PENGGUNAAN METODE FUZZY DALAM PENENTUAN ZONA RESIKO MALARIA DI PULAU FLORES NTT

  • Dony Sihotang
  • Honey Ndoen
  • Defritus Punuf
Keywords: Malaria, fuzzy model, level of risk

Abstract

The purpose of this study was to compare the result of mapping malaria risk zone by fuzzy method against actual data of Annual Parasite Insidence (API 2014). Variables used in determining malaria risk area are temperature, densiy of vegetation and land cover. From the result of satellite image processing by remote sensing technology obtained an average of every pixel in the district area for temperature, density of vegetation and land cover are then processed by the fuzzy model. Accuracy tests have been conducted for 100 districts where the fuzzy model has an accuracy rate of 61.54%. From the test results shows that the fuzzy model tends to produce a higher grade than the grade on actual data. As fuzzy model produces class “High” but actually “Low” (17,85%), fuzzy model produces class “Medium” but actually “Low” (2,20%), or fuzzy models produces class “High” but actually “Medium” (14,29%). This could be caused by a form of intervention for mosquito nest eradication conducted in some districts is quite effective. Beside that, several districts are still passive in detecting the number of malaria cases so that the actual data is provided tends to lower.

References

[1] DINKES Provinsi NTT., 2014. Profil Kesehatan. Kupang: Dinas Kesehatan Provinsi Nusa Tenggara Timur.
[2] DINKES Provinsi NTT., 2014. Laporan P2MK DINKES NTT. Kupang: Dinas Kesehatan Provinsi Nusa Tenggara Timur..
[3] Wilder, J., 2007. Modeling Malaria Transmission Risk Using Satellite-Based Remote Sensing Imagery. Thesis. Department of Geology and Geography NMSU Missouri.
[4] Simeon, M., 2014. Geographic Information System and Remote Sensing Based Malaria Risk Mapping Using Environmental Factors: A Case of Arba Minch Zuria Woreda. Southern Nations Nationalities and People’s Regional State. Thesis. The Department of Geography and Environmental Studies.
[5] Dutta, S., 2006. Malaria epidemiology on Jalapaigur District Applying Remote Sensing and Geographic Information System.Unpublished Dissertation Paper. University of North Bengal.
[6] Abeku, T.A., 2006. Malaria Epidemics in Africa Prediction, Detection, and Response. Thesis. Erasmus University Roterdam.
[7] Afrene, Y.A., 2011. Malaria Transmission in The African Highlands in a Changing Climate Situation: Perspective from Kenyan Highlands. Global Warming Impacts.
[8] Chikodzi, D., 2013. Spatial Modelling of Malaria Risk Zones Using Environmental, Anthropogenic Variables and Geogra-Phical Information Systems Techniques. Journal of Geosciences and Geomatics, Vol. 1, No.1, 8-14.
[9] Sihotang, D., Punuf, D., 2015. Analisis Parameter Spasial Habitat Nyamuk Anopheles. Jurnal MIPA UNDANA, Vol.19, No.2, 101 -111.
[10] Sihotang, D., Widiastuti, T., Kartika, I.S., 2013. Route Selection System Based on GIS Using Scoring Method and Fuzzy Method. Proceeding International Conference on Information System for Business Competitiveness. Semarang, December 5 2013, UNDIP Semarang.
[11] Ross, T.J., 2003. Fuzzy Logic with Engineering Application. USA: Willey & Sons.
[12] Wang, L-X., 1996. A Course Fuzzy System and Control, USA: Prentice-Hall International Inc.
[13] Susilo, F., 2003. Pengantar Himpunan dan Logika Kabur Serta Aplikasinya. Yogyakarta: Universitas Sanata Dharma
Published
2018-05-18
Section
Articles