Hybrid data-driven vigilance model in traffic control center using eye-tracking data and context data

Abstract

Vigilance decrement of traffic controllers would greatly threaten public safety. Hence, extensive studies have been conducted to establish the physiological data-based vigilance model for objectively monitoring or detecting vigilance decrement. Nevertheless, most of them using intrusive devices to collect physiological data and failed to consider context information. Consequently, these models can be used in a laboratory environment while cannot adapt to dynamic working conditions of traffic controllers. The goal of this research is to develop an adaptive vigilance model for monitoring vigilance objectively and non-intrusively. In recent years, with advanced information and communication technology, a massive amount of data can be collected from connected daily use items. Hence, we proposed a hybrid data-driven approach based on connected objects for establishing vigilance model in the traffic control center and provide an elaborated case study to illustrate the method. Specifically, eye movements are selected as the primary inputs of the proposed vigilance model; Bagged trees technique is adapted to generate the vigilance model. The results of case study indicated that (1) eye metrics would be correlated with the vigilance performance subjected to the mental fatigue levels, (2) the bagged trees with the fusion features as inputs achieved a relatively stable performance under the condition of data loss, (3) the proposed method could achieve better performance than the other classic machine learning methods.