LSTM-based Approach to Monitor Operator Situation Awareness via HMI State Prediction
Harsh V.P. Singh, Qusay H. Mahmoud · 2019
Situational Awareness is an indispensable barrier against execution human errors from cascading across system processes. Therefore, early detection and intervention is vital for preventing accidents in time-critical scenarios. Evidently, legacy human-machine interfaces especially those prevalent in nuclear power plant and aviation industry, are complex, elaborate and require continual supervision of operator situational aware-ness. In this paper, a novel approach towards achieving non-intrusive real-time monitoring of operator situational awareness is framed as a supervised learning task suitable for applying deep recurrent neural network (RNN) models. Results, include performance evaluation of few typical RNN Long-Short Term Memory (LSTM) based time-series forecast models for predicting expected operator n-step ahead response pattern given current human-machine interface state as inputs.