An intelligent machine learning alerting system for distracted pedestrians

Distracted walking, such as looking at a smartphone, is associated with an increased loss of situation awareness and a risk of injury and could be a contributing factor to increasing pedestrian deaths. To examine how well a smartphone-based intelligent alerting device could prevent distracted pedestrians from making unsafe or risky road crossings, an experiment was conducted in a controlled field setting. Thirty participants each performed 30 road crossings while walking and playing a game on a smartphone. Alerts warned pedestrians at different points to not attempt a crossing due to an oncoming car. Out of 900 crossing events, 20% of crossings were risky or unsafe. The smartphone-based alerts did not produce substantially safer pedestrian behaviors. Results also illustrated that international participants were at higher risk of making risky crossing decisions. These results suggest that culture could play an important role in the use of technological interventions meant to promote positive behaviors, and a solution effective in one setting may not generalize to other cultures.