Application of a Spatial Intelligent Decision System on Self-Rated Health Status Estimation
Self- assessed general health status is a commonly-used survey technique since it can be used as a predictor for several public health risks such as mortality, deprivation, and fear of crime or poverty. Therefore, it is a useful alternative measure to help assessing the public health situation of a neighborhood or town, and can be utilized by authorities in many decision support situations related to public health, budget allocation and general policy-making, among others. It can be considered as spatial decision problems, since both data location and spatial relationships make a prominent impact during the decision making process. This paper utilizes a recently-developed spatial intelligent decision system, named, Spatial RIMER+, to model the self-rated health estimation decision problem using real data in the areas of Northern Ireland, UK. The goal is to learn from past or partial observations on self-rated health status to predict its future or neighborhood behavior and reference it in the map. Three scenarios in line of this goal are discussed in details, i.e., estimation of unknown, downscaling, and predictions over time. They are used to demonstrate the flexibility and applicability of the spatial decision support system and their positive capabilities in terms of accuracy, efficiency and visualization.
KeywordsSelf-rated health Spatial decision support Rule-based systems Belief rule base Uncertainty
- 1.Sugumaran R. and DeGroote J.P., Spatial Decision Support Systems: Principles and Practices. CRC Press, 2010.Google Scholar
- 8.Thomas, C., and Humenik, N., GIS for Decision Support and Public Policy Making. Calif.: ESRI Press, Redlands, 2009.Google Scholar
- 10.Angelov P. and Yager R., A simple fuzzy rule-based system through vector membership and kernel-based granulation. Proceedings of 2010 I.E. Intl Conf. on Intelligent Syst., pp. 349-354, 2010, London, UKGoogle Scholar
- 12.Calzada A., Liu J., Wang H. and Kashyap A., A novel spatial belief rule-based intelligent decision support system. IEEE International Conference on Systems, Man and Cybernetics (IEEE SMC 2013), October 13-16, 2013, Manchester, UK: 639-644.Google Scholar
- 13.Lloyd C.D., Local Models for Spatial Analysis, Second Edition. CRC Press, Taylor and Francis Group, 2011.Google Scholar
- 14.Calzada A., Liu J., Nugent C., Wang H., and Martinez L. (2014), Using the spatial RIMER+ approach to estimate negative self-rated health and its causes across Northern Ireland, Proceeding of the 8th International Conference on Ubiquitous Computing & Ambient Intelligence (UCAmI 2014) & the 6th International Work-conference on Ambient Assisted Living (IWAAL 2014), Belfast, 2nd - 5th December 2014.Google Scholar
- 18.Calzada A., Liu J. and Wang H., A new dynamic rule activation method for extended belief rule-bases, IEEE Transactions on Knowledge and Data Engineering, accepted and in press, 2014.Google Scholar
- 19.gvSIG Project, http://www.gvsig.org/web/home/, 2010.
- 21.Ripley B.D., Spatial Statistics. Vol. 575. 2005, Wiley-Inter Science.Google Scholar
- 22.Charlton M., Fotheringham S., and Brunsdon C., Geographically Weighted Regression. White paper. National Centre for Geocomputation. National University of Ireland Maynooth, 2009.Google Scholar
- 23.Brunsdon, C., Fotheringham, S., and Charlton, M., Geographically weighted regression. Journal of the Royal Statistical Society: Series D (The Statistician) 47.3:431–443, 1998.Google Scholar
- 25.Fotheringham A.S., Geographically Weighted Regression. The Sage handbook of spatial analysis, 243-254, 2009.Google Scholar
- 26.Fotheringham, A. S., Brunsdon, C., and Charlton, M., Geographically Weighted Regression: The Analysis of Spatially Varying Relationships. Wiley, Chichester, 2002.Google Scholar
- 27.Sheehan K.R., Strager M.P., Welsh S.A., Advantages of geographically weighted regression for modeling benthic substrate in two greater yellowstone ecosystem streams. Environmental Modeling & Assessment: 1-11, 2013.Google Scholar
- 31.Tian, F., Qiu, G. Y., Yang, Y. H., Xiong, Y. J., and Wang, P., Studies on the relationships between land surface temperature and environmental factors in an inland river catchment based on geographically weighted regression and MODIS Data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 5(3):687–698, 2012.CrossRefGoogle Scholar
- 32.NINIS (2013): The data used was obtained from the Northern Ireland Neighbourhood Information Service (NINIS), which is one function of the Northern Ireland Statistics and Research Agency (NISRA). The material featured on the NINIS website (www.nisra.gov.uk/ninis, last accessed 26, January, 2014).
- 33.LPS (2013): Land and Property Services (LPS) Ordnance Survey of Northern Ireland® (OSNI®). This map is reproduced under the Northern Ireland Mapping Agreement (NIMA) reference MOU 203, which applies to non-commercial research published within the University of Ulster.Google Scholar
- 34.Calzada A., Liu J., Wang H., and Kashyap A., Uncertainty and incompleteness analysis using the RIMER approach for urban regeneration processes: the case of the Greater Belfast region. International Conference on Machine Learning and Cybernetics (ICMLC 2012), 15-17 July 2012, Xian, China: 928-934.Google Scholar