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

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 study, we have proposed a novel method to detect the 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 convolutional neural network with long short term memory (CNN-LSTM) model with self-attention has been used to perform the time-series classification into sabotage and no-sabotage, by transforming the time-series into two-dimensional (2D) image-based scalogram representations. This approach allows the inspection of frequency-based, and 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 the data of all subjects. We also compare the scalogram-based results with the results that we obtained by using raw time-series, showing that scalogram-based gave better performance. Our method can be applied in clinical applications such as baseline testing, assessing the current state of injury and recovery tracking and industrial applications like monitoring performance deterioration in workplaces.

Effects of Concussion on the Relative Contributions of Sensorimotor Memories during Adaptation to Unpredictable Spring-Like Loads

“…Sabotaging performance may be exploited by athletes during pre-season baseline testing such that sabotaged scores appear comparable to post-concussion scores – thus impeding a concussion diagnosis and removal from play to avoid further injury. Sergio and colleagues have addressed this issue by instrumenting participants with a commercial four-channel EEG headset and using a neural network to detect sabotaged performance [31] which can then be used to justify a retest. We have addressed this issue through an inherent property of the implicit sensorimotor resources we are probing – implicit sensorimotor memories do not seem to be accessible or modifiable by the individual [8,16].…”

Machine learning algorithms for detection of visuomotor neural control differences in individuals with PASC and ME

“…Another significant challenge is the need for a robust and standardized methodology to compare the performance of various machine learning and deep learning models for PASC/ME effects detection using EEG data. Our study addresses this issue by transforming raw EEG signals via Continuous Wavelet Transform (CWT) into a spectrogram-like matrix (Chaudhary et al, 2021 ). This matrix is then applied to train diverse models, including CONVLSTM (Convolutional Long Short-Term Memory; Shi et al, 2015 ), CNN-LSTM (Hochreiter and Schmidhuber, 1997 ; Krizhevsky et al, 2012 ), and Bi-LSTM (Bidirectional Long short-term memory; Graves et al, 2013 ).…”