hig.sePublikasjoner
Endre søk
Link to record
Permanent link

Direct link
BETA
Seipel, Stefan, ProfessorORCID iD iconorcid.org/0000-0003-0085-5829
Publikasjoner (10 av 16) Visa alla publikasjoner
Ren, Z., Jiang, B. & Seipel, S. (2019). Capturing and characterizing human activities using building locations in America. ISPRS International Journal of Geo-Information, 8(5), Article ID 200.
Åpne denne publikasjonen i ny fane eller vindu >>Capturing and characterizing human activities using building locations in America
2019 (engelsk)Inngår i: ISPRS International Journal of Geo-Information, ISSN 2220-9964, Vol. 8, nr 5, artikkel-id 200Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Capturing and characterizing collective human activities in a geographic space have become much easier than ever before in the big era. In the past few decades it has been difficult to acquire the spatiotemporal information of human beings. Thanks to the boom in the use of mobile devices integrated with positioning systems and location-based social media data, we can easily acquire the spatial and temporal information of social media users. Previous studies have successfully used street nodes and geo-tagged social media such as Twitter to predict users’ activities. However, whether human activities can be well represented by social media data remains uncertain. On the other hand, buildings or architectures are permanent and reliable representations of human activities collectively through historical footprints. This study aims to use the big data of US building footprints to investigate the reliability of social media users for human activity prediction. We created spatial clusters from 125 million buildings and 1.48 million Twitter points in the US. We further examined and compared the spatial and statistical distribution of clusters at both country and city levels. The result of this study shows that both building and Twitter data spatial clusters show the scaling pattern measured by the scale of spatial clusters, respectively, characterized by the number points inside clusters and the area of clusters. More specifically, at the country level, the statistical distribution of the building spatial clusters fits power law distribution. Inside the four largest cities, the hotspots are power-law-distributed with the power law exponent around 2.0, meaning that they also follow the Zipf’s law. The correlations between the number of buildings and the number of tweets are very plausible, with the r square ranging from 0.53 to 0.74. The high correlation and the similarity of two datasets in terms of spatial and statistical distribution suggest that, although social media users are only a proportion of the entire population, the spatial clusters from geographical big data is a good and accurate representation of overall human activities. This study also indicates that using an improved method for spatial clustering is more suitable for big data analysis than the conventional clustering methods based on Euclidean geometry.

sted, utgiver, år, opplag, sider
MDPI AG, 2019
Emneord
Big data, City-size distribution, Human activities, Scaling, Twitter, US building footprints
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-30544 (URN)10.3390/ijgi8050200 (DOI)00470965400001 ()2-s2.0-85066441533 (Scopus ID)
Tilgjengelig fra: 2019-08-22 Laget: 2019-08-22 Sist oppdatert: 2019-08-22bibliografisk kontrollert
Milutinovic, G., Ahonen-Jonnarth, U., Seipel, S. & Brandt, S. A. (2019). The impact of interactive visualization on trade-off-based geospatial decision-making. International Journal of Geographical Information Science, 33(10), 2094-2123
Åpne denne publikasjonen i ny fane eller vindu >>The impact of interactive visualization on trade-off-based geospatial decision-making
2019 (engelsk)Inngår i: International Journal of Geographical Information Science, ISSN 1365-8816, E-ISSN 1365-8824, Vol. 33, nr 10, s. 2094-2123Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

In a previous work we developed GISwaps, a novel method for geospatial decision-making based on Even Swaps. In this paper, we present the results of an evaluation of a visualization framework integrated with this method, implemented within a decision support system. This evaluation is based on two different studies. In the quantitative study, 15 student participants used GISwaps with no visual features, and 15 participants used GISwaps with the integrated visual framework, as the tool in a solar farm site location case study. The results of the quantitative evaluation show positive impact of the visualization in terms of increased coherency in trade-offs. The results also show a statistically significant difference in average trade-off values between the groups, with users from the non-visual group setting on average 20% higher trade-off values compared with the users in the visual group. In the qualitative study, we had one expert in GIS, two experts in decision-making and two experts in solar energy as a focus user group. Data in this study were obtained by observations and semi-structured interviews with the participants. The impact of the visualization framework was assessed positively by all participants in the expert group. 

