Page 34 - Contributed Paper Session (CPS) - Volume 3

CPS1934 Atikur R. K. et al.
4. Discussion and Conclusion
Prediction of daily number of RTI episodes provides an insight regarding
the healthcare planning and early warning for an epidemic. Variations in
climatic factors affect the residents directly or indirectly and may seriously
affect the at-risk group. We have identified three different classes of variations
in diurnal temperature change and relative humidity that are likely to increase
the number of RTI episodes. Results obtained from panel generalized linear
model demonstrate that these classes have significant impact on RTI episodes.
Further, we apply flexible machine learning methods such as regression tree
and random forest to obtain 7-day ahead forecast based on rolling statistics
of climatic factors. This 7-day ahead forecast is suitable for planning healthcare
services that may require in the following week, and a 1-day ahead forecast
can be used to revise the planned healthcare services. We have also observed
the higher magnitude of root mean squared forecast errors for highly air
polluted cities which are likely to be a combined effect of air pollution and
weather extremes, and a further research is required to investigate this
phenomena.

References
1. Alencar, A. P. (2018). Seasonality of hospitalizations due to respiratory
diseases: modelling serial correlation all we need is Poisson. Journal of
Applied Statistics, 45 (10), 1813-1822.
2. Choi, Y., Ahn, H. & Chen, J. J. (2005). Regression trees for analysis of count
data with extra Poisson variation. Computational Statistics & Data Analysis,
49(3), 893-915.
3. Eccles, R. (2002). An Explanation for the Seasonality of Acute Upper
Respiratory Tract Viral Infections. Acta Otolaryngol, 122, 183-191.
4. Lahouar, A. & Slama, J. B. H. (2015). Day-ahead load forecast using random
forest and expert input selection, Energy Conversion and Management,
103, 1040-1051.
5. Liu, Y., Liu, J., Chen, F., Shamsi, B. H., Wang, Q., Jiao, F., Qiao, Y. & Shi, Y.
(2016). Impact of meteorological factors on lower respiratory tract
infections in children. Journal of International Medical Research, 44(1): 30–
41.
6. Mirsaeidi, M., Motahari, H., Khamesi, M. T., Sharif, A., Campos, M. &
Schraufnagel, D. E. (2016). Climate change and respiratory infections.
Annals of the American Thoracic Society, 13(8): 1223-1230.
7. WHO, 2014. Ambient (Outdoor) Air Quality and Health. World Health
Organization. http://www.who.int/mediacentre/factsheets/fs313/en/.
8. Xu, Z., Etzel, R. A., Su, H., Huang, C., Guo, Y. & Tong, S. (2012). Impact of
ambient temperature on children's health: a systematic review.
Environmental Research, 117: 120-131.

23 | I S I W S C 2 0 1 9