BCIAUT-P300: A Multi-Session and Multi-Subject Benchmark Dataset on Autism for P300-Based Brain-Computer-Interfaces.

Marco Simões,Paulo Carvalho,Carlos Amaral,Jorge Henriques,Miguel Castelo-Branco,Thomas Schmid,Eduardo Santamaría-Vázquez,Bruno Direito,Aleksandar Miladinović,Davide Borra,Dominik Krzemiński,Gbt-Upm ,Mayra Bittencourt-Villalpando,Neural_Engineering_Group ,Haifeng Zhao

doi:10.3389/fnins.2020.568104

Abstract

There is a lack of multi-session P300 datasets for Brain-Computer Interfaces (BCI). Publicly available datasets are usually limited by small number of participants with few BCI sessions. In this sense, the lack of large, comprehensive datasets with various individuals and multiple sessions has limited advances in the development of more effective data processing and analysis methods for BCI systems. This is particularly evident to explore the feasibility of deep learning methods that require large datasets. Here we present the BCIAUT-P300 dataset, containing 15 autism spectrum disorder individuals undergoing 7 sessions of P300-based BCI joint-attention training, for a total of 105 sessions. The dataset was used for the 2019 IFMBE Scientific Challenge organized during MEDICON 2019 where, in two phases, teams from all over the world tried to achieve the best possible object-detection accuracy based on the P300 signals. This paper presents the characteristics of the dataset and the approaches followed by the 9 finalist teams during the competition. The winner obtained an average accuracy of 92.3% with a convolutional neural network based on EEGNet. The dataset is now publicly released and stands as a benchmark for future P300-based BCI algorithms based on multiple session data.

Highlights

A Brain-Computer Interface (BCI) is a system that provides a direct communication between the brain and a computer or external device (Wolpaw and Winter Wolpaw, 2012)
This paper presented the BCIAUT-P300 dataset which combines multi-session and multi-subject data of 15 autism spectrum disorder (ASD) participants using a P300-based Brain-Computer Interfaces (BCI) for training joint-attention skills
Deep learning methods were able to overcome the more traditional machine learning approaches, with the best method obtaining an average accuracy of 92.3%

Summary

Introduction

A Brain-Computer Interface (BCI) is a system that provides a direct communication between the brain and a computer or external device (Wolpaw and Winter Wolpaw, 2012). The P300 approach, first attempted by Farwell and Donchin in the 80s (Farwell and Donchin, 1988), uses an oddball paradigm where an infrequent stimulus of interest is presented in a sequence of frequent stimuli of non-interest. With this paradigm, a positive deflection of the EEG measured in the central and posterior parts of the scalp is observed approximately around 300 ms after the infrequent stimulus of interest is presented (Guo et al, 2019; Riggins and Scott, 2019). The use-cases of P300based BCIs have greatly increased over the past years, from steering a wheelchair (Lopes et al, 2016) to composing music (Pinegger et al, 2017)

Methods

Results

Discussion

Conclusion