AUTHOR=Chaudhary Mahima , Adams Meaghan S. , Mukhopadhyay Sumona , Litoiu Marin , Sergio Lauren E. 

TITLE=Sabotage Detection Using DL Models on EEG Data From a Cognitive-Motor Integration Task

JOURNAL=Frontiers in Human Neuroscience

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/human-neuroscience/articles/10.3389/fnhum.2021.662875

DOI=10.3389/fnhum.2021.662875

ISSN=1662-5161

ABSTRACT=Objective clinical tools, including cognitive-motor integration (CMI) tasks have the potential to improve concussion rehabilitation by helping to determine whether or not a concussion has occurred. In order to be useful, however, an individual must put forth their best effort. In this work, we have proposed a novel method to detect difference in cortical activity between best effort (no-sabotage) and willful under-performance (sabotage) using a deep learning (DL) approach on the electroencephalogram (EEG) signals. The EEG signals from a wearable four-channel headband were acquired during a CMI task. Each participant completed sabotage and no-sabotage conditions in random order. A multi-channel CNN-LSTM (convolutional neural network with long short term memory) model with self-attention has been used to perform the time-series classification into sabotage and no-sabotage, by transforming the time series into 2D image-based scalogram representations. This approach allows the inspection of frequency-based, as well as temporal features of EEG and the use of a multi-channel model facilitates in capturing correlation and causality between different EEG channels. By treating the 2D scalogram as an image, we show that the trained CNN-LSTM classifier based on automated visual analysis can achieve high levels of discrimination and an overall accuracy of 98.71% in case of intra-subject classification, as well as low false-positive rates. The average intra-subject accuracy obtained was 92.8% and the average inter-subject accuracy was 86.15%. These results indicate that our proposed model performed well on all subjects data. We also compare the scalogram-based results with the results that we obtained by using raw timeseries, showing that scalogram-based gave better performance. Our method can be applied in clinical applications such as baseline testing, assessing current state of injury and recovery tracking as well as industrial applications like monitoring performance deterioration in workplaces.