sted, utgiver, år, opplag, sider
Taylor & Francis, 2019
Emneord
GIS decision-making, GISwaps, interactive visualization, tradeoffs
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-30515 (URN)10.1080/13658816.2019.1613547 (DOI)000470448200001 ()2-s2.0-85065643312 (Scopus ID)
Tilgjengelig fra: 2019-08-19 Laget: 2019-08-19 Sist oppdatert: 2019-08-19bibliografisk kontrollert
Andrée, M., Paasch, J. M., Paulsson, J. & Seipel, S. (2018). BIM and 3D property visualisation. In: FIG Congress 2018: Proceedings. Paper presented at FIG Congress 2018; Istanbul, Turkey; 6-11 May 2018. , Article ID 9367.
Åpne denne publikasjonen i ny fane eller vindu >>BIM and 3D property visualisation
2018 (engelsk)Inngår i: FIG Congress 2018: Proceedings, 2018, artikkel-id 9367Konferansepaper, Publicerat paper (Annet vitenskapelig)
Abstract [en]

The concept of 3D property has only existed a short period of time in Sweden, being introduced in 2004 and expanded in 2009 by the addition of condominium (apartment) ownership. It is therefore a rather new form of land management, and the demand for 3D property formation has not been as high as initially expected. There is however an increased interest in 3D property and ownership apartments today, also as being part of the nation’s geospatial infrastructure together with related 3D information for e.g. buildings, utility networks and other features. An effective management of 3D property is depending on, among other things, visualization, representation and storage of 3D real property data, such as legal boundaries and real property rights. There are at present a number of ongoing 3D development and research projects focusing on visualization and standardization of 3D cadastral boundaries. They are part of the national "Smart Built Environment" development and research program, which includes the use of BIM in the (future) 3D property formation process with focus on visualization of 3D real property and condominiums, and specification of requirements and evaluation of 3D digital real property information created and managed in the processes.

This paper presents the preliminary results of the working group on visualization of 3D boundaries in the project "Smart planning, construction and management processes throughout the life cycle". The aim is to test the results produced in the project "Information for planning, real property formation and building permission", working group "BIM for 3D property formation." The purpose of this working group is to set the requirements for and evaluate the test bed for 3D property information. The focus is on visualization of 3D property and ownership apartments. The proposed model for digitization and visualization of 3D property formation will be tested in a test bed environment. A pilot case from the Stockholm area is then used in the test bed to see how it could work in practice.

The expected outcome is recommendations for the exchange of documentation and other digital information in 3D processes, the visualization of legal boundaries for stakeholders, registration of legal 3D objects in the Swedish national real property register and how to communicate 3D models to right holders/stakeholders for 3D property and condominiums and the property market, as well as suggestions for a homogeneous, effective and digital flow of 3D information to be used by actors and other stakeholders in the property formation, planning and building processes.

Emneord
3D Real Property, Property Formation, BIM, Cadastre, standardization, Sweden
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-28329 (URN)
Konferanse
FIG Congress 2018; Istanbul, Turkey; 6-11 May 2018
Prosjekter
Smart Built Environment. "Smarta plan-, bygg-, förvaltnings- och nyttjandeprocesser över hela livscykeln"
Tilgjengelig fra: 2018-10-16 Laget: 2018-10-16 Sist oppdatert: 2018-12-03bibliografisk kontrollert
Aslani, M., Seipel, S. & Wiering, M. (2018). Continuous residual reinforcement learning for traffic signal control optimization. Canadian journal of civil engineering (Print), 45(8), 690-702
Åpne denne publikasjonen i ny fane eller vindu >>Continuous residual reinforcement learning for traffic signal control optimization
2018 (engelsk)Inngår i: Canadian journal of civil engineering (Print), ISSN 0315-1468, E-ISSN 1208-6029, Vol. 45, nr 8, s. 690-702Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Traffic signal control can be naturally regarded as a reinforcement learning problem. Unfortunately, it is one of the most difficult classes of reinforcement learning problems owing to its large state space. A straightforward approach to address this challenge is to control traffic signals based on continuous reinforcement learning. Although they have been successful in traffic signal control, they may become unstable and fail to converge to near-optimal solutions. We develop adaptive traffic signal controllers based on continuous residual reinforcement learning (CRL-TSC) that is more stable. The effect of three feature functions is empirically investigated in a microscopic traffic simulation. Furthermore, the effects of departing streets, more actions, and the use of the spatial distribution of the vehicles on the performance of CRL-TSCs are assessed. The results show that the best setup of the CRL-TSC leads to saving average travel time by 15% in comparison to an optimized fixed-time controller.

