Principal Attributes of Wearable Warning Alarms to Promote Roadway Worker Safety

In response to a concerning increase in annual worker fatalities within U.S. roadway work zones and a lack of effective worker-centered alert systems in current practice, this study investigates how wearable alarms impact worker reactions (e.g., body movement away from traffic, head turn towards traffic) for their safety from traffic hazards (e.g., speeding, collision vehicles) in unstructured and short-term urban roadway work zones. This study captures human behavioural data in roadway work zones through virtual reality and micro-traffic simulation-based user testing, where varied alarm patterns (e.g., changing modality, duration, repetitions) triggered by traffic hazards are sent to a smartwatch wearable warning device. Through a machine learning-based Shapley value analysis to assess the influence of alarm attributes on roadway worker behaviour, this study identified that sensory modality (i.e., auditory/tactile senses stimulated) and duration (i.e., continuous active time interval) have significant impact on improving workers’ safety in their reactions to traffic hazards. Workers often improved their level of safety in reaction to alarm patterns with a “haptics and sound” modality and a continuous duration of 350 ms. Results identifying modality and duration as principal alarm attributes can inform future research directions towards improving the alarm design of wearable warning devices for roadway workers.