Forecasting Model Penyakit Demam Berdarah Dengue Di Provinsi DKI Jakarta Menggunakan Algoritma Regresi Linier Untuk Mengetahui Kecenderungan Nilai Variabel Prediktor Terhadap Peningkatan Kasus

Authors

  • Aji Rahmat Muhajir Telkom University
  • Edi Sutoyo Universitas Telkom Bandung
  • Irfan Darmawan Universitas Telkom Bandung

DOI:

https://doi.org/10.21111/fij.v4i2.3199

Keywords:

Data Mining, Predictive Mining, Linear, Dengue Fever (DHF)

Abstract

AbstrakDi Indonesia khususnya di Provinsi DKI Jakarta sampai saat ini Demam Berdarah Dengue masih merupakan masalah kesehatan masyarakat yang utama. Meski sudah ada beberapa langkah untuk mengatasi penyebaran penyakit Demam Berdarah Dengue (DBD), namun harus ada metode analisis untuk melakukan peramalan terhadap kasus DBD menggunakan serangkaian data yang ada, dan memperkirakan nilai data dimasa yang akan datang. Penelitian ini bertujuan untuk membuat model forecasting peningkatan jumlah kasus Demam Berdarah Dengue menggunakan algoritma regresi linear dan melakukan analisis pengaruh dari temperatur, kelembapan dan curah hujan dalam kanaikan kasus penyakit Demam Berdarah Dengue di Provinsi DKI Jakarta dari model regresi yang dibuat. Data DBD yang digunakkan merupakan dataset pemantauan penyakit endemik yang diperoleh dari Dinas Kesehatan DKI Jakarta sedangkan data cuaca merupakan dataset yang didapat dari Dinas Lingkungan Hidup DKI Jakarta. Dari model regresi yang dibuat diperoleh nilai R2 sebesar 0.3622, hal tersebut menunjukan presentase pengaruh variabel predictor terhadap kasus demam berdarah sebesar 36.22%, sedangkan 63.78% dipengaruhi oleh faktor lain diluar variabel independen tersebut.Setelah melakukan uji simultan, dapat disimpulkan bahwa temperatur, kelambapan, dan curah hujan secara bersama-sama berpengaruh terhadap kenaikan jumlah kasus demam berdarah di Provinsi DKI Jakarta. Selanjutnya uji parsial membuktikan bahwa, kelembapan dan curah hujan memiliki pengaruh signifikan terhadap kenaikan kasus demam berdarah, sedangkan untuk variabel bebas, temperatur terbukti tidak memiliki pengaruh yang signifikan terhadap kenaikan kasus demam berdarah dengue di Provinsi DKI Jakarta.Kata kunci: Data Mining, Predictive Mining, Regresi Linier, Demam Berdarah Dengue Abstract[Forecasting Model of Dengue Hemorrhagic Fever in DKI Jakarta Using Linear Regression Algorithm to Know Trends of Predictor Variable Value for Case Increasing] In Indonesia specifically in DKI Jakarta Province, Dengue fever is still the main public health problem. Although there are already several steps to overcome the spread of Dengue Fever (DHF), there still needs to be an analytical method to forecast the increase dengue cases using and estimated data values in the future. This study aims to make a forecasting model for increasing the number of cases of Dengue Fever using a linear regression algorithm and analyzing the effect of temperature, humidity and rainfall in the case of Dengue Hemorrhagic Fever in DKI Jakarta Province from a regression model made. The DHF data used is an endemic disease monitoring dataset obtained from the DKI Jakarta Health Office while the weather data is a dataset obtained from the DKI Jakarta Environmental Service. From the regression model made, the value of R2 is 0.3622, it shows the percentage of the influence of temperature, humidity and rainfall on cases of dengue fever is 36.22%, while 63.78% is influenced by other factors outside the independent variable. After conducting a simultaneous test, it can be concluded that temperature, humidity and rainfall together, influence the increase in the number of dengue cases in DKI Jakarta Province. Then the partial test proves that humidity and rainfall have a significant influence on the increase in dengue cases, whereas for temperature independent variables proved that no significant effect on the increase in cases of dengue hemorrhagic fever in DKI Jakarta Province.Keywords: Data Mining, Predictive Mining, Linear Regression, Dengue Fever (DHF)

