Research on Pilots ’ Mental Workload Classification in Simulated Flight

Abstract The problem of human-computer interaction mental workload in flight driving has great reference value for the prevention safety hazards aviation driving. This paper analyzes and studies classification method by designing different simulated experiment tasks. study uses a combination EEG signals subjective evaluation, through use convolutional neural networks long short-term memory network combining research analysis. accuracy signal is as high 94.9 %. NASA-TLX evaluation results show that there positive correlation between task load difficulty score. suitable pilots ’ classification. important practical significance accidents caused workload.