EEG Dataset for RSVP and P300 Speller Brain-Computer Interfaces

Won, Kyungho; Kwon, Min Seong; Ahn, Minkyu; Jun, Sung Chan

doi:10.1038/s41597-022-01509-w

Cited by 36 publications

(15 citation statements)

References 37 publications

(43 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We employed four EEG datasets to evaluate the method proposed. Three were recorded with the P300 speller systems [30][31][32], and the last was obtained with the auditory oddball paradigm [11]. Detailed information on each dataset is provided in table 1.…”

Section: Datasets and Preprocessingmentioning

confidence: 99%

“…The second dataset [31], referred to as 'Speller-2,' was also acquired with the standard P300 BCI speller system using BCI2000 software with ActiveTwo (Biosemi Inc.). The EEG data were recorded from 55 subjects using 64 electrodes at 512 Hz, and signals were processed using common average referencing (CAR) and bandpass-filtering (0.1 Hz to 60 Hz).…”

Section: Datasets and Preprocessingmentioning

confidence: 99%

See 1 more Smart Citation

Signal alignment for cross-datasets in P300 brain-computer interfaces

Song,

Gwon,

Jun

et al. 2024

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

Objective. Transfer learning has become an important issue in the brain-computer interface (BCI) field, and studies on subject-to-subject transfer within the same dataset have been performed. However, few studies have been performed on dataset-to-dataset transfer, including paradigm-to-paradigm transfer. In this study, we propose a signal alignment for P300 event-related potential (ERP) signals that is intuitive, simple, computationally less expensive, and can be used for cross-dataset transfer learning.Approach. We proposed a linear signal alignment that uses the P300’s latency, amplitude scale, and reverse factor to transform signals. For evaluation, four datasets were introduced (two from conventional P300 Speller BCIs, one from a P300 Speller with face stimuli, and the last from a standard auditory oddball paradigm).Results. Although the standard approach without signal alignment had an average precision score of 25.5%, the approach demonstrated a 35.8% average precision score, and we observed that the number of subjects showing improvement was 36.0% on average. Particularly, we confirmed that the Speller dataset with face stimuli was more comparable with other datasets. Significance. We proposed a simple and intuitive way to align ERP signals that uses the characteristics of ERP signals. The results demonstrated the feasibility of cross-dataset transfer learning even between datasets with different paradigms.

show abstract

Section: Datasets and Preprocessingmentioning

confidence: 99%

Section: Datasets and Preprocessingmentioning

confidence: 99%

Signal alignment for cross-datasets in P300 brain-computer interfaces

Song,

Gwon,

Jun

et al. 2024

J. Neural Eng.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The first dataset was based on the rapid serial visual presentation (RSVP) task, designed to evoke ERP responses [30]. The dataset contained 55 subjects (14 females, age 22.91 ± 2.87).…”

Section: Datasets and Preprocessingmentioning

confidence: 99%

A feature enhanced EEG compression model using asymmetric encoding–decoding network ^*

Wang,

Zhang,

2024

J. Neural Eng.

View full text Add to dashboard Cite

Objective. Recently, the demand for wearable devices using electroencephalography (EEG) has increased rapidly in many fields. Due to its volume and computation constraints, wearable devices usually compress and transmit EEG to external devices for analysis. However, current EEG compression algorithms are not tailor-made for wearable devices with limited computing and storage. Firstly, the huge amount of parameters makes it difficult to apply in wearable devices; secondly, it’s tricky to learn EEG signals’ distribution law due to the low signal-to-noise ratio, which leads to excessive reconstruction error and suboptimal compression performance. Approach. Here, a feature enhanced asymmetric encoding-decoding network is proposed. EEG is encoded with a lightweight model, and subsequently decoded with a multi-level feature fusion network by extracting the encoded features deeply and reconstructing the signal through a two-branch structure. Main results. On public EEG datasets, motor imagery and event-related potentials, experimental results show that the proposed method has achieved the state of the art compression performance. In addition, the neural representation analysis and the classification performance of the reconstructed EEG signals also show that our method tends to retain more task-related information as the compression ratio increases and retains reliable discriminative information after EEG compression. Significance. This paper tailors an asymmetric EEG compression method for wearable devices that achieves state-of-the-art compression performance in a lightweight manner, paving the way for the application of EEG-based wearable devices.

show abstract

“…Literatürde EEG sinyallerinin kullanımından elde edilen öznitelikleri kullanarak genellikle motor hayali (Arpaia, Esposito, Natalizio, & Parvis, 2022;Kevric & Subasi, 2017;Stephe & Kumar, 2022), olay ilişkili P300 potansiyel temelli (Sellers, Krusienski, McFarland, Vaughan, & Wolpaw, 2006;Won, Kwon, Ahn, & Jun, 2022;Xu vd., 2013) ve kararlı durum görsel olarak uyarılmış potansiyel tabanlı (Jalilpour, Sardouie, & Mijani, 2020;Muller-Putz & Pfurtscheller, 2007; Z. Wu, Lai, Xia, Wu, & Yao, 2008) olmak üzere üç ana yaklaşım vardır.…”

Section: Introductionunclassified

Investigation of the Effects of Two and Three Dimensional Paradigms on Event-Related Potentials Using Wavelet Transform Based Method

Korkmaz

2022

EJOSAT

View full text Add to dashboard Cite

In event-related P300 potential-based Brain Computer Interface (BCI) systems, the main focus of the studies is how different stimulus types affect system performance. In a study, a data set was created using classical two-dimensional row-column flashing-based and proposed three-dimensional column flashing-based paradigms. According to the results obtained, the proposed three-dimensional column flashing shows high performance in terms of classification accuracy of stimulus presentation. However, how this paradigm changes the P300 potential has not been demonstrated. In this study, the effect of both paradigms on the event-related P300 potential is discussed using a wavelet transform-based method in terms of both time and frequency space. According to the results obtained, it was observed that the proposed paradigm activated more frequency bands on the P300 potential. In addition, using the proposed method, higher P300 amplitude was obtained in many channels. As a result, more effective P300 signals are received in stimulus presentation using the proposed paradigm, increasing the BCI system performance.

show abstract

EEG Dataset for RSVP and P300 Speller Brain-Computer Interfaces

Cited by 36 publications

References 37 publications

Signal alignment for cross-datasets in P300 brain-computer interfaces

Signal alignment for cross-datasets in P300 brain-computer interfaces

A feature enhanced EEG compression model using asymmetric encoding–decoding network ^*

Investigation of the Effects of Two and Three Dimensional Paradigms on Event-Related Potentials Using Wavelet Transform Based Method

Contact Info

Product

Resources

About

EEG Dataset for RSVP and P300 Speller Brain-Computer Interfaces

Cited by 36 publications

References 37 publications

Signal alignment for cross-datasets in P300 brain-computer interfaces

Signal alignment for cross-datasets in P300 brain-computer interfaces

A feature enhanced EEG compression model using asymmetric encoding–decoding network *

Investigation of the Effects of Two and Three Dimensional Paradigms on Event-Related Potentials Using Wavelet Transform Based Method

Contact Info

Product

Resources

About

A feature enhanced EEG compression model using asymmetric encoding–decoding network ^*