Elnaz Lashgari1, Dehua Liang2, Uri Maoz3. 1. Schmid College of Science and Technology, Chapman University, United States; Institute for Interdisciplinary Brain and Behavioral Sciences, Chapman University, United States. Electronic address: Lashgari@chapman.edu. 2. Schmid College of Science and Technology, Chapman University, United States; Institute for Interdisciplinary Brain and Behavioral Sciences, Chapman University, United States. 3. Schmid College of Science and Technology, Chapman University, United States; Institute for Interdisciplinary Brain and Behavioral Sciences, Chapman University, United States; Crean College of Health and Behavioral Sciences, Chapman University, United States; Anderson School of Management, University of California Los Angeles, United States; Biology and Bioengineering, California Institute of Technology, United States.
Abstract
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.
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.
Authors: Almudena López-Dorado; Miguel Ortiz; María Satue; María J Rodrigo; Rafael Barea; Eva M Sánchez-Morla; Carlo Cavaliere; José M Rodríguez-Ascariz; Elvira Orduna-Hospital; Luciano Boquete; Elena Garcia-Martin Journal: Sensors (Basel) Date: 2021-12-27 Impact factor: 3.576
Authors: Amelia A Casciola; Sebastiano K Carlucci; Brianne A Kent; Amanda M Punch; Michael A Muszynski; Daniel Zhou; Alireza Kazemi; Maryam S Mirian; Jason Valerio; Martin J McKeown; Haakon B Nygaard Journal: Sensors (Basel) Date: 2021-05-11 Impact factor: 3.576