The eCOMPASS multimodal tourist tour planner. Issue 21 (30th November 2015)

• Record Type: Journal Article
• Authors: Gavalas, Damianos; Kasapakis, Vlasios; Konstantopoulos, Charalampos; Pantziou, Grammati; Vathis, Nikolaos; Zaroliagis, Christos
• Is Part Of: Expert systems with applications. Volume 42:Issue 21(2015)
• Page Start: 7303
• Page End: 7316
• Publication Date: 2015-11-30
• Subjects: Tourist Trip Design Problem -- Multimodal tour planning -- Urban transportation -- Orienteering Problem -- Time window -- Time dependent travel time -- Context awareness -- Web service -- Mobile application; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2015.05.046
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: Personalized near-optimal multiple-day tours (via several POIs) for tourists. eCOMPASS: the first mobile tour planner to consider public transit transfers among POIs. Incorporating lunch breaks in tour planning. Arbitrary start/end locations for each daily tour. High-performance tour planning algorithm tested on real tourist destinations. Abstract: Tour planning represents a challenging task for individuals visiting unfamiliar tourist destinations, mainly due to the availability of numerous attractions (points of interest, POIs) and the complexity of metropolitan public transit networks. Several web and mobile tourist city guides already support personalized tour recommendations. However, they exclusively consider walking tours; namely, they fail in motivating tourists to use public transportation for reaching far located important POIs, thereby compromising the perceived overall attractiveness of recommended tours. In this paper, we introduce eCOMPASS, a context-aware web/mobile application which derives personalized multimodal tours via selected urban attractions. eCOMPASS is the only available research or commercial tour planner that assists the way arounds of tourists through public transit. Far beyond than just providing navigational aid, eCOMPASS incorporates multimodality (i.e. time dependency) within its routing logic aiming at deriving near-optimal sequencing of POIs along recommended tours so as to best utilize the time available for sightseeing and minimize waiting time at transit stops. Further advancing the state of the art, eCOMPASS allows users to define arbitrary start/end locations (e.g. the current location of a mobile user) rather than choosing among a fixed set of locations. Last, eCOMPASS may assist in scheduling lunch breaks at affordable restaurants, conveniently located along the recommended tours. The provision of the above mentioned unique features of eCOMPASS is based on modeling and solving a complex optimization problem which takes into account a long list of problem variables and constraints. This paper describes the routing algorithm which comprises the core functionality of eCOMPASS. Further, it discusses the implementation details of the web and mobile eCOMPASS applications using the metropolitan areas of Athens (Greece) and Berlin (Germany) as case studies. Evaluation results report positive user attitude as to the tour planning output with respect to attractiveness, meaningfulness and the overall perceived utility.