Travel surveys has been used for decades to observe the patterns, locations, and choices, which travellers chose and do during the given observed period. This information can be utilized as background for informed planning decisions. Despite the progress in the travel survey technologies, the applications mostly focus on more traditional travel parameters. With programmable smart watches now, we can also collect real time data that is not solely pertaining to position and travel mode choices, but also to users’ biometric data. Such an application would open another level of possibilities in dynamically integrating land use and transport planning with public health research.

Utilising a smart watch platform, we are aiming to develop a tool that will collect biometric data, in combination with spatial context, such as position, spatial features and objects in the built environment, and by utilizing machine learning algorithms, try to detect how travellers are affected by their choice of transport mode, the built environment in general as well as how the public transport is operated.

Early testing reveals the possibility to find correlations between heart rate and position, which in turn could reveal the effect of spatial and transportation elements on the traveller. By targeting widely available hardware, the scalability for this tool is virtually endless, making it possible to collect large amounts of data and utilizing machine learning algorithms to analyse it.