Employing Eye Trackers to Reduce Nuisance Alarms

Abstract

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, p = 0.263, partial η² = 0.056). However, the scenario type affected which GBA method was more utilized (X² (2, N = 432) = 30.147, p < 0.001). Alarm prediction hits with gaze-based acknowledgements coincided more frequently than alarm prediction hits without gaze-based acknowledgements (X² (1, N = 432) = 23.802, p < 0.001, OR = 3.877, 95% CI 2.25-6.68, p < 0.05). Participant ratings indicated an overall preference for the three GBA methods over a standard alarm design (F(3,63) = 3.745, p = 0.015, partial η² = 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.

Keywords: alarms; attention; eye tracking; monitoring; user interface.

Figure 6

Graphical representations of (a) proximity-based GBA method, (b) entropy-based GBA method, and (c) prediction-based GBA method. The X-axis represents the time scale in seconds, and the y-axis represents the parameter scale in percentage. The blue line in each graph shows that acknowledgements muted some visual and auditory signals of the alarm at t = 0 if two fixations landed on the target parameters within the time window. The red line in each graph shows that acknowledgement did not occur regardless of the number of fixations on the target AOI within the time window for fixations because the parameter behaviors depicted by the red lines did not satisfy the pre-defined criteria.

Figure 1

The experimental apparatus consisted of an LCD screen (top) for the participants to keep one parameter within 20–60% capacity by regulating a valve (top monitor) and another LCD screen (bottom) to monitor a set of parameters and predict any alarms in a chemical plant simulation.

Figure 2

Chemical plant simulator used for the alarm monitoring task. The simulator has seven components that can alarm. Each parameter has marks noting the alarm set points and a trendline graph.

Figure 3

When participants click on a parameter, a blue dotted outline signifies the participant’s prediction of the impending alarm.

Figure 4

The original alarm presentation (a) versus an alarm during gaze-based acknowledgement (b).

Figure 5

The parameter control task consisted of participants maintaining the feedwater tank level between 20 and 60% by toggling the valve on/off.

Figure 7

Mean plot of scenario type main effect on parameter control task performance, F(2,46) = 5.075, p = 0.011, partial η² = 0.181.

Figure 8

Mean plot of GBA methods’ main effect on usability ratings, F(3,63) = 3.745, p = 0.015, partial η² = 0.151. Confidence intervals were omitted to avoid statistical inference with repeated measure ANOVA.