Exploring Associations between Changes in Ambient Temperature and Stroke Occurrence: Comparative Analysis Using Global and Personalised Modelling Approaches
Stroke is a major cause of disability and mortality in most economically developed countries that increasing global importance. Up till now, there is uncertainty regarding the effect of weather conditions on stoke occurrence. This paper is offering a comparative study of exploring associations between changes in ambient temperature and stroke occurrence using global and personalised modelling methods. Our study has explored weather conditions have significant impact on stroke occurrence. In addition, our experimental results show that the personalised modelling approach outperforms the global modelling approach.
Keywordsweather stroke occurrence personalised modelling global modelling FaLK-SVM
Unable to display preview. Download preview PDF.
- 6.Khosla, A., Cao, Y., Lin, C.Y., Chiu, H.K., Hu, J.L., Lee, H.: An itegrated machine learning approach to stroke prediction. In: 16th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. ACM, Washington (2010)Google Scholar
- 8.Vapnik, V., Lerner, A.: Pattern recognition using generalized portrait method. Automation and Remote Control 24, 774–780 (1963)Google Scholar
- 9.Aizerman, E.M., Braverman, L.R.: Theoretical foundations of the potential function method in pattern recognition learning. Automat. Remote Control 25, 821–837 (1964)Google Scholar
- 12.Dudani, S.A.: The distance-weighted k-nearest-neighbor rule. IEEE Transactions on System Man and Cybernetics, 325–327 (1976)Google Scholar
- 15.Beygelzimer, A., Kakade, A., Langford, J.: Cover trees for nearest neighbour. In: 23rd International Conference on Machine Learning, Pittsburgh (2006)Google Scholar
- 16.Chang, C.C., Lin, C.J.: LIBSVM: A library for support vector machines (2001), http://www.csie.ntu.edu.tw/~cjlin/libsvm
- 20.Zou, K.H.: Receiver operating characteristic (ROC) literature research (2002), http://splweb.bwh.harvard.edu:8000/pages/ppl/zou/roc.html
- 21.Zweig, M.H., Campbell, G.: Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin. Chem. 39(4), 561–577 (1993)Google Scholar