sted, utgiver, år, opplag, sider
NRC Research Press, 2018
Emneord
continuous state reinforcement learning, adaptive traffic signal control, microscopic traffic simulation
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-27845 (URN)10.1139/cjce-2017-0408 (DOI)000440632100009 ()2-s2.0-85051122432 (Scopus ID)
Tilgjengelig fra: 2018-09-05 Laget: 2018-09-05 Sist oppdatert: 2018-09-05bibliografisk kontrollert
Ooms, K., Åhlén, J. & Seipel, S. (2018). Detecting Collapsed Buildings in Case of Disaster: Which Visualisation Works Best?. In: Kiefer, Peter Giannopoulos, Ioannis Göbel, Fabian Raubal, Martin Duchowski, Andrew T. (Ed.), Eye Tracking for Spatial Research: Proceedings of the 3rd International Workshop. Paper presented at 3rd International Workshop on Eye Tracking for Spatial Research, January 14, 2018, Zurich, Switzerland. Zurich
Åpne denne publikasjonen i ny fane eller vindu >>Detecting Collapsed Buildings in Case of Disaster: Which Visualisation Works Best?
2018 (engelsk)Inngår i: Eye Tracking for Spatial Research: Proceedings of the 3rd International Workshop / [ed] Kiefer, Peter Giannopoulos, Ioannis Göbel, Fabian Raubal, Martin Duchowski, Andrew T., Zurich, 2018Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

A user study is conducted to evaluate the efficiency and effectiveness of two types of visualizations to identify damage sites in case of disaster. The test consists out 36 trials (18 for each visualisation) and in each trial an area of 1x1km, located in Ghent, is displayed on a screen. This image shows the combined height information from before and after the disaster. The first visualisation, page flipping, is based on greyscale images with height information from the pre- and post-disaster situation between which users can switch manually. The second visualisation, difference image, is a result of subtracting the heights (before versus after) and assigning a blue-white-red colour ramp. In order to simulate the urgency with which the data is captured, systematic and random imperfections are introduced in the post-disaster data. All participants’ mouse and key interactions are logged, which is further complemented by the registration of their eye movements. This give insights the visualizations’ efficiency, effectiveness and the overall search strategies of the participants.

sted, utgiver, år, opplag, sider
Zurich: , 2018
Emneord
user study; mouse & key logging; eye tracking; emergency response; damage assessment
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-29175 (URN)10.3929/ethz-b-000222480 (DOI)
Konferanse
3rd International Workshop on Eye Tracking for Spatial Research, January 14, 2018, Zurich, Switzerland
Tilgjengelig fra: 2019-01-25 Laget: 2019-01-25 Sist oppdatert: 2019-02-13bibliografisk kontrollert
Aslani, M., Mesgari, M. S., Seipel, S. & Wiering, M. (2018). Developing adaptive traffic signal control by actor-critic and direct exploration methods. Proceedings of the Institution of Civil Engineers: Transport, 172(5), 289-298
Åpne denne publikasjonen i ny fane eller vindu >>Developing adaptive traffic signal control by actor-critic and direct exploration methods
2018 (engelsk)Inngår i: Proceedings of the Institution of Civil Engineers: Transport, ISSN 0965-092X, E-ISSN 1751-7710, Vol. 172, nr 5, s. 289-298Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

Designing efficient traffic signal controllers has always been an important concern in traffic engineering. This is owing to the complex and uncertain nature of traffic environments. Within such a context, reinforcement learning has been one of the most successful methods owing to its adaptability and its online learning ability. Reinforcement learning provides traffic signals with the ability automatically to determine the ideal behaviour for achieving their objective (alleviating traffic congestion). In fact, traffic signals based on reinforcement learning are able to learn and react flexibly to different traffic situations without the need of a predefined model of the environment. In this research, the actor-critic method is used for adaptive traffic signal control (ATSC-AC). Actor-critic has the advantages of both actor-only and critic-only methods. One of the most important issues in reinforcement learning is the trade-off between exploration of the traffic environment and exploitation of the knowledge already obtained. In order to tackle this challenge, two direct exploration methods are adapted to traffic signal control and compared with two indirect exploration methods. The results reveal that ATSC-ACs based on direct exploration methods have the best performance and they consistently outperform a fixed-time controller, reducing average travel time by 21%.

