Intelligent emotion recognition system in neural network basis

Abstract

The human factor plays a significant role in ensuring the integrated safety of technological facilities. It is important to monitor the state of the operator of automated process control systems in soft real-time mode in order to reduce the risk of attention and concentration losses. Paper discusses the issues of increasing the efficiency of monitoring system of the operator’s state by using algorithms for assessing the psycho-emotional state. These algorithms apply methods of intelligent analysis of video sequence data without the use of additional contact sensors, which reduces probability of making a wrong decision due to the timely detection of unstable psycho-emotional states. The accuracy of detecting unstable psycho- emotional states on a test data set is 79%.