Path routing personalization
The increasing user access to geo-localized mobile devices enables the provision of navigation recommendations that suit the needs of individual users at-scale.
In this line of my research I focus on the development of personalized path routing algorithms for crowds inside physical spaces, in particular museums. Which exhibits and other Points Of Interest should we recommend to the visitors according to their interests, available time, and the way they prefer to move? How can we accommodate these individual objectives with museum-wide ones, like the need for low congestion around the most popular exhibits? I experimentally validate the developed algorithms through crowd simulations, calibrated according to the movement behavior of the specific type of crowd, as well as through experiments with real museum visitors. |
Related Publications |
Improving museum visitors’ Quality of Experience through intelligent recommendations: A visiting style-based approachLykourentzou I., Dagka F., Papadaki K., Lepouras G., Vassilakis C. (2012), Enterprise Information Systems, 6(1), 1-53.We examine the effect of smart routing and recommendations on improving the Quality of Experience of museum visitors. The novelty of our approach consists of taking into account not only user interests but also their visiting styles, as well as modeling the museum not as a sterile space but as a location where crowds meet and interact, impacting each visitor’s Quality of Experience. We validate the proposed approach on a custom-made simulator tailored for the museum path routing problem. Results are promising and future potential and directions are discussed.
|
Software |
Museum crowd simulator
This custom-made museum simulator developed in collaboration with the team at LIST, for the purposes of the Experimedia BLUE project, models the interaction of visitors with the physical space of the museum. Built using the Java and Javascript technologies, it features a user-friendly front-end and a backend with multiple parameters. Among these we find museum characteristics (topology, room number and exhibit density), visitor characteristics (visiting style, interests per exhibit, available time, walking speed, crowd tolerance), and a range of path routing personalization algorithms.
The simulator provides an overview of how the visitor crowd will behave inside the museum, how much will their Quality of Experience be affected by path recommendations and the effect of visitor movement on congestion inside the museum. The simulator can also be used to re-organise the exhibit topology and select the best path recommendation strategies, to increase the visitors' Quality of Experience. Copyright: LIST |
Related Projects |
Experimedia BLUE
Funding: FP7, European Commission |