event4th International Conference on Physiological Computing Systems, PhyCS 2017 - Madrid, Spain
Duration: Jul 27 2017Jul 28 2017

Other

Other4th International Conference on Physiological Computing Systems, PhyCS 2017
CountrySpain
CityMadrid
Period7/27/177/28/17

Fingerprint

Brain computer interface
Electroencephalography
Brain
Computer monitors
Feedback
Learning algorithms
Learning systems
Chemical activation
Sensors

Keywords

  • ADHD
  • Attention
  • BCI
  • Bidirectional brain-computer interface
  • Brain-computer interface
  • Default mode network
  • EEG
  • Entropic brain-computer interface
  • Entropy
  • FNIRS
  • Implicit interface
  • Meditation
  • Physiological computing
  • Task-positive network
  • Workload

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Science Applications

Cite this

Hincks, S. W., Bratt, S., Poudel, S., Phoha, V., Jacob, R. J. K., Dennett, D. C., & Hirshfield, L. M. (2017). Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework. In PhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems (pp. 23-34). SciTePress.

Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework. / Hincks, Samuel W.; Bratt, Sarah; Poudel, Sujit; Phoha, Vir; Jacob, Robert J.K.; Dennett, Daniel C.; Hirshfield, Leanne M.

PhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems. SciTePress, 2017. p. 23-34.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hincks, SW, Bratt, S, Poudel, S, Phoha, V, Jacob, RJK, Dennett, DC & Hirshfield, LM 2017, Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework. in PhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems. SciTePress, pp. 23-34, 4th International Conference on Physiological Computing Systems, PhyCS 2017, Madrid, Spain, 7/27/17.
Hincks SW, Bratt S, Poudel S, Phoha V, Jacob RJK, Dennett DC et al. Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework. In PhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems. SciTePress. 2017. p. 23-34
Hincks, Samuel W. ; Bratt, Sarah ; Poudel, Sujit ; Phoha, Vir ; Jacob, Robert J.K. ; Dennett, Daniel C. ; Hirshfield, Leanne M. / Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework. PhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems. SciTePress, 2017. pp. 23-34
@inproceedings{823b0c5ebdef4a96841162f77a62b3cd,
title = "Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework",
abstract = "Implicit Brain-Computer Interfaces (BCI) adapt system settings subtly based on real time measures of brain activation without the user's explicit awareness. For example, measures of the user's cognitive profile might drive a system that alters the timing of notifications in order to minimize user interruption. Here, we consider new avenues for implicit BCI based on recent discoveries in cognitive neuroscience and conduct a series of experiments using BCI's principal non-invasive brain sensors, fNIRS and EEG. We show how Bayesian and systems neuroscience formulations explain the difference in performance of machine learning algorithms trained on brain data in different conditions. These new formulations posit that the brain aims to minimize its long-term surprisal of sensory data and organizes its calculations on two anti-correlated networks. We consider how to use real-time input that portrays a user along these dimensions in designing Bidirectional BCIs, which are Implicit BCIs that aim to optimize the user's state by modulating computer output based on feedback from a brain monitor. We introduce Entropic Brain-Computer Interfacing as a type of Bidirectional BCI which uses physiological measurements of information theoretical dimensions of the user's state to evaluate the digital flow of information to the user's brain, tweaking this output in a feedback loop to the user's benefit.",
keywords = "ADHD, Attention, BCI, Bidirectional brain-computer interface, Brain-computer interface, Default mode network, EEG, Entropic brain-computer interface, Entropy, FNIRS, Implicit interface, Meditation, Physiological computing, Task-positive network, Workload",
author = "Hincks, {Samuel W.} and Sarah Bratt and Sujit Poudel and Vir Phoha and Jacob, {Robert J.K.} and Dennett, {Daniel C.} and Hirshfield, {Leanne M}",
year = "2017",
language = "English (US)",
pages = "23--34",
booktitle = "PhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems",
publisher = "SciTePress",

}

TY - GEN

T1 - Entropic brain-computer interfaces using fNIRS & EEG to measure attentional states in a Bayesian framework

AU - Hincks, Samuel W.

AU - Bratt, Sarah

AU - Poudel, Sujit

AU - Phoha, Vir

AU - Jacob, Robert J.K.

AU - Dennett, Daniel C.

AU - Hirshfield, Leanne M

PY - 2017

Y1 - 2017

N2 - Implicit Brain-Computer Interfaces (BCI) adapt system settings subtly based on real time measures of brain activation without the user's explicit awareness. For example, measures of the user's cognitive profile might drive a system that alters the timing of notifications in order to minimize user interruption. Here, we consider new avenues for implicit BCI based on recent discoveries in cognitive neuroscience and conduct a series of experiments using BCI's principal non-invasive brain sensors, fNIRS and EEG. We show how Bayesian and systems neuroscience formulations explain the difference in performance of machine learning algorithms trained on brain data in different conditions. These new formulations posit that the brain aims to minimize its long-term surprisal of sensory data and organizes its calculations on two anti-correlated networks. We consider how to use real-time input that portrays a user along these dimensions in designing Bidirectional BCIs, which are Implicit BCIs that aim to optimize the user's state by modulating computer output based on feedback from a brain monitor. We introduce Entropic Brain-Computer Interfacing as a type of Bidirectional BCI which uses physiological measurements of information theoretical dimensions of the user's state to evaluate the digital flow of information to the user's brain, tweaking this output in a feedback loop to the user's benefit.

AB - Implicit Brain-Computer Interfaces (BCI) adapt system settings subtly based on real time measures of brain activation without the user's explicit awareness. For example, measures of the user's cognitive profile might drive a system that alters the timing of notifications in order to minimize user interruption. Here, we consider new avenues for implicit BCI based on recent discoveries in cognitive neuroscience and conduct a series of experiments using BCI's principal non-invasive brain sensors, fNIRS and EEG. We show how Bayesian and systems neuroscience formulations explain the difference in performance of machine learning algorithms trained on brain data in different conditions. These new formulations posit that the brain aims to minimize its long-term surprisal of sensory data and organizes its calculations on two anti-correlated networks. We consider how to use real-time input that portrays a user along these dimensions in designing Bidirectional BCIs, which are Implicit BCIs that aim to optimize the user's state by modulating computer output based on feedback from a brain monitor. We introduce Entropic Brain-Computer Interfacing as a type of Bidirectional BCI which uses physiological measurements of information theoretical dimensions of the user's state to evaluate the digital flow of information to the user's brain, tweaking this output in a feedback loop to the user's benefit.

KW - ADHD

KW - Attention

KW - BCI

KW - Bidirectional brain-computer interface

KW - Brain-computer interface

KW - Default mode network

KW - EEG

KW - Entropic brain-computer interface

KW - Entropy

KW - FNIRS

KW - Implicit interface

KW - Meditation

KW - Physiological computing

KW - Task-positive network

KW - Workload

UR - http://www.scopus.com/inward/record.url?scp=85029364660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029364660&partnerID=8YFLogxK

M3 - Conference contribution

SP - 23

EP - 34

BT - PhyCS 2017 - Proceedings of the 4th International Conference on Physiological Computing Systems

PB - SciTePress

ER -