School of Engineering, RMIT University, Bundoora, VIC 3083, Australia.
Department of Aerospace Engineering, Khalifa University of Science and Technology, Abu Dhabi 127788, United Arab Emirates.
Sensors (Basel). 2022 Jun 21;22(13):4673. doi: 10.3390/s22134673.
Emerging Air Traffic Management (ATM) and avionics human-machine system concepts require the real-time monitoring of the human operator to support novel task assessment and system adaptation features. To realise these advanced concepts, it is essential to resort to a suite of sensors recording neurophysiological data reliably and accurately. This article presents the experimental verification and performance characterisation of a cardiorespiratory sensor for ATM and avionics applications. In particular, the processed physiological measurements from the designated commercial device are verified against clinical-grade equipment. Compared to other studies which only addressed physical workload, this characterisation was performed also looking at cognitive workload, which poses certain additional challenges to cardiorespiratory monitors. The article also addresses the quantification of uncertainty in the cognitive state estimation process as a function of the uncertainty in the input cardiorespiratory measurements. The results of the sensor verification and of the uncertainty propagation corroborate the basic suitability of the commercial cardiorespiratory sensor for the intended aerospace application but highlight the relatively poor performance in respiratory measurements during a purely mental activity.
新兴的空中交通管理 (ATM) 和航空电子人机系统概念需要实时监测操作人员,以支持新的任务评估和系统自适应功能。为了实现这些先进概念,必须依靠一系列传感器来可靠准确地记录神经生理数据。本文介绍了一种用于 ATM 和航空电子应用的心肺传感器的实验验证和性能特征。特别是,指定的商业设备的处理生理测量结果与临床级设备进行了验证。与仅解决物理工作量的其他研究相比,这种特征分析还考虑了认知工作量,这对心肺监测器提出了某些额外的挑战。本文还讨论了如何根据输入心肺测量的不确定性来量化认知状态估计过程中的不确定性。传感器验证和不确定性传播的结果证实了商业心肺传感器基本适用于预期的航空航天应用,但突出表明在纯粹的脑力活动期间,呼吸测量的性能相对较差。