Skip to Main Content
Opportunistic, mobility-assisted, or encounter networking is a technique to disseminate data in a store-and-forward manner by means of spontaneously connecting mobile devices. New networking opportunities of moving devices can be exploited in addition to traditional wireless infrastructure networks or in absence of these networks. Algorithms for opportunistic data dissemination often make use of information about the future path of mobile entities. The availability of this information is reasonable for traveling by, e.g., public transport lines or vehicles following a navigation system, while other, more unstructured movement activities often lack this information and new techniques are required to derive similar useful movement information. By observing movement characteristics like average velocities or revisiting patterns, estimates about the likelihood of getting in contact with other devices can be derived and forwarding capabilities can be estimated. Our approach goes one step further by modeling the users' movement activities derived from movement patterns. Activity descriptions are useful for aggregating movement patterns into a notion meaningful to users. Additionally, movement activities can be used to estimate user caused network traffic and, in case movement patterns are uncertain or fragmentary, knowledge about activities may help to faster estimate average movement characteristics. The main objective of this paper is to introduce an approach to relate activities to an observed multi-variate mobility characteristic based on the Naïve Bayes classifier. Therefore, we introduce and use the commonly considered mobility characteristics velocity, direction change, pause time, flight length, number of revisited positions, time between revisits, and mobility range. The approach is applied to four typical urban movement use case activities and classification results are presented based on experimental GPS traces.