Data Quality Assurance for Volunteered Geographic Information

摘要: The availability of technology and tools enables the public to participate in collection, contribution, editing, usage geographic information, a domain previously reserved for mapping agencies or companies. data Volunteered Geographic Information (VGI) systems, such as OpenStreetMap (OSM), is based on participation individuals. However, this combination also implies quality issues related data: some contributed entities can be assigned wrong implausible classes, due individual interpretation submitted data, misunderstanding about available classes. In paper we propose two methods check integrity VGI with respect hierarchical consistency classification plausibility. These are constraint checking machine learning methods. They used validity during contribution at later stage collaborative manual automatic correction.