| 1. |
- Khoshahval, Samira, et al.
(författare)
-
A Personalized location-based and serendipity-oriented point of interest recommender assistant based on behavioral patterns
- 2018
-
Ingår i: Geospatial Technologies for All : Selected Papers of the 21st AGILE Conference on Geographic Information Science - Selected Papers of the 21st AGILE Conference on Geographic Information Science. - Cham : Springer International Publishing. - 1863-2246 .- 1863-2351. - 9783319782089 - 9783319782072 ; part F3, s. 271-289
-
Konferensbidrag (refereegranskat)abstract
- The technological evolutions have promoted mobile devices from rudimentary communication facilities to advanced personal assistants. According to the huge amount of accessible data, developing a time-saving and cost-effective method for location-based recommendations in mobile devices has been considered a challenging issue. This paper contributes a state-of-the-art solution for a personalized recommender assistant which suggests both accurate and unexpected point of interests (POIs) to users in each part of the day of the week based on their previously monitored, daily behavioral patterns. The presented approach consists of two steps of extracting the behavioral patterns from users’ trajectories and location-based recommendation based on the discovered patterns and user’s ratings. The behavioral pattern of the user includes their activity types in different parts of the day of the week, which is monitored via a combination of a stay point detection algorithm and an association rule mining (ARM) method. Having the behavioral patterns, the system exploits two recommendation procedures based on conventional collaborative filtering and K-furthest neighborhood model to recommend typical and serendipitous POIs to the users. The suggested POI list contains not only relevant and precise POIs but also unpredictable and surprising items to the users. To evaluate the system, the values of RMSE of each procedure were computed and compared. Conducted experiments proved the feasibility of the proposed solution.
|
|
| 2. |
- Mansourian, Ali, et al.
(författare)
-
Geospatial Technologies for All: Preface
- 2018
-
Ingår i: Geospatial technologies for all : Selected Papers of the 21st AGILE Conference on Geographic Information Science - Selected Papers of the 21st AGILE Conference on Geographic Information Science. - Cham : Springer International Publishing. - 1863-2246 .- 1863-2351. - 9783319782072 - 9783319782089 ; part F3
-
Tidskriftsartikel (övrigt vetenskapligt/konstnärligt)
|
|
| 3. |
- Pantazatou, Karolina, et al.
(författare)
-
Recommendation for Vegetation Information in Semantic 3D City Models Used in Urban Planning Applications
- 2024. - 1
-
Ingår i: Recent Advances in 3D Geoinformation Science : Proceedings of the 18th 3D GeoInfo Conference - Proceedings of the 18th 3D GeoInfo Conference. - 1863-2246 .- 1863-2351. - 9783031436994 - 9783031436987 ; , s. 3-30
-
Bokkapitel (refereegranskat)abstract
- Cities are growing in size and becoming increasingly dense. This situation calls for strategic planning of green infrastructure in the urban planning process. Safeguarding the green infrastructure is important for maintaining urban ecosystem services and increasing the well-being of urban populations. To facilitate appropriate urban planning that enables cities to grow sustainably, it is important that the geospatial community provides adequate vegetation information. In this study, we investigate the need for vegetation information in urban planning applications such as modelling ecosystem services and noise, as well as performing case studies of using vegetation information in daylight and solar energy simulations. Based on these investigations, we formulate a recommendation of how vegetation information should be included in 3D city models. The study is focused on the development of a Swedish national profile of CityGML, but many of the conclusions are general and universally applicable. In short, the recommendations are that: (1) the vegetation theme should follow CityGML 3.0 with some additional attributes (e.g., popular name of tree species) added as an application domain extension, (2) no LOD division is required for the vegetation information stored (but rather derived if necessary), (3) the vegetation theme should only contain 3D vegetation objects while the 2D vegetation is part of the land cover theme, and (4) the building specification (and city furniture specification) must include the possibility to store information on whether building roofs or facades (and walls) are covered with vegetation.
|
|
| 4. |
- Pilesjö, Petter, et al.
(författare)
-
An integrated raster-tin surface flow algorithm
- 2008
-
Ingår i: Lecture Notes in Geoinformation and Cartography. - Berlin, Heidelberg : Springer Berlin Heidelberg. - 1863-2351 .- 1863-2246. - 9783540777991 - 9783540778004 ; :199049, s. 237-255
-
Bokkapitel (refereegranskat)abstract
- In this chapter, an alternative surface flow algorithm is presented. The basic idea behind the algorithm is the use of the advantages of TIN-based algorithms within a raster based environment. A gridded raster DEM is used to create a ‘regular TIN’, over which surface flow is estimated. Since each facet in the TIN has a constant slope and slope direction, the estimations of, for example, flow velocity and diversion/convergence are less complicated compared to traditional ‘cell based’ solutions. The flow is treated as ‘water packages’, given specific (point) positions on the surface. The number of water packages per cell is initially set to eight, but this number can be increased or decreased. After each time step, the water packages have moved a certain distance (depending on slope and water depth), and new water packages have been created due to precipitation. In order to keep the number of water packages constant (to reduce memory and computer time), all water packages within a TIN facet are merged after each iteration. Parameters in time and space, e.g. precipitation, infiltration, vegetation and elevation, can all be loaded into the software.
|
|
| 5. |
|
|
| 6. |
- Soltani, Ali, et al.
(författare)
-
Exploring Shared-Bike Travel Patterns Using Big Data: Evidence in Chicago and Budapest
- 2019. - 1
-
Ingår i: Computational Urban Planning and Management for Smart Cities. - Cham : Springer International Publishing. - 1863-2351. - 9783030194239 - 9783030194246 ; , s. 53-68
-
Bokkapitel (refereegranskat)abstract
- Bike-sharing systems are an emerging form of sharing-mobility in manycities worldwide. The travel patterns of users that take advantage of smart devices to ride a shared-bicycle in two large cities (Chicago and Budapest) have been investigated, with analysis of approximately two million transaction data records associated with bike trips made over a three-month period in each location. Several aspects of user travel behavior—such as day and time of travel, frequency of usage, duration of usage, seasonal and peak/off-peak variations, major origin/destinations—have been included in this analysis. The results show that in both cities the bike-sharing option is a male-dominated alternative, particularly welcomed by younger groups, with the largest share of trips occurring in the afternoon peak. Appropriate usage of opensource big-data provides important lessons for successful vehicle sharing models,allowing the application of the findings to other cities and mobility options wherethese systems are still developing.
|
|
