An AI based approach to multiple census data analysis for feature selection
Building upon prior work on sociodemographic clustering of Beppu City, Japan, with data from the year 2000 census, this paper analyzes the sociodemographic development of the city. Viscovery SOMine clustering shows that, although there are some new sociodemographic trends, local districts in 2010 largely cluster in the same way they did in the year 2000.
Assessing regional wellbeing in Italy: an application of Malmquist–DEA and self-organizing map neural clustering
Social and economic well-being of all 20 Italian regions in the period of 2005–2011 is analyzed. The explorative analysis conducted with Viscovery SOMine reveals a North–South disparity. The North is not only richer but also exhibits better performance with respect to well-being within this time frame.
Citizens as consumers: profiling e-government services’ users in Egypt via data mining techniques
The dependence of Egyptian citizens' use of e-government services from various demographic and psychographic variables is researched. Viscovery SOMine is used alongside various other machine learning methods to classify citizens into users, non-users and potential users.
Mathematical clustering integrated with SWOT analysis as a tool for design of sustainable development strategies
This paper aims at creating a draft for a sustainable-development strategy framework in the Czech Republic. Viscovery SOMine is used to analyze statements with respect to their meaning for sustainability. By applying SWOT analyses to the resulting clusters, specific interventions are defined for building a basis for the development strategy.
Clustering the ecological footprint of nations using Kohonen’s self-organizing maps
140 countries are clustered to identify sociodemographic and economic indicators affecting the magnitude of the ecological footprints per capita. Applying Viscovery SOMine's SOM-Ward algorithm, the author finds that geographical position, GDP, urbanization level, export rate, rate of GDP created by services and literacy rate are major correlates with the ecological footprint.
Community health assessment using self-organizing maps and geographic information systems
This study analyzes 511 communities from New York State with respect to social, demographic, economic and environmental background to reveal connections between these variables and occurrences of particular diseases. Viscovery SOMine found clusters of similar communities and significant different incidence rates for diseases, such as hepatitis, tuberculosis, asthma, chronic obstructive pulmonary disease (COPD), diabetes, influenza and atherosclerosis.
Toward optimal calibration of the SLEUTH land use change model
SLEUTH is a computational simulation model that uses adaptive cellular automata to simulate the way cities grow and change their surrounding land uses. Viscovery SOMine is used to generate a self-organizing map for reducing data, to pursue the isolation of the best parameter sets and to indicate which of the existing 13 calibration metrics used in SLEUTH are necessary to arrive at the optimum. A new metric is proposed for increasing the value in future SLEUTH applications.
Social area analysis using SOM and GIS: a preliminary research
Local units of the Japanese city Beppu are analyzed with respect to their sociodemographic and economic properties. Viscovery SOMine is used to obtain clusters of similar local units to enable city planners to understand local properties and take them into account for planning decisions.
Development of an ecologically derived environmental health model using geographic information systems
This dissertation studies environmental influences on public health. Viscovery SOMine is used to cluster environmental, socioeconomic and health data for 569 communities in 5 counties of New York State.
Towards fair ranking of Olympics achievements: the case of Sydney 2000
An objective, impartial system for analyzing Olympic results, which the majority of participating countries could agree upon, is analyzed by discussing different ways of ranking the performance of participating countries at the Sydney 2000 Olympic Games. The unsupervised data mining technique of self-organizing maps is used to group the participating countries into homogenous clusters. A model based on data-envelopment analysis is then used for producing a new ranking of participating teams that could be accepted as “fair” by the majority of participants.
Operationalising multidimensional concepts of chronic poverty: an exploratory spatial analysis
Viscovery SOMine analysis is used to detect spatial inequalities in social development for Indian regions and districts. The nature and extent of these inequalities varies with choice of indicator and geographical space over which comparisons are made.
Self-organising map methods in integrated modelling of environmental and economic systems
The paper elaborates on how self-organizing map methodologies using Viscovery SOMine within the connectionist paradigms of artificial neural networks could be applied to disparate data analysis at two different scales of environmental and economic systems: regional (using river-water quality-monitoring data to evaluate ecosystem response to human influence) and global (for modeling environmental and economic system data and trade-off analysis) within an integrated framework to inform sustainable environment management.