Sensor-based detection of individual walkability perception to promote healthy communities

Abstract

People living in walkable areas are more likely to maintain a physically active lifestyle. Adverse elements of the built environment (e.g., demolished houses, damaged sidewalks) can cause physical or emotional distress, and negatively affect walkability patterns. Individuals are likely to perceive walkability of a place in distinct ways and can be differentially impacted by the built environment. This paper quantifies walkability perception of the built environment using data from in-the-moment interactions between pedestrians and the built environment, captured by wearable physiological and accelerometry sensors. Prominent temporal change patterns in physiological reactivity (i.e., electrodermal activity, heart rate) and gait are captured through a physiological saliency cue (PSC), which comprises the input of a machine learning model automatically estimating pedestrians perceived walkability. Contextual information from user's location is further used to augment the features. Results obtained on 25 participants in a field experiment indicate that the PSC measures can reliably detect individual perception of walkability, often more accurately compared to the aggregate measures from the corresponding raw signals. Inclusion of contextual information further improves the performance. Findings from this study can enhance our understanding on the association between walkability and the built environment, and lead to more effective planning and public health strategies that contribute to community health.