Transfer learning and SpecAugment applied to SSVEP based BCI classification. (May 2021)

• Record Type: Journal Article
• Authors: Bassi, Pedro R.A.S.; Rampazzo, Willian; Attux, Romis
• Is Part Of: Biomedical signal processing and control. Volume 67(2021)
• Publication Date: 2021-05
• Subjects: Transfer learning -- SSVEP -- BCI -- Neural networks -- SpecAugment; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.102542
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: SpecAugment can improve SSVEP based BCI classification performances. DNNs surpass FBCCA and SVMs in a single-channel BCI with small data length. Transfer learning made training faster. Window slicing can be combined with SpecAugment to improve performances. Abstract: Objective: We used deep convolutional neural networks (DCNNs) to classify electroencephalography (EEG) signals in a steady-state visually evoked potentials (SSVEP) based single-channel brain–computer interface (BCI), which does not require calibration on the user. Methods: EEG signals were converted to spectrograms and served as input to train DCNNs using the transfer learning technique. We also modified and applied a data augmentation method, SpecAugment, generally employed for speech recognition. Furthermore, for comparison purposes, we classified the SSVEP dataset using support-vector machines (SVMs) and filter bank canonical correlation analysis (FBCCA). Results: Excluding the evaluated user's data from the fine-tuning process, we reached 82.2% mean test accuracy and 0.825 mean F1-Score on 35 subjects from an open dataset, using a small data length (0.5 s), only one electrode (Oz) and the DCNN with transfer learning, window slicing (WS) and SpecAugment's time masks. Conclusion: The DCNN results surpassed SVM and FBCCA performances, using a single electrode and a small data length. Transfer learning provided minimal accuracy change, but made training faster. SpecAugment created a small performance improvement and was successfully combined with WS, yielding higher accuracies. Significance: We present a new methodology to solve the problem of SSVEP classification using DCNNs. We also modified a speech recognition data augmentation technique and applied it to the context of BCIs. The presented methodology surpassed performances obtained with FBCCA and SVMs (more traditional SSVEP classification methods) in BCIs with small data lengths and one electrode. This type of BCI can be used to develop small and fast systems.