Toward improving the visual stimulus meaning for increasing the P300 detection
December 12, 2016 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Hubert Cecotti, Bertrand Rivet
arXiv ID
1612.03640
Category
cs.HC: Human-Computer Interaction
Cross-listed
q-bio.NC
Citations
0
Venue
arXiv.org
Last Checked
5 months ago
Abstract
The P300 speller is a well known Brain-Computer Interface paradigm that has been used for over two decades. A new P300 speller paradigm (XP300) is proposed. It includes several characteristics: (i) the items are not intensified by using rows and columns, (ii) the order of the visual stimuli is pseudo-random, (iii) a visual feedback is added on each item to increase the stimulus meaning, which is the main novelty. XP300 has been tested on ten healthy subjects on copy spelling mode, with only eight sensors. It has been compared with the classical P300 paradigm (CP300). With five repetitions, the average recognition rate across subjects is 85.25% for XP300 and 77.25% for CP300. Single-trial detection is significantly higher with XP300 by comparing the AUC (Area Under Curve) of the ROC (Receiver Operating Characteristic) curve. The mean AUC is 0.86 for XP300, 0.80 for CP300. More importantly, XP300 has also been judged as more convenient and user-friendly than CP300, hence being able to allow longer sessions.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Human-Computer Interaction
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Improving fairness in machine learning systems: What do industry practitioners need?
R.I.P.
π»
Ghosted
Identifying Stable Patterns over Time for Emotion Recognition from EEG
R.I.P.
π»
Ghosted
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
R.I.P.
π»
Ghosted
Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
R.I.P.
π»
Ghosted
Educational data mining and learning analytics: An updated survey
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted