The status of an operator's situation awareness is one of the critical factors that influence the quality of the missions. Thus the measurement method of the situation awareness status is an important topic to research. So far, there are lots of methods designed for the measurement of situation awareness status, but there is no model that can measure it accurately in real-time, so this work is conducted to deal with such a gap. Firstly, collect the relevant physiological data of operators while they are performing a specific mission, simultaneously, measure their status of situation awareness by using the situation awareness global assessment technique (SAGAT), which is known for accuracy but cannot be used in real-time. And then, after the preprocessing of the raw data, use the physiological data as features, the SAGAT's results as a label to train a fuzzy cognitive map (FCM), which is an explainable and powerful intelligent model. Also, a hybrid learning algorithm of particle swarm optimization (PSO) and gradient descent is proposed for the FCM training. The final results show that the learned FCM can assess the status of situation awareness accurately in real-time, and the proposed hybrid learning algorithm has better efficiency and accuracy.
- fuzzy cognitive map (FCM)
- gradient descent
- particle swarm optimization (PSO)
- situation awareness (SA)