Conventional approaches to modelling driver risk have incorporated measures such as driver gender, age, place of residence, vehicle model, and annual miles driven. However, in the last decade, research has shown that assessing a driver’s crash risk based on these variables does not go far enough—especially as advanced technology changes today’s vehicles, as well as the role and behavior of the driver. There is growing recognition that actual driver usage patterns and driving behavior, when it can be properly captured in modelling risk, offers higher accuracy and more individually tailored projections. However, several challenges make this difficult. These challenges include accessing the right types of data, dealing with high-dimensional data, and identifying the underlying structure of the variance in driving behavior. There is also the challenge of how to identify key variables for detecting and predicting risk, and how to combine them in predictive algorithms. This paper proposes a systematic feature extraction and selection framework for building Comprehensive Driver Profiles that serves as a foundation for driver behavior analysis and building whole driver profiles. Features are extracted from raw data using statistical feature extraction techniques, and a hybrid feature selection algorithm is used to select the best driver profile feature set based on outcomes of interest such as crash risk. It can give rise to individualized detection and prediction of risk, and can also be used to identify types of drivers who exhibit similar patterns of driving and vehicle/technology usage. The developed framework is applied to a naturalistic driving dataset—NEST, derived from the larger SHRP2 naturalistic driving study to illustrate the types of information about driver behavior that can be harnessed—as well as some of the important applications that can be derived from it.

Background: The persuasive systems design approach draws together theories around persuasive technology and their psychological foundations to form, alter and/or reinforce compliance, attitudes, and/or behaviors, which have been useful in building health and wellness apps. But with pandemics such as COVID and their ever-changing landscape, there is a need for such design processes to be even more time sensitive, while maintaining the inclusion of empirical evidence and rigorous testing that are the basis for the approach’s successful deployment and uptake. Objective: In response to this need, this study applied a recently developed rapid persuasive systems design (R-PSD) process to the development and testing of a COVID support app. The aim of this effort was to identify concrete steps for when and how to build new persuasion features on top of existing features in existing apps to support the changing landscape of target behaviors from COVID tracing and tracking, to long-term COVID support, information, and prevention. Methods: This study employed a two-fold approach to achieve this objective. First, a rapid persuasive systems design framework was implemented. A technology scan of current COVID apps was conducted to identify apps that had employed PSD principles, in the context of an ongoing analysis of behavioral challenges and needs that were surfacing in public health reports and other sources. Second, a test case of the R-PSD framework was implemented in the context of providing COVID support by building a COVID support app prototype. The COVID support prototype was then evaluated and tested to assess the effectiveness of the integrated approach. Results: The results of the study revealed the potential success that can be obtained from the application of the R-PSD framework to the development of rapid release apps. Importantly, this application provides the first concrete example of how the R-PSD framework can be operationalized to produce a functional, user-informed app under real-world time and resource constraints. Further, the persuasive design categories enabled the identification of essential persuasive features required for app development that are intended to facilitate, support, or precipitate behavior change. The small sample study facilitated the quick iteration of the app design to ensure time sensitivity and empirical evidence-based application improvements. The R-PSD approach can serve as a guided and practical design approach for future rapid release apps particularly in relation to the development of support apps for pandemics or other time-urgent community emergencies.

Familiarity with a route is influenced by levels of dynamic and static knowledge about the route and the route network such as type of roads, infrastructure, traffic conditions, purpose of travel, weather, departure time, etc. To better understand and develop route choice models that can incorporate more meaningful representations of route familiarity, OBDII devices were installed in the vehicles of 32 drivers, 65 years and older, for a period of three months. Personalized web-based trip diaries were used to provide older drivers with post-trip feedback reports about their risky driving behaviors, and collect feedback about their route familiarity, preferences, and reasons for choosing the route driven vs. an alternate low-risk route. Feedback responses were analyzed and mapped onto an abstraction hierarchy framework, which showed that among older drivers, route familiarity depends not only on higher abstraction levels such as trip goals, purpose, and driving strategies, but also on the lower levels of demand on driving skills, and characteristics of road type. Additionally, gender differences were identified at the lower levels of the familiarity abstraction model, especially for driving challenges and the driving environment. Results from the analyses helped highlight the multi-faceted nature of route familiarity, which can be used to build the necessary levels of granularity for modelling and interpretation of spatial and contextual route choice recommendation systems for specific population groups such as older drivers.