A Multi-lingual pedestrian navigation and campusguidance system using CloudMade API
01 Jan 2009-
TL;DR: The importance of a good campus navigation system with a multi-lingual interface helps in personalizing the system according to the user’s preference for the language of interaction.
Abstract: The importance of a good campus navigation system cannot be ignored as the users will
vary from students, special guests, visitors and multi-lingual attendees. Providing a
navigation and guidance system with a multi-lingual interface helps in personalizing the
system according to the user’s preference for the language of interaction. [Pascal Neis,
2009] is an example of a multi-lingual routing application for navigation developed at the
University of Bonn where optimal paths are generated with textual description in the
user’s preferred language. Natural language generation (NLG) is the subfield of artificial
intelligence and computational linguistics. It is concerned with the construction of
computer systems that can produce understandable texts in human languages and form
some underlying non-linguistic representation of information in order to meet specified
communicative goals [McDonald D.D., 1987].
Citations
More filters
01 Jan 2014
TL;DR: Overall coverage was extremely poor, as more than 94 % of the country consisted of ‘incomplete regions’ (regions with few or no data), however, OSM data has grown quickly, according to a comparison of three years, 2011 to 2013.
Abstract: OpenStreetMap (OSM) has been successfully applied all around the world, especially in developed western countries, but this is the first study of the quality of OSM data in China. Two data quality elements, completeness and positional accuracy, were chosen to conduct the assessment via a comparison against Baidu datasets. This chapter quantitatively depicts some characteristics of the distribution of OSM data based on the density of line and point features. The analysis showed that 71 % of the OSM data was less detailed than the Baidu datasets, but on average 66 % of OSM data was accurate. The OSM data for Beijing and Shanghai is most complete with high positional accuracy. Overall coverage was extremely poor, as more than 94 % of the country consisted of ‘incomplete regions’ (regions with few or no data). However, OSM data has grown quickly, according to a comparison of three years, 2011 to 2013. More interestingly, OSM contained more detailed information in some poor areas, which could be an improvement over datasets provided for normal users by commercial or governmental agencies.
56 citations
TL;DR: A mechanistic procedure for determining the level of granularity is proposed and applied to a place descriptions corpus and results show that the procedure delivers generally good results in agreement with the corresponding map locations.
30 citations
01 Jan 2014
TL;DR: Thematic Cartography for the Society as discussed by the authors is a survey of the best 30 papers presented at the 5th InternationalConference on Cartography and GIS held in Albena, Bulgaria in 2014.
Abstract: “Thematic Cartography for the Society” is prepared on the basis
of the best 30 papers presented at the 5th International
Conference on Cartography and GIS held in Albena, Bulgaria in
2014. The aim of the conference is to register new knowledge
and shape experiences about the latest achievements in
cartography and GIS worldwide. At the same time, the focus is
on the important European region - the Balkan Peninsula. The
following topics are covered: User-friendly Internet and Web
Cartography; User-oriented Map Design and Production;
Context-oriented Cartographic Visualization; Map Interfaces for
Volunteered Geographic Information; Sensing Technologies and
their Integration with Maps; Cartography in Education. Focus on
user-oriented cartographic approaches.
20 citations
25 Nov 2013
TL;DR: A field study was run in a university campus context, aiming to identify key information required in a mobile pedestrian navigation system for user traveling in university campuses, and investigated user's interactions and behaviours while they were navigating in the campus environment.
Abstract: University campuses have thousands of new students, staff and visitors every year. For those who are unfamiliar with the campus environment, an effective pedestrian navigation system is essential to orientate and guide them around the campus. Compared to traditional navigation systems, such as physical signposts and digital map kiosks, a mobile pedestrian navigation system provides advantages in terms of mobility, sensing capabilities, weather-awareness when the user is on the go. However, how best to design a mobile pedestrian navigation system for university campuses is still vague due to limited research in understanding how pedestrians interact with the system, and what information is required for traveling in a complex environment such as university campus. In this paper, we present a mobile pedestrian navigation system called QUT Nav. A field study with eight participants was run in a university campus context, aiming to identify key information required in a mobile pedestrian navigation system for user traveling in university campuses. It also investigated user's interactions and behaviours while they were navigating in the campus environment. Based on the results from the field study, a recommendation for designing mobile pedestrian navigation systems for university campuses is stated.
3 citations
DOI•
01 Jan 2013TL;DR: This cumulative thesis deals with human place descriptions and their interpretation and poses four different research questions: What are dominant types of place descriptions?
Abstract: This cumulative thesis deals with human place descriptions and their interpretation. In particular, it poses four different research questions: What are dominant types of place descriptions? What different types of hierarchical structures do they use? What is the role of spatial relationships in defining the actual location? Can violations in form of flat structures or gaps in levels be related to the applied classification scheme?
2 citations
References
More filters
01 Jan 2010
TL;DR: This article begins by contrasting generation with language understanding, establishing basic concepts about the breakdown of the process into components and the flow of information and decisions through it, and surveyed the common approaches to generation.
Abstract: : Generation is the process of deliberately constructing a natural language text in order to meet specified communicative goals. The goals come from another program, perhaps an expert reasoning system or a ICAI tutor, that is motivated to talk to a human user. The texts that are produced may range from a single phrase given in answer to a question, through multi-sentence remarks and questions within a dialog, to full-page explanations. This article describes AI research on natural language generation with a historical perspective, emphasizing the special character of the problems to be solved. It begins by contrasting generation with language understanding, establishing basic concepts about the breakdown of the process into components and the flow of information and decisions through it. A section of excerpts from the output of illustrative generation systems follows, showing what kinds of performance are possible and where the difficulties are. In the remainder of the article the common approaches to generation are surveyed, including characteristic messages and the nature of a generator's lexicon.
10 citations