Generating a synthetic probabilistic daily activity-location schedule using large-scale, long-term and low-frequency smartphone GPS data with limited activity information

Household travel survey data is a critical input to travel behavior modeling, and it also can be used to generate trip schedules for activity-based traffic simulation. With emerging information and communication technology (ICT) tools like smartphones, the collection of passive datasets for travelers' real-time information becomes available. Smartphone GPS survey apps have emerged to be a popular tool for conducting household travel surveys. Most existing studies employ high frequency smartphone GPS data and collect accurate activity information. However, their study periods are still rather short, ranging from a few days to a few weeks. For a long-term GPS survey, the issues of missing activity information and sparse GPS data are inevitable and must be addressed carefully. This paper uses 7-month low-frequency smartphone GPS data collected from over 2000 participants, who report 5 most frequently visited locations weekly. The essential goal is to develop a synthetic model of daily activity-location scheduling to capture data with both known and unknown activities. To handle missing activity data, this research develops a new probabilistic approach, which measures the probability of visiting a place by three scores, global visit score (GVS), temporal visit score (TVS), and periodical visit score (PVS). Three different levels of activity-location schedule are modeled respectively. The first level handles only those data with known activities, while data with unknown activities are disregarded. The second takes unknown activities into account but combines all types of them into a single category. The third one models each location with unknown activities separately. These models are able to generate activity location schedule in different levels of detail for activity-based traffic simulator. After developing activity-location schedule models, both individual and aggregated validation processes are performed with simulation. The validation result shows that the simulated proportion of activity types and activity duration are close to the survey data, indicating the effectiveness of the proposed approaches. This research sheds a light on building sustainable and long-term travel survey using GPS data with missing activity information. In addition, this study will be valuable to model infectious disease transmission, e.g. COVID-19 and assess health risk in urban areas.