Data about people movement is nowadays easy to collect by GPS technology embedded in smartphones. GPS routes provide information about position, time and speed, but further conclusion requires either prior information or data analysis. We propose a method to detect the movement type by segmentation of the GPS route using speed, direction and their derivatives, and by applying an inference algorithm via a second order Markov model. The method is able to classify most typical moving types such as motor vehicle, bicycle, run, walk and stop.

Systems that aim to predict user preferences and give recommendations are now commonly used in many systems such as online shops, social websites, and tourist guides. In this paper, we present a context aware personalized recommendation system on web and mobile, which recommends relevant location-based data from user collection and consisting of GPS routes and photos. We recommend three types of items: services, photos and GPS routes that are points of interests in user's surrounding. We score all items from database based on four aspects of relevance: location, content, time and network. In order to personalize the results we built user profile based on user's activity in the system. We study performance of the system within MOPSI.

No abstract

No abstract

Increasing availability of mobile devices with GPS receiver gives users the possibility to record and share a variety of location-based data, including GPS tracks. We describe a complete real-time system for acquisition, storage, querying, retrieval and visualization of GPS tracks. The main problems faced are how to store the data, how to access and how to visualize large amount of data. We propose to reduce the quantity of the data to be visualized, without affecting visualization quality. In order to achieve this, our system uses a fast polygonal approximation algorithm for different map scales along with a bounding box solution.