SoftGIS data mining and analysis: A case study of urban impression in Helsinki
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Insinööritieteiden korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
2014-05-19
Department
Major/Subject
Geoinformatics
Mcode
IA3002
Degree programme
Geomatiikan koulutusohjelma
Language
en
Pages
48+2
Series
Abstract
In recent years there has been considerable breakthrough in acquisition of qualitative georeferenced data. SoftGIS is one of the most prominent attempts in this context that is capable of providing useful data that has applications in different disciplines. However, similar to any other large spatial dataset, the SoftGIS data requires a set of spatial analysis and data mining techniques in order to yield the desired information and to be considered as a reliable source of knowledge. This thesis propounded a four stage knowledge discovery process in which several exploratory, visual and analytical spatial techniques were proposed. Moreover, the proposed techniques were applied and implemented in a case study of urban impression in Helsinki metropolitan area. The proposed techniques take advantage of an appropriate data quantification approach and aim to facilitate the knowledge discovery process of spatio-qualitative data and contribute to the revelation of the desired information. Due to the distinct characteristics of this type of data, partially caused by its acquisition procedure and partially by its qualitative nature, certain considerations needed to be taken into account. These considerations could not be accomplished without studying the data and exploring its specific characteristics. The striking existence of cognitive uncertainty in SoftGIS data led to the application of fuzzy logic techniques in this thesis. The results indicate that using fuzzy techniques is a promising approach towards mitigating the negative effects of the aforesaid uncertainty in SoftGIS datasets. Furthermore, this thesis widened its domain of knowledge discovery to a less explicit realm of information through employing spatial data mining. This resulted in discovery of interesting associations between the SoftGIS data and the neighboring building types.Description
Supervisor
Virrantaus, KirsiThesis advisor
Nikander, JussiAhonen-Rainio, Paula
Keywords
SoftGIS, knowledge discovery, spatio-qualitative data mining, association rules, fuzzy, clustering validation, spatial analysis, visualization