Data Augmentation for Deep-Learning-Based Electroencephalography.
By Elnaz Lashgari, Dehua Liang, Uri Maoz. Journal of Neuroscience Methods, 2020
351 citations recorded by the source corpus.
BACKGROUND Data augmentation (DA) has recently been demonstrated to achieve considerable performance gains for deep learning (DL)-increased accuracy and stability and reduced overfitting. Some electroencephalography (EEG) tasks suffer from low samples-to-features ratio, severely reducing DL effectiveness. DA with DL thus holds transformative promise for EEG processing, possibly like DL revolutionized computer vision, etc. NEW METHOD: We review trends and approaches to DA for DL in EEG to address: Which DA approaches exist and are common for which EEG tasks? What input features are used? And, what kind of accuracy gain can be expected? RESULTS DA for DL on EEG begun 5 years ago and is steadily used more. We grouped DA techniques (noise addition, generative adversarial networks, sliding windows, sampling, Fourier transform, recombination of segmentation, and others) and EEG tasks (into seizure detection, sleep stages, motor imagery, mental workload, emotion recognition, motor tasks, and visual tasks). DA efficacy across techniques varied considerably. Noise addition and sliding windows provided the highest accuracy boost; mental workload most benefitted from DA. Sliding window, noise addition, and sampling methods most common for seizure detection, mental workload, and sleep stages, respectively. COMPARING WITH EXISTING METHODS Percent of decoding accuracy explained by DA beyond unaugmented accuracy varied between 8% for recombination of segmentation and 36% for noise addition and from 14% for motor imagery to 56% for mental workload-29% on average. CONCLUSIONS DA increasingly used and considerably improved DL decoding accuracy on EEG. Additional publications-if adhering to our reporting guidelines-will facilitate more detailed analysis.
Subfields: Cognitive Neuroscience, Signal Processing
View Paper: https://www.semanticscholar.org/paper/3571241861333dee845c9970dbd0d1e68a32fe71
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Signal Processing
Citations in the corpus
- Data Augmentation techniques in time series domain: a survey and taxonomy (2022, methodology): “The approach followed in [29] is to compare different DA techniques by the increase in accuracy produced in each case of study.”
- Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: a review (2021, methodology): “Apart from classification-based techniques, other articles have reviewed specific machine learning strategies and techniques for EEG brain signals, such as feature extraction [15], transfer learning [40], and data augmentation [41].”