Regional search and visualization methodologies for multi-criteria geographic retrieval.

Abstract

The objective of this research is to investigate and develop sophisticated visual interfaces and ranking methods to enable end-users in discovering knowledge hid-den in multi-dimensional geospatial databases. To characterize the atmosphere, composition, and spatial distribution of geographic regions we proposed to ex-tract spatially relevant information from publicly available Web data sources, e.g., OpenStreetMap, spatial documents, events, social media, etc. The inter-action procedure goes beyond the conventional list based local search interfaces and proposes to access the geospatial data sources with regional overview. Users can compare the characterization of urban areas with respect to multiple spatial dimensions of interest and can search for the most suitable region. To tackle the human centered aspects we proposed novel query methods where users could go beyond the popular place names and locations for the characterization of their region of interest. We investigated different geovisualization methods to support easy access and interaction with the spatial database. The search experience is further enhanced via efficient regional ranking algorithms to accomplish the complex search task in computationally effective manner. The proposed rank-ing phenomenon is a novel methodology to generalize from point data to spatial distributions, captivating on multi-criteria optimization algorithms.