sted, utgiver, år, opplag, sider
Thomas Telford, 2018
Emneord
communications & control systems; traffic engineering; transport management
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-28332 (URN)10.1680/jtran.17.00085 (DOI)
Tilgjengelig fra: 2018-10-16 Laget: 2018-10-16 Sist oppdatert: 2019-10-11bibliografisk kontrollert
Ooms, K., Åhlén, J. & Seipel, S. (2018). Efficiency and effectiveness in case of disaster: a visual damage assessment test. In: Proceedings of the International Cartographic Association (Proceedings of the ICA): . Paper presented at The 28th International Cartographic Conference took place, 2–7 July 2017, Washington D.C., USA. , 1, Article ID 86.
Åpne denne publikasjonen i ny fane eller vindu >>Efficiency and effectiveness in case of disaster: a visual damage assessment test
2018 (engelsk)Inngår i: Proceedings of the International Cartographic Association (Proceedings of the ICA), 2018, Vol. 1, artikkel-id 86Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

 A user study is conducted to evaluate the efficiency and effectiveness of two types of visualizations to identify damages sites in case of disaster. The test consists out 36 trials (18 for each visualisation) and in each trial an area of 1×1km, located in Ghent, is displayed on a screen. This image shows the combined height information from before and after the disaster. The first visualisation, page flipping, is based on greyscale images with height information from the pre- and post-disaster situation between which users can switch manually. The second visualisation, difference image, is a result of subtracting the heights (before versus after) and assigning a blue-white-red colour ramp. In order to simulate the urgency with which the data is captured, systematic and random imperfections are introduced in the post-disaster data. All participants’ mouse and key interactions are logged, which is further complemented by the registration of their eye movements. This give insights the visualizations’ efficiency, effectiveness and the overall search strategies of the participants.

Emneord
User study, mouse & key logging, eye tracking, emergency response, damage assessment
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-29174 (URN)10.5194/ica-proc-1-86-2018 (DOI)
Konferanse
The 28th International Cartographic Conference took place, 2–7 July 2017, Washington D.C., USA
Tilgjengelig fra: 2019-01-25 Laget: 2019-01-25 Sist oppdatert: 2019-02-13bibliografisk kontrollert
Milutinovic, G., Ahonen-Jonnarth, U. & Seipel, S. (2018). GISwaps: A New Method for Decision Making in Continuous Choice Models Based on Even Swaps. International Journal of Decision Support System Technology, 10(3), 57-78
Åpne denne publikasjonen i ny fane eller vindu >>GISwaps: A New Method for Decision Making in Continuous Choice Models Based on Even Swaps
2018 (engelsk)Inngår i: International Journal of Decision Support System Technology, ISSN 1941-6296, E-ISSN 1941-630X, Vol. 10, nr 3, s. 57-78Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

This article describes how continuous GIS-MCDM problems are commonly managed by combining some weighting method based on pairwise comparisons of criteria with an aggregation method. The reliability of this approach may be questioned, though. First, assigning weights to criteria, without taking into consideration the actual consequences or values of the alternatives, is in itself controversial. Second, the value functions obtained by this approach are in most cases linear, which is seldom the case in reality. The authors present a new method for GIS-MCDM in continuous choice models based on Even Swaps. The method is intuitive and easy to use, based on value trade-offs, and thus not relying on criteria weighting. Value functions obtained when using the method may be linear or non-linear, and thereby are more sensitive to the characteristics of the decision space. The performed case study showed promising results regarding the reliability of the method in GIS-MCDM context.

sted, utgiver, år, opplag, sider
IGI Global, 2018
Emneord
Continuous Choice Models, Even Swaps, GIS-MCDM, Trade-Offs, Value Functions
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-26576 (URN)10.4018/IJDSST.2018070104 (DOI)000455413900004 ()2-s2.0-85047766922 (Scopus ID)
Tilgjengelig fra: 2018-05-16 Laget: 2018-05-16 Sist oppdatert: 2019-03-19bibliografisk kontrollert
Åhlén, J. & Seipel, S. (2018). Mapping of roof types in orthophotos using feature descriptors. In: International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM: Proceedings of the International Multidisciplinary Scientific GeoConference SGEM. Paper presented at 18th International Multidisciplinary Scientific GeoConference SGEM,30th June - 9th July 2018, Albena, Bulgaria (pp. 285-291). , 18
Åpne denne publikasjonen i ny fane eller vindu >>Mapping of roof types in orthophotos using feature descriptors
2018 (engelsk)Inngår i: International Multidisciplinary Scientific GeoConference Surveying Geology and Mining Ecology Management, SGEM: Proceedings of the International Multidisciplinary Scientific GeoConference SGEM, 2018, Vol. 18, s. 285-291Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

In the context of urban planning, it is very important to estimate the nature of the roof of every building and, in particular, to make the difference between flat roofs and gable ones. This analysis is necessary in seismically active areas. Also in the assessment of renewable energy projects such solar energy, the shape of roofs must be accurately retrieved. In order to perform this task automatically on a large scale, aerial photos provide a useful solution. The goal of this research project is the development of algorithm for accurate mapping of two different roof types in digital aerial images. The algorithm proposed in this paper includes several components: pre-processing step to reduce illumination differences of individual roof surfaces, statistical moments calculation and color indexing. Roof models are created and saved as masks with feature specific descriptors. Masks are then used to mark areas that contain elements of the different roof types (e.g. gable and hip). The final orthophoto visualize an accurate position of each of the roof types. The result is evaluated using precision recall method.

Serie
Proceedings of the International Multidisciplinary Scientific GeoConference SGEM, ISSN 1314-2704 ; 2.2
Emneord
URBAN planning, ROOFS, BUILDINGS, ALGORITHMS, AERIAL photography, classification, orthophoto, Roof types, segmentation
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-28694 (URN)10.5593/sgem2018/2.2/S08.036 (DOI)2-s2.0-85058885965 (Scopus ID)
Konferanse
18th International Multidisciplinary Scientific GeoConference SGEM,30th June - 9th July 2018, Albena, Bulgaria
Tilgjengelig fra: 2018-11-28 Laget: 2018-11-28 Sist oppdatert: 2019-01-07bibliografisk kontrollert
Liu, F. & Seipel, S. (2018). Precision study on augmented reality-based visual guidance for facility management tasks. Automation in Construction, 90, 79-90
Åpne denne publikasjonen i ny fane eller vindu >>Precision study on augmented reality-based visual guidance for facility management tasks
2018 (engelsk)Inngår i: Automation in Construction, ISSN 0926-5805, E-ISSN 1872-7891, Vol. 90, s. 79-90Artikkel i tidsskrift (Fagfellevurdert) Published
Abstract [en]

One unique capability of augmented reality (AR) is to visualize hidden objects as a virtual overlay on real occluding objects. This “X-ray vision” visualization metaphor has proved to be invaluable for operation and maintenance tasks such as locating utilities behind a wall. Locating virtual occluded objects requires users to estimate the closest projected positions of the virtual objects upon their real occluders, which is generally under the influence of a parallax effect. In this paper we studied the task of locating virtual pipes behind a real wall with “X-ray vision” and the goal is to establish relationships between task performance and spatial factors causing parallax through different forms of visual augmentation. We introduced and validated a laser-based target designation method which is generally useful for AR-based interaction with augmented objects beyond arm's reach. The main findings include that people can mentally compensate for the parallax error when extrapolating positions of virtual objects on the real surface given traditional 3D depth cues for spatial understanding. This capability is, however, unreliable especially in the presence of the increasing viewing offset between the users and the virtual objects as well as the increasing distance between the virtual objects and their occluders. Experiment results also show that positioning performance is greatly increased and unaffected by those factors if the AR support provides visual guides indicating the closest projected positions of virtual objects on the surfaces of their real occluders.

Emneord
Augmented reality “X-ray vision”, Experiment, Facility management, Positioning task, Precision study, Spatial judgment, Augmented reality, Experiments, Geometrical optics, Location, Office buildings, Positioning tasks, Precision studies, Spatial judgments, X-ray vision, X rays
HSV kategori
Identifikatorer
urn:nbn:se:hig:diva-26238 (URN)10.1016/j.autcon.2018.02.020 (DOI)000430520300007 ()2-s2.0-85042273035 (Scopus ID)
Tilgjengelig fra: 2018-03-15 Laget: 2018-03-15 Sist oppdatert: 2018-05-31bibliografisk kontrollert
Organisasjoner
Identifikatorer
ORCID-id: ORCID iD iconorcid.org/0000-0003-0085-5829