AUTHOR=Du Pu , Li Penghai , Cheng Longlong , Li Xueqing , Su Jianxian 

TITLE=Single-trial P300 classification algorithm based on centralized multi-person data fusion CNN

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1132290

DOI=10.3389/fnins.2023.1132290

ISSN=1662-453X

ABSTRACT=To solve typical problems faced by the existing P300 classification such as complex and time-consuming process and low accuracy, a single-trial P300 classification algorithm based on multi-person data fusion Convolutional Neural Networks (CNN) is designed to achieve rapid and highly accurate classification of P300 electroencephalography (EEG) signals. In the data preprocessing phase, two centralized data fusion methods are adopted to merge multi-person EEG information stimulated by the same task instruction, and the fused data is then fed as input to CNN for classification. In the constructed CNN network, the Conv layer extracts the features, then the Maxpooling layer is used to connect the Flatten layer for secondary feature extraction and dimensionality reduction, thus simplifying computation. Batch Normalization is used to train the data in small Batch in order to better generalize the network and speed up single-trial P300 signal classifications. In this paper, the above new algorithms were tested on the Kaggle dataset and the Brain-Computer Interface (BCI) Competition III dataset, and by analyzing the P300 waveform features and EEG topography and the four standard evaluation metrics, namely Accuracy, Precision, Recall and F1- score, it was demonstrated that the single-trial P300 classification algorithm of the two multi-person data fusion CNNs significantly outperformed the classification of single-trial P300 by the CNN in single-person mode. and that the single-trial P300 classification algorithm with two multi-person data fusion CNNs involves smaller models, fewer training parameters, higher classification accuracy and improves the overall P300-cBCI classification rate and actual performance more effectively with a small amount of sample information compared to other algorithms.