Synthetic Biological Signals Machine-Generated by GPT-2 Improve the Classification of EEG and EMG Through Data Augmentation

  title={Synthetic Biological Signals Machine-Generated by GPT-2 Improve the Classification of EEG and EMG Through Data Augmentation},
  author={Jordan J. Bird and Michael Pritchard and Antonio Fratini and Anik{\'o} Ek{\'a}rt and Diego Resende Faria},
  journal={IEEE Robotics and Automation Letters},
Synthetic data augmentation is of paramount importance for machine learning classification, particularly for biological data, which tend to be high dimensional and with a scarcity of training samples. The applications of robotic control and augmentation in disabled and able-bodied subjects still rely mainly on subject-specific analyses. Those can rarely be generalised to the whole population and appear to over complicate simple action recognition such as grasp and release (standard actions in… Expand
General Robot Dynamics Learning and Gen2Real
A model is built that learns the intrinsic dynamics of various robots and lower the threshold of dynamics learning by enabling an amateur to obtain robot models without being trapped in details and a new concept, “Gen2Real”, to transfer simulated, general models to physical, specific robots is investigated. Expand
SynthBio: A Case Study in Human-AI Collaborative Curation of Text Datasets
This work introduces a novel method for efficient dataset curation: a large language model is used to provide seed generations to human raters, thereby changing dataset authoring from a writing task to an editing task. Expand
Fruit Quality and Defect Image Classification with Conditional GAN Data Augmentation
This work suggests a machine learning pipeline that combines the ideas of fine-tuning, transfer learning, and generative model-based training data augmentation towards improving fruit quality image classification, arguing that Conditional Generative Adversarial Networks have the ability to produce new data to alleviate issues of data scarcity. Expand


Data Augmentation of Surface Electromyography for Hand Gesture Recognition
A significant improvement of 1% in the classification accuracy of the state-of-the-art model in hand gesture recognition is achieved and a detailed evaluation of existing and novel strategies of data augmentation for electromyography signals is provided. Expand
A New Method to Generate Artificial Frames Using the Empirical Mode Decomposition for an EEG-Based Motor Imagery BCI
Results showed that, in some subjects, it is possible to replace up to 50% of frames with artificial data, which reduces training time from 720 to 360 s, and the method can be used to replace EEG frames that contain artifact, which reduced the impact of rejecting data with artifact. Expand
Classification of Motor Imagery EEG Signals with multi-input Convolutional Neural Network by augmenting STFT
This paper proposes a Motor Imagery EEG signal classification framework based on Convolutional Neural Network to enhance the classification accuracy and showed competitive performance when compared with other methods. Expand
Signal Processing Approaches to Minimize or Suppress Calibration Time in Oscillatory Activity-Based Brain–Computer Interfaces
  • F. Lotte
  • Computer Science
  • Proceedings of the IEEE
  • 2015
This paper proposes to generate artificial EEG trials from the few EEG trials initially available, in order to augment the training set size, and surveys existing approaches to reduce or suppress calibration time and proposes three different methods to do so. Expand
A Study on Mental State Classification using EEG-based Brain-Machine Interface
Results show that only 44 features from a set of over 2100 features are necessary when used with classical classifiers such as Bayesian Networks, Support Vector Machines and Random Forests, attaining an overall accuracy over 87%. Expand
HS-CNN: A CNN with hybrid convolution scale for EEG motor imagery classification.
This work has proposed a hybrid-scale CNN architecture with a data augmentation method for EEG motor imagery classification that effectively addressed the issues of existing CNN-based EEGMotor imagery classification methods and improved the classification accuracy. Expand
Thumbs up, thumbs down: non-verbal human-robot interaction through real-time EMG classification via inductive and supervised transductive transfer learning
This study presents a transfer learning method for gesture classification via an inductive and supervised transductive approach with an electromyographic dataset gathered via the Myo armband, and shows that 5 s of data per-class is the strongest for classification. Expand
Data augmentation for deep-learning-based electroencephalography
DA increasingly used and considerably improved DL decoding accuracy on EEG and holds transformative promise for EEG processing, possibly like DL revolutionized computer vision, etc. Expand
Data augmentation for self-paced motor imagery classification with C-LSTM.
The results of this study show that the proposed network achieves adequate results in distinguishing between different control classes, but both considered deep learning models are still less reliable than a Riemannian Minimum Distance to the Mean (MDM) classifier. Expand
EEG Data Augmentation for Emotion Recognition Using a Conditional Wasserstein GAN
  • Yun Luo
  • Medicine, Computer Science
  • 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2018
The experimental results demonstrate that using the EEG data generated by the proposed Conditional Wasserstein GAN (CWGAN) framework significantly improves the accuracies of emotion recognition models. Expand