Detecting error-related negativity for interaction design

@article{Vi2012DetectingEN,
  title={Detecting error-related negativity for interaction design},
  author={Chi Thanh Vi and Sriram Subramanian},
  journal={Proceedings of the SIGCHI Conference on Human Factors in Computing Systems},
  year={2012}
}
  • C. Vi, S. Subramanian
  • Published 5 May 2012
  • Computer Science
  • Proceedings of the SIGCHI Conference on Human Factors in Computing Systems
This paper examines the ability to detect a characteristic brain potential called the Error-Related Negativity (ERN) using off-the-shelf headsets and explores its applicability to HCI. ERN is triggered when a user either makes a mistake or the application behaves differently from their expectation. We first show that ERN can be seen on signals captured by EEG headsets like Emotiv™ when doing a typical multiple choice reaction time (RT) task -- Flanker task. We then present a single-trial online… 
Error related negativity in observing interactive tasks
TLDR
The results show that online single trial detection is possible using both headsets during tasks that are typical of collaborative interactive applications, however there is a trade-off between the detection speed and the quality/prices of the headsets.
Detection of error-related negativity in complex visual stimuli: a new neuroergonomic arrow in the practitioner’s quiver
TLDR
For the first time, error-related negativity (ERN) has been successfully elicited and detected in a visually complex applied search task and results show that the ERN can be successfully eliciting and detecting in visual search of complex static images, opening the door to applied neuroergonomic use.
Subject- and task-independent neural correlates and prediction of decision confidence in perceptual decision making
TLDR
The results suggest that confidence in perceptual decision making tasks could be reconstructed from neural signals even when using transfer learning approaches, and are based on the decision-making process rather than just the confidence-reporting process.
Reliable subject-adapted recognition of EEG error potentials using limited calibration data
TLDR
A system for the recognition of error potentials from single-trial Electroencephalography (EEG) is investigated, with the focus here is the development of a system using only limited calibration data from the test subject, while exploiting available training data from other subjects.
Investigating the Emotiv EPOC for cognitive control in limited training time
TLDR
Two studies investigating cognitive control with the Emotiv EPOC are ran, including analysis of detection filters for maximising cognitive control, and the Affectiv suite is reviewed and how to analyse the user’s emotional measurements it provides.
Brain signal-based safety measure activation for robotic systems
TLDR
It is demonstrated that it is possible to send an emergency stop action during mobile navigation task when unexpected events occur with an accuracy of 75% and the probability of failure in demand is derived.
Toward Interfaces that Help Users Identify Misinformation Online: Using fNIRS to Measure Suspicion
TLDR
A convolutional long short-term memory classifier that predicts suspicion using a leave-one-participant-out cross-validation scheme, with average accuracy greater than 76%, and the brain regions implicated by the results dovetail with prior theoretical definitions of suspicion.
Design and Evaluation of a Self-Correcting Gesture Interface based on Error Potentials from EEG
TLDR
It is shown that self-correction significantly improves gesture recognition accuracy at lower costs and with higher acceptance than manual correction.
Adding Human Learning in Brain--Computer Interfaces (BCIs)
TLDR
This article introduces CLBCI (Co-Learning for Brain--Computer Interfaces), a BCI architecture based on co-learning in which users can give explicit feedback to the system rather than just receiving feedback and proposes a new scheme for real-time two-dimensional visualization of classification outcomes using Wachspress coordinate interpolation.
Brain Machine Interface System Automation Considering User Preferences and Error Perception Feedback
TLDR
Experimental evidence is provided that demonstrates the effectiveness of the methodologies to design and build hardware and software interfaces, acquire and process brain signals, and train the system using machine learning techniques that gradually become autonomous.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 33 REFERENCES
Performance monitoring in a confusing world: error-related brain activity, judgments of response accuracy, and types of errors.
TLDR
Irrespective of behavioral accuracy, the amplitude of the ERN covaried with the perceived inaccuracy of the behavior, and this results are consistent with the proposal that performance monitoring, as manifested by the ERNs, involves a comparison between representations of the appropriate response and the response actually made.
Brain Errormonitoring Activity is Affected by Semantic Relatedness: An Event-related Brain Potentials Study
TLDR
It is found that the ERN was largest following errors that occurred after semantically related distractors had been presented, as compared to semantically unrelated ones, suggesting that the functioning of the verbal self-monitoring system during speaking is comparable to other performance monitoring, such as action monitoring.
Online Detection of P300 and Error Potentials in a BCI Speller
TLDR
This work implemented a P300-based BCI speller that uses a genetic algorithm (GA) to detect P300s, and added an automatic error-correction system (ECS) based on the single-sweep detection of ErrPs.
The neural basis of error detection: conflict monitoring and the error-related negativity.
TLDR
It is concluded that the ERN can be explained in terms of response conflict and that monitoring for conflict may provide a simple mechanism for detecting errors.
Event-Related Brain Potentials Following Incorrect Feedback in a Time-Estimation Task: Evidence for a Generic Neural System for Error Detection
TLDR
The error-related negativity is the manifestation of the activity of a generic neural system involved in error detection, and the distribution of the scalp potential was consistent with a local source in the anterior cingulate cortex or a more distributed sources in the supplementary motor areas.
You Are Wrong! - Automatic Detection of Interaction Errors from Brain Waves
TLDR
Experimental results with three volunteer subjects during a simple human-robot interaction are reported that seem to reveal a new kind of ErrP, which is satisfactorily recognized in single trials, which significantly improve the performance of the brain interface.
Using a low-cost electroencephalograph for task classification in HCI research
TLDR
An initial step in exploring how off-the-shelf electroencephalograph technologies may be used to perform task classification and applied in a relevant manner to HCI research is presented.
Talking off the top of your head: toward a mental prosthesis utilizing event-related brain potentials.
Brain measurement for usability testing and adaptive interfaces: an example of uncovering syntactic workload with functional near infrared spectroscopy
TLDR
An experiment protocol is presented that can be used to measure the workload experienced by users in their various cognitive resources while working with a computer and functional near infrared spectroscopy is used, a new brain imaging technology that is beginning to be used in HCI.
The Impact of Cognitive Deficits on Conflict Monitoring
TLDR
The present research demonstrates that the conflict-monitoring theory can account for these dissociations in terms of the dissociable effects of alcohol and ACC lesions on processing of relevant stimulus information and processing of irrelevant, distracting information.
...
1
2
3
4
...