TL-P3GAN: An Efficient Temporal-Learning-Based Generative Adversarial Network for Precise P300 Signal Generation for P300 Spellers
- 21 June 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cognitive and Developmental Systems
- Vol. 16 (2) , 692-705
Abstract
Problem of data imbalance among target and non-target classes is inherent in the oddball paradigm-based P300 speller. This class imbalance is a critical issue and requires advanced rigorous learning to deal with. Conventionally, data level-like sampling approaches and algorithmic level-like ensemble approaches had been attempted in past research for data augmentation. However, information loss, overfitting and subject variability were their major pitfalls. Alternatively, generative adversarial network (GAN) based data augmentation managed to alleviate information loss but exhibits problems of overfitting and subject variability due to lack of temporal learning. To compensate for those problems, authors have proposed novel temporal learning-based GAN (TL-P3GAN) to generate precise P300 signals and augment the minority class i.e., P300. The TL-P3GAN comprises novel contribution of multiscale morphological learning in both generator and discriminator. Moreover, the multiscale hybrid model in generator learns multi-resolution morphological information and considers sample-wise latency information from original P300. The effectiveness of TL-P3GAN was confirmed by qualitative and quantitative evaluation metrics with two standard datasets. Further, the work is extended to analyze the effect of generated P300 signals on P300 classification and found significant performance improvement of 8-16% with both datasets in comparison with existing conventional and GAN-based data augmentation approaches.Keywords
This publication has 33 references indexed in Scilit:
- Effect of Input Noise Dimension in GANs2021
- EEG data augmentation for emotion recognition with a multiple generator conditional Wasserstein GANComplex & Intelligent Systems, 2021
- Combining generative adversarial networks and multi-output CNN for motor imagery classificationJournal of Neural Engineering, 2021
- Data augmentation for enhancing EEG-based emotion recognition with deep generative modelsJournal of Neural Engineering, 2020
- Convolutional neural networks for decoding of covert attention focus and saliency maps for EEG feature visualizationJournal of Neural Engineering, 2019
- Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial networkScientific Reports, 2019
- Weighted extreme learning machine for P300 detection with application to brain computer interfaceJournal of Ambient Intelligence and Humanized Computing, 2018
- Deep learning based on Batch Normalization for P300 signal detectionNeurocomputing, 2018
- Brain–computer interfaces for communication and controlClinical Neurophysiology, 2002
- Psychophysiology of P300.Psychological Bulletin, 1981