References

World Health Organization, “Dengue: guidelines for diagnosis, treatment, prevention, and control,” Spec. Program. Res. Train. Trop. Dis., p. x, 147, 2009. [2] InfoDatin Kementerian Kesehatan, “Situasi DBD di Indonesia,” InfoDATIN. p. p 12, 2016. [3] Jakarta Provincial Health Agencies, “Health Profile of DKI Jakarta Province 2016,” p. 131, 2016. [4] A. QomaruddinMunir and E. Winarko, “Classification Model Disease Risk Areas Endemicity Dengue Fever Outbreak based Prediction of Patients, Death, IR and CFR using Forecasting Techniques,” Int. J. Comput. Appl., vol. 114, no. 2, pp. 20–25, 2015. [5] Y. A. Lesnussa, L. J. Sinay, and M. R. Idah, “Aplikasi Jaringan Saraf Tiruan Backpropagation untuk Penyebaran Penyakit Demam Berdarah Dengue (DBD) di Kota Ambon,” J. Mat. Integr., vol. 13, no. 2, p. 63, 2017. [6] L. C. Lubos, “Dengue Incidence using Climate Variables as Predictors,” Asian J. Heal., vol. 5, no. 1, pp. 1–11, 2015. [7] M. M. Sintorini, “Pengaruh Iklim terhadap Kasus Demam Berdarah Dengue,” Kesmas Natl. Public Heal. J., vol. 2, no. 1, p. 11, 2016. [8] J. Han and M. Kamber, Data Mining, Southeast Asia Edition: Concepts and Techniques. Morgan kaufmann, 2006. [9] J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques. 2012. [10] E. Sutoyo, I. T. R. Yanto, R. R. Saedudin, and T. Herawan, “A soft set-based co-occurrence for clustering web user transactions,” Telkomnika (Telecommunication Comput. Electron. Control., vol. 15, no. 3, 2017. [11] E. Sutoyo, R. R. Saedudin, I. T. R. Yanto, and A. Apriani, “Application of adaptive neuro-fuzzy inference system and chicken swarm optimization for classifying river water quality,” in Electrical, Electronics and Information Engineering (ICEEIE), 2017 5th International Conference on, 2017, pp. 118–122. [12] H. Chiroma et al., An intelligent modeling of oil consumption, vol. 320. 2015. [13] R. R. Saedudin, E. Sutoyo, S. Kasim, H. Mahdin, and I. T. R. Yanto, “Attribute selection on student performance dataset using maximum dependency attribute,” in Electrical, Electronics and Information Engineering (ICEEIE), 2017 5th International Conference on, 2017, pp. 176–179. [14] E. S.-F. of I. Journal and undefined 2018, “Implementasi Limited Tolerance Relation Untuk Sistem Informasi yang Tidak Lengkap Pada Data Mahasiswa,” ejournal.unida.gontor.ac.id. [15] N. Singh, R. A. M. S. Raw, and R. K. Chauhan, “Data Mining With Regression Technique,” vol. 3, no. 1, pp. 199–202, 2012. [16] K. D. Ariani, J. Teknik, I. Fik, and J. N. N. Semarang-, “Data Pabrik Gula Rendeng Kudus,” no. 5. [17] S. Sulistyono and W. Sulistiyowati, “Peramalan Produksi dengan Metode Regresi Linier Berganda,” PROZIMA (Productivity, Optim. Manuf. Syst. Eng., vol. 1, no. 2, p. 82, 2018. [18] A. Amrin, “Data Mining Dengan Regresi Linier Berganda Untuk Peramalan Tingkat Inflasi,” J. Techno Nusa Mandiri, vol. XIII, no. 1, pp. 74–79, 2016. [19] C. Eswaran and R. Logeswaran, “A Comparison of ARIMA , Neural Network and Linear Regression Models for the Prediction of Infant Mortality Rate,” no. 2, 2010. [20] J. Han, “Data mining : concepts and techniques,” J. Chem. Inf. Model., pp. 101–103, 2012. [21] T. T. Hanifa, S. Al-faraby, F. Informatika, and U. Telkom, “Analisis Churn Prediction pada Data Pelanggan PT . Telekomunikasi dengan Logistic Regression dan Underbagging,” vol. 4, no. 2, pp. 3210–3225, 2017.

Downloads

Submitted

2019-06-27

Accepted

2019-09-01

Published

2019-11-01

Issue

Section

Articles