Enhanced Accuracy for Multiclass Mental Workload Detection Using Long Short-Term Memory for Brain–Computer Interface

• Published in: Frontiers in neuroscience Vol. 14; p. 584
• Main Authors: Asgher, Umer, Khalil, Khurram, Khan, Muhammad Jawad, Ahmad, Riaz, Butt, Shahid Ikramullah, Ayaz, Yasar, Naseer, Noman, Nazir, Salman
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 23.06.2020; Frontiers Media S.A
• Subjects: Accuracy; Algorithms; Brain; Brain research; brain–computer interface; Classification; Cognitive ability; Computer applications; convolutional neural network; Deep learning; deep neural networks; Electroencephalography; Engineering; functional near-infrared spectroscopy; Implants; Infrared spectroscopy; Learning algorithms; Long short-term memory; Machine learning; Medical research; Medical screening; Memory; mental workload; Neural networks; Neuroergonomics; Neuroimaging; Neuroscience; Physiology; Prefrontal cortex; Spectrum analysis; Statistical analysis; Support vector machines; Traffic accidents & safety; Workloads; deep learning; convolutional neural network; functional near-infrared spectroscopy; mental workload; brain–computer interface; deep neural networks; long short-term memory
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2020.00584

Cognitive workload is one of the widely invoked human factors in the areas of human-machine interaction (HMI) and neuroergonomics. The precise assessment of cognitive and mental workload (MWL) is vital and requires accurate neuroimaging to monitor and evaluate the cognitive states of the brain. In this study, we have decoded four classes of MWL using long short-term memory (LSTM) with 89.31% average accuracy for brain-computer interface (BCI). The brain activity signals are acquired using functional near-infrared spectroscopy (fNIRS) from the prefrontal cortex (PFC) region of the brain. We performed a supervised MWL experimentation with four varying MWL levels on 15 participants (both male and female) and 10 trials of each MWL per participant. Real-time four-level MWL states are assessed using fNIRS system, and initial classification is performed using three strong machine learning (ML) techniques, support vector machine (SVM), -nearest neighbor ( -NN), and artificial neural network (ANN) with obtained average accuracies of 54.33, 54.31, and 69.36%, respectively. In this study, novel deep learning (DL) frameworks are proposed, which utilizes convolutional neural network (CNN) and LSTM with 87.45 and 89.31% average accuracies, respectively, to solve high-dimensional four-level cognitive states classification problem. Statistical analysis, -test, and one-way -test (ANOVA) are also performed on accuracies obtained through ML and DL algorithms. Results show that the proposed DL (LSTM and CNN) algorithms significantly improve classification performance as compared with ML (SVM, ANN, and -NN) algorithms.