No abstract

Walkability is a term that describes aspects of the built and social environment. Previous studies have shown that different operationalisations of walkability are associated with physical activity and health. Walkability can be subjective and although multiple operational definitions and walkability measurement exist, there is no single agreed upon conceptual definition. Despite lack of consensus of a walkability definition, typical operational definitions include measures of population density, destinations, and the road network. Network science approaches such centralities and network embedding are missing from existing methods, yet they are integral parts of our mobility and should be an important part of how walkability is measured. Furthermore, most walkability measures have a one-size-fits-all approach and do not take into account individual user’s characteristics or walking preferences. To address some limitations of previous works, we developed the Active Living Feature Score (ALF-Score). ALF-Score is a network-based walkability measure that incorporates the road network structures as a core component. It also utilizes user data to build high-confidence ground truth that are used in conjunction with our machine learning pipeline to generate models capable of estimating walkability scores that address existing gaps in the walkability literature. We find, relying on road structure alone, we are able to train our models to estimate walkability scores with an accuracy of over 86% while maintaining a consistency of over 98% over collected user data. Our proposed approach outperforms existing measures by providing a walkability data at a much higher resolution as well as a user-derived result.

No abstract

Measuring environments around us (cities, roads, social environments) is crucial to understand human behaviour and help predict how aspects of environment influence behaviour and health. Walkability is one measure of environment used to predict health. Walkability combines aspects of environment (population, roads, amenities) into a single score. Existing measures are often one-size-fits-all with very limited personalization. In our previous work, we defined Active Living Feature Score, ALF-Score, a novel approach to measure network-based walkability. ALF-Score uses road network structures and points of interest to generate models capable of estimating walkability for any point on map. One of ALF-Score's contributions was the inclusion of user opinions to partially address the different perception among individuals and help derive a more personalized walkability score. Here, we take this personalization much further by introducing ALF-Score+ which uses individual user demographics (age, gender, ...) grouped using k-means and t-distributed stochastic neighbor embedding to create clusters based on individuals’ demographic characteristics. Each cluster is treated as a single profile representing a subset of users. Cluster profiles are added into our pipelines to generate profile-specific network-based walkability models. Results show strong variability among scores generated for each cluster profile with a clear variation in walkability generated for different users within same clusters. ALF-Score+ maintains an accuracy of 90.48% on average showing improvement compared to ALF-Score. We found strong association between cluster profiles' demographics and their scores. ALF-Score+ shows promising results providing personalized walkability based on cluster profiles, instead of a one-size-fits-all approach used by other walkability measures.

Walkability is a term that describes various aspects of the built and social environment and has been associated with physical activity and public health. Walkability is subjective and although multiple definitions of walkability exist, there is no single agreed upon definition. Road networks are integral parts of mobility and should be an important part of walkability. However, using the road structure as nodes is not widely discussed in existing methods. Most walkability measures only provide area–based scores with low spatial resolution, have a one–size–fits–all approach, and do not consider individuals opinion. Active Living Feature Score (ALF–Score) is a network–based walkability measure that incorporates road network structures as a core component. It also utilizes user opinion to build a high–confidence ground–truth that is used in our machine learning pipeline to generate models capable of estimating walkability. We found combination of network features with road embedding and points of interest features creates a complimentary feature set enabling us to train our models with an accuracy of over 87% while maintaining a conversion consistency of over 98%. Our proposed approach outperforms existing measures by introducing a novel method to estimate walkability scores that are representative of users opinion with a high spatial resolution, for any point on the road.