Klasifikasi Penyakit Tuberkulosis Menggunakan Metode Naive Bayes (Studi Kasus: Data Pasien Di Puskesmas Petung Kabupaten Penajam Paser Utara)

Ahmad Aliful Abidin; Rito Goejantoro; M. Fathurahman

doi:10.30872/eksponensial.v14i1.1031

Ahmad Aliful Abidin Student
Rito Goejantoro
M. