Herdt Katherine, Hildebrandt Michael, LeBlanc Katya, Lau Nathan
Grado Department of Industrial and Systems Engineering, Virginia Tech, Blacksburg, VA 24061, USA.
Humans and Automation Department, Institute for Energy Technology, 1777 Halden, Norway.
Sensors (Basel). 2025 Apr 22;25(9):2635. doi: 10.3390/s25092635.
When process operators anticipate an alarm prior to its annunciation, that alarm loses information value and becomes a nuisance. This study investigated using eye trackers to measure and adjust the salience of alarms with three methods of gaze-based acknowledgement (GBA) of alarms that estimate operator anticipation. When these methods detected possible alarm anticipation, the alarm's audio and visual salience was reduced. A total of 24 engineering students (male = 14, female = 10) aged between 18 and 45 were recruited to predict alarms and control a process parameter in three scenario types (parameter near threshold, trending, or fluctuating). The study evaluated whether behaviors of the monitored parameter affected how frequently the three GBA methods were utilized and whether reducing alarm salience improved control task performance. The results did not show significant task improvement with any GBA methods (F(3,69) = 1.357, = 0.263, partial η = 0.056). However, the scenario type affected which GBA method was more utilized ( (2, = 432) = 30.147, 0.001). Alarm prediction hits with gaze-based acknowledgements coincided more frequently than alarm prediction hits without gaze-based acknowledgements ( (1, = 432) = 23.802, < 0.001, OR = 3.877, 95% CI 2.25-6.68, < 0.05). Participant ratings indicated an overall preference for the three GBA methods over a standard alarm design (F(3,63) = 3.745, = 0.015, partial η = 0.151). This study provides empirical evidence for the potential of eye tracking in alarm management but highlights the need for additional research to increase validity for inferring alarm anticipation.
当过程操作员在警报发出之前就预料到它时，该警报就失去了信息价值并变成了一种干扰。本研究调查了使用眼动仪，通过三种基于注视的警报确认（GBA）方法来测量和调整警报的显著性，这三种方法用于估计操作员的预料情况。当这些方法检测到可能的警报预料时，警报的音频和视觉显著性就会降低。总共招募了24名年龄在18至45岁之间的工科学生（男性14名，女性10名），让他们在三种场景类型（参数接近阈值、呈趋势变化或波动）下预测警报并控制一个过程参数。该研究评估了被监测参数的行为是否会影响三种GBA方法的使用频率，以及降低警报显著性是否能提高控制任务的性能。结果显示，使用任何一种GBA方法都没有显著提高任务表现（F(3,69) = 1.357, = 0.263, 部分η = 0.056）。然而，场景类型会影响哪种GBA方法被更多地使用（(2, = 432) = 30.147, 0.001）。基于注视确认的警报预测命中比没有基于注视确认的警报预测命中更频繁地同时出现（(1, = 432) = 23.802, < 0.001, OR = 3.877, 95% CI 2.25 - 6.68, < 0.05）。参与者评分表明，总体上对三种GBA方法的偏好超过了标准警报设计（F(3,63) = 3.745, = 0.015, 部分η = 0.151）。本研究为眼动追踪在警报管理中的潜力提供了实证证据，但也强调了需要进行更多研究以提高推断警报预料的有效性。
