Evaluating the Brownian Bridge Movement Model to Determine Regularities of People’s Movements

Abstract

The movements of animals or humans are characterized by starting points, transitions and end points, where starting and end points typically represent distinct locations. Knowledge of such locations and movement patterns is relevant to predict future movements or to detect regularities in movement behaviour. We present a Brownian bridge-based approach applied to human movement data to extract regularities of people staying in distinct locations. Such information is, for example, of interest in zoology (e.g. animal home range estimation) or health (e.g. detection of deviations from regular behaviour of people with cognitive impairments). To obtain information about where a person stayed, we derived the areas of their whereabouts from GPS trajectories by using a Brownian bridge movement model (BBMM). The resulting whereabouts areas were intersected with these GPS trajectories to create so-called whereabouts tables, which describe time of day, duration and place of a person's stay. The probability of finding a person in a particular area within a particular time window was determined. The whereabouts areas of two people were investigated and assessed by using two tailored quality measures: spatial accuracy and spatial uniqueness. In order to reduce the computational costs of BBMM, down-sampling was investigated. With respect to spatial accuracy, results improved by down-sampling.

A Framework for Evaluating Stay Detection Approaches

“…Additional measures are rarely used. Spatio-temporal measures have been introduced by Gröchenig and Schneider [13] and Venek et al [14]. As time-aware computation plays an important role for many application fields, runtime should additionally be considered.…”

“…Examples for grid-/cell-based approaches can be found in [13,24,25]. Examples for stochastic approaches are discussed in [14,26,27]. …”

“…Montoliu et al [12] called this users' forgetfulness and introduced a correction factor for precision and F-measure. Runtime or rather computation time has been addressed by Changqing et al [10], Gröchenig and Schneider [13], Porras Bernárdez [30], Venek et al [14] as an additional measure. Dedicated spatio-temporal measures have been introduced in Gröchenig and Schneider [13] and Venek et al [14].…”

“…For instance, the approach might detect more than one stay, if GPS measurement errors, which occurred more frequently during a single tagged stay, remain even after pre-processing. Experiences have shown [13,14] that values for recall, precision, and F-measure > 0.65 seem appropriate to determine an appropriate stay detection approach. Thus, thresholds are set to 0.65.…”

“…Therefore, this paper proposes an evaluation framework for stay detection approaches taking into account the aforementioned aspects. As stochastic and grid-/cell-based approaches have already been investigated in previous work [13,14] spatio-temporal clustering approaches are now investigated here. The proposed framework is validated by comparing three different spatio-temporal clustering approaches using two different datasets, namely ground truth data as well as application data from a field trial conducted with older (partly cognitively impaired) people.…”