| 1. |
|
|
| 2. |
- Richter, Kai-Florian, et al.
(författare)
-
Current topics and challenges in geoAI
- 2023
-
Ingår i: Künstliche Intelligenz. - : Springer Nature. - 0933-1875 .- 1610-1987. ; 37, s. 11-16
-
Tidskriftsartikel (refereegranskat)abstract
- Taken literally, geoAI is the use of Artificial Intelligence methods and techniques in solving geo-spatial problems. Similar to AI more generally, geoAI has seen an influx of new (big) data sources and advanced machine learning techniques, but also a shift in the kind of problems under investigation. In this article, we highlight some of these changes and identify current topics and challenges in geoAI.
|
|
| 3. |
- Richter, Kai-Florian, et al.
(författare)
-
Icon-based Navigation
- 2018
-
Ingår i: Geospatial Technologies for All. - Lund : Lund University. - 9783319782089
-
Konferensbidrag (refereegranskat)abstract
- Icon-based navigation uses a minimalist approach to mobile navigation assistance by offering navigators only icon displays representing landmark objects at waypoints along a route in an indoor environment. In this paper, we motivate this new concept and its usefulness, present a first prototype implementation exploring the concept, and results of an initial empirical evaluation. While results are not fully conclusive, they point to the potential of this kind of navigation assistance.
|
|
| 4. |
- Richter, Kai-Florian, et al.
(författare)
-
Inside an autonomous car : some open issues and social implications
- 2023
-
Ingår i: CarSA Workshop. - : Association for Computing Machinery (ACM).
-
Konferensbidrag (refereegranskat)abstract
- Driving is a highly social activity with various interactions between the different actors involved in traffic. Autonomous vehicles will pose several challenges to the social fabric of traffic and, as most new technology, will lead to changes in human behavior. This will surely hold for interactions between autonomous vehicles and actors \emph{outside} the vehicle. However and importantly, autonomous vehicles will also alter existing and introduce new social situations and interactions for those \emph{inside} the vehicle, which appears to be an under-researched topic. This paper will focus on the passengers of autonomous vehicles. We will discuss some of the implications and expected changes in the relationship between a car and those inside it, and highlight some of the open issues of being enclosed and driven by a highly complex, largely black-box AI system on wheels.
|
|
| 5. |
- Kashian, Alireza, et al.
(författare)
-
Automatic analysis of positional plausibility for points of interest in OpenStreetMap using coexistence patterns
- 2019
-
Ingår i: International Journal of Geographical Information Science. - : Taylor & Francis Group. - 1365-8816 .- 1365-8824 .- 1362-3087. ; 33:7, s. 1420-1443
-
Tidskriftsartikel (refereegranskat)abstract
- In the past decade, Volunteered Geographic Information (VGI) has emerged as a new source of geographic information, making it a cheap and universal competitor to existing authoritative data sources. The growing popularity of VGI platforms, such as OpenStreetMap (OSM), would trigger malicious activities such as vandalism or spam. Similarly, wrong entries by unexperienced contributors adds to the complexities and directly impact the reliability of such databases. While there are some existing methods and tools for monitoring OSM data quality, there is still a lack of advanced mechanisms for automatic validation. This paper presents a new recommender tool which evaluates the positional plausibility of incoming POI registrations in OSM by generating near real-time validation scores. Similar to machine learning techniques, the tool discovers, stores and reapplies binary distance-based coexistence patterns between one specific POI and its surrounding objects. To clarify the idea, basic concepts about analysing coexistence patterns including design methodology and algorithms are covered in this context. Furthermore, the results of two case studies are presented to demonstrate the analytical power and reliability of the proposed technique. The encouraging results of this new recommendation tool elevates the need for developing reliable quality assurance systems in OSM and other VGI projects.
|
|
| 6. |
- Ahlgren, Per, et al.
(författare)
-
Field normalized citation rates, field normalized journal impact and Norwegian weights for allocation of university research funds
- 2012
-
Ingår i: Scientometrics. - : Springer. - 0138-9130 .- 1588-2861. ; 92:2, s. 767-780
-
Tidskriftsartikel (refereegranskat)abstract
- We compared three different bibliometric evaluation approaches: two citationbased approaches and one based on manual classification of publishing channels into quality levels. Publication data for two universities was used, and we worked with two levels of analysis: article and department. For the article level, we investigated the predictive power of field normalized citation rates and field normalized journal impact with respect to journal level. The results for the article level show that evaluation of journals based on citation impact correlate rather well with manual classification of journals into quality levels. However, the prediction from field normalized citation rates to journal level was only marginally better than random guessing. At the department level, we studied three different indicators in the context of research fund allocation within universities and the extent to which the three indicators produce different distributions of research funds. It turned out that the three distributions of relative indicator values were very similar, which in turn yields that the corresponding distributions of hypothetical research funds would be very similar.
|
|
| 7. |
- Bergström, Jenny, et al.
(författare)
-
Becoming materials : material forms and forms of practice
- 2010
-
Ingår i: Digital Creativity. - : Routledge. - 1462-6268 .- 1744-3806. ; 21:3, s. 155-172
-
Tidskriftsartikel (refereegranskat)abstract
- As a result of development toward ‘smart’ materials, materials now enable an expanding range of aesthetic expressions and user experiences. These materials are fundamentally temporal in their capacity to assume multiple, discrete states of expression that can be repeatedly and minutely controlled. These materials come to be, or become, only over time and in context—they are becoming materials. Thus, in the development and application of such materials, we must engage more extensively with the experience of materials in practices of design and of use. This paper introduces and discusses the concept of becoming materials—as well as the implications for practice—through a series of examples from our own practice-led research within art, design and architecture. Coming to terms with the implications for material practices of design and of use, we suggest, requires the development of new concepts and methods for doing and studying the design of becoming materials.
|
|
| 8. |
- Guo, Li, et al.
(författare)
-
Design of a garment-based sensing system for breathing monitoring
- 2013
-
Ingår i: Textile research journal. - : SAGE Publications. - 0040-5175 .- 1746-7748. ; 83:5, s. 499-509
-
Tidskriftsartikel (refereegranskat)abstract
- The long-term monitoring of biophysiological signals requires new types of sensor systems that are wearable and at the same time convenient for the users. This paper describes the design of a novel garment-based sensing system for the long-term monitoring of breathing rhythm. The system concept was realized in a prototype garment, integrated with coated piezoresistive sensors. The prototype garment was tested by five subjects, and compared with a standard piezoelectric respiratory belt. Each signal was quantitatively and qualitatively evaluated in the time and frequency domain to make sure that no medical and diagnostic information was lost. The results showed a good agreement between the garment-based sensors and the standard reference, where errors occurred only when the breathing rate was extremely high. The garment-based sensor system could also distinguish the predominance breathing compartment (chest versus abdominal breathing). The system could detect a 10 s pause in breathing, which could be of importance in studies of sleep apnea. A garment-based sensing system maintains the accuracy of the signal quality without reducing the comfort for the user. It makes possible long-term ambulatory monitoring and has home-based healthcare applications.
|
|
| 9. |
- Blöcker, Christopher, et al.
(författare)
-
Similarity-based Link Prediction from Modular Compression of Network Flows
-
Annan publikation (övrigt vetenskapligt/konstnärligt)abstract
- Node similarity scores constitute a foundation for machine learning in graphs. Besides clustering, node classification, and anomaly detection, they are a basis for link prediction with critical applications in biological systems, information networks, and recommender systems. Recent works on link prediction use vector space embeddings to calculate node similarities. While these methods can provide good performance in undirected networks, they have several disadvantages: limited interpretability, problem-specific hyperparameter tuning, manual model fitting through dimensionality reduction, and poor performance of symmetric similarities in directed link prediction. To address these issues, we propose MapSim, a novel information-theoretic approach to assess node similarities based on modular compression of network flows. Different from vector space embeddings, MapSim represents nodes in a discrete, non-metric space of communities and yields asymmetric similarities suitable to predict directed and undirected links in an unsupervised fashion. The resulting similarities can be explained based on a network's hierarchical modular organisation, facilitating interpretability. MapSim naturally accounts for Occam's razor, leading to parsimonious representations of clusters at multiple scales. Addressing unsupervised link prediction, we compare MapSim to popular embedding-based algorithms across 47 data sets of networks from a few hundred to hundreds of thousands of nodes and millions of links. Our analysis shows that MapSim's average performance across all networks is more than 7% higher than its closest competitor, outperforming all embedding methods in 14 of the 47 networks, and a more than 33% better worst-case performance. Our method demonstrates the potential of compression-based approaches in graph representation learning, with promising applications in other graph learning tasks.
|
|
| 10. |
- Blöcker, Christopher, 1986-
(författare)
-
Through the coding-lens : community detection and beyond
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- We live in a highly-connected world and find networks wherever we look: social networks, public transport networks, telecommunication networks, financial networks, and more. These networks can be immensely complex, comprising potentially millions or even billions of inter-connected objects. Answering questions such as how to control disease spreading in contact networks, how to optimise public transport networks, or how to diversify investment portfolios requires understanding each network's function and working principles.Network scientists analyse the structure of networks in search of communities: groups of objects that form clusters and are more connected to each other than the rest. Communities form the building blocks of networks, corresponding to their sub-systems, and allow us to represent networks with coarse-grained models. Analysing communities and their interactions helps us unravel how networks function.In this thesis, we use the so-called map equation framework, an information-theoretic community-detection approach. The map equation follows the minimum description length principle and assumes complete data in networks with one node type. We challenge these assumptions and adapt the map equation for community detection in networks with two node types and incomplete networks where some data is missing. We move beyond detecting communities and derive approaches for how, based on communities, we can identify influential objects in networks, and predict links that do not (yet) exist.
|
|
