Transfer Learning and SpecAugment applied to SSVEP Based BCI Classification

• URL: http://arxiv.org/abs/2010.06503v2
• Date: Thu, 18 Mar 2021 06:58:13 GMT
• Title: Transfer Learning and SpecAugment applied to SSVEP Based BCI Classification
• Authors: Pedro R. A. S. Bassi, Willian Rampazzo and Romis Attux
• Abstract summary: We use deep convolutional neural networks (DCNNs) to classify EEG signals in a single-channel brain-computer interface (BCI) EEG signals were converted to spectrograms and served as input to train DCNNs using the transfer learning technique.
• Score: 1.9336815376402716
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• CNN-Transformer Rectified Collaborative Learning for Medical Image Segmentation [60.08541107831459]
  This paper proposes a CNN-Transformer rectified collaborative learning framework to learn stronger CNN-based and Transformer-based models for medical image segmentation. Specifically, we propose a rectified logit-wise collaborative learning (RLCL) strategy which introduces the ground truth to adaptively select and rectify the wrong regions in student soft labels. We also propose a class-aware feature-wise collaborative learning (CFCL) strategy to achieve effective knowledge transfer between CNN-based and Transformer-based models in the feature space.
  arXiv  Detail & Related papers  (2024-08-25T01:27:35Z)
• Evaluating Fast Adaptability of Neural Networks for Brain-Computer Interface [0.23020018305241333]
  We use motor movement and imaginary signals as input to Convolutional Neural Networks (CNN) based classifier for experiments. We empirically show that layer-normalization can improve the adaptability of CNN-based EEG classifiers with not more than ten fine-tuning steps.
  arXiv  Detail & Related papers  (2024-04-14T22:36:53Z)
• Physics-informed and Unsupervised Riemannian Domain Adaptation for Machine Learning on Heterogeneous EEG Datasets [53.367212596352324]
  We propose an unsupervised approach leveraging EEG signal physics. We map EEG channels to fixed positions using field, source-free domain adaptation. Our method demonstrates robust performance in brain-computer interface (BCI) tasks and potential biomarker applications.
  arXiv  Detail & Related papers  (2024-03-07T16:17:33Z)
• Convolutional Monge Mapping Normalization for learning on sleep data [63.22081662149488]
  We propose a new method called Convolutional Monge Mapping Normalization (CMMN) CMMN consists in filtering the signals in order to adapt their power spectrum density (PSD) to a Wasserstein barycenter estimated on training data. Numerical experiments on sleep EEG data show that CMMN leads to significant and consistent performance gains independent from the neural network architecture.
  arXiv  Detail & Related papers  (2023-05-30T08:24:01Z)
• Deep comparisons of Neural Networks from the EEGNet family [0.0]
  We compared 5 well-known neural networks (Shallow ConvNet, Deep ConvNet, EEGNet, EEGNet Fusion, MI-EEGNet) using open-access databases with many subjects next to the BCI Competition 4 2a dataset. Our metrics showed that the researchers should not avoid Shallow ConvNet and Deep ConvNet because they can perform better than the later published ones from the EEGNet family.
  arXiv  Detail & Related papers  (2023-02-17T10:39:09Z)
• Transfer Learning of an Ensemble of DNNs for SSVEP BCI Spellers without User-Specific Training [3.6144103736375857]
  Current high performing SSVEP BCI spellers require an initial lengthy and tiring user-specific training for each new user for system adaptation. To ensure practicality, we propose a highly novel target identification method based on an ensemble of deep neural networks (DNNs) We exploit already-existing literature datasets from participants of previously conducted EEG experiments to train a global target identifier DNN first. We transfer this ensemble of fine-tuned DNNs to the new user instance, determine the k most representative DNNs according to the participants' statistical similarities to the new user, and predict the target character through a weighted combination of
  arXiv  Detail & Related papers  (2022-09-03T23:24:47Z)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• FBCNN: A Deep Neural Network Architecture for Portable and Fast Brain-Computer Interfaces [3.198144010381572]
  We propose two models: the FBCNN-2D and the FBCNN-3D. The FBCNNs surpassed traditional SSVEP classification methods in our simulated BCI.
  arXiv  Detail & Related papers  (2021-09-05T20:34:15Z)
• Classification of Motor Imagery EEG Signals by Using a Divergence Based Convolutional Neural Network [0.0]
  It is observed that the augmentation process is not applied for increasing the classification performance of EEG signals. In this study, we have investigated the effect of the augmentation process on the classification performance of MI EEG signals.
  arXiv  Detail & Related papers  (2021-03-19T18:27:28Z)
• EEG-Inception: An Accurate and Robust End-to-End Neural Network for EEG-based Motor Imagery Classification [123.93460670568554]
  This paper proposes a novel convolutional neural network (CNN) architecture for accurate and robust EEG-based motor imagery (MI) classification. The proposed CNN model, namely EEG-Inception, is built on the backbone of the Inception-Time network. The proposed network is an end-to-end classification, as it takes the raw EEG signals as the input and does not require complex EEG signal-preprocessing.
  arXiv  Detail & Related papers  (2021-01-24T19:03:10Z)
• ECG-DelNet: Delineation of Ambulatory Electrocardiograms with Mixed Quality Labeling Using Neural Networks [69.25956542388653]
  Deep learning (DL) algorithms are gaining weight in academic and industrial settings. We demonstrate DL can be successfully applied to low interpretative tasks by embedding ECG detection and delineation onto a segmentation framework. The model was trained using PhysioNet's QT database, comprised of 105 ambulatory ECG recordings.
  arXiv  Detail & Related papers  (2020-05-11T16:29:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.