Mental Workload Estimation Using EEG

Abstract

Mental workload contributes considerably to the outcome or the performance of any task. The concern of human workload increases during a human-machine collaboration task or in a multitasking environment. This paper presents a comparative study of machine learning algorithms used to estimate workload using Electroencephalography (EEG) data. An open-access EEG dataset acquired during a “simultaneous capacity (SIMKAP) experiment” and “no task” is used to create and validate models for binary classification of workload as present and absent respectively. The paper presents an implementation of various classification models that use EEG data to predict the workload. In this paper, implementation for KNN classifier (57.3%), Random Forest classifier (57.19%), MLP network classifier (58.2%), CNN+ LSTM network classifier (58.68%), and LSTM network classifier (61.08%) has been reported. The paper can be further extended to study operator workload in real-time using a brain-computer interface paradigm for any kind of task in a real-world application. The workload classification can be further used in human-machine tasks to decide task allocation between the system to achieve optimal performance in a complex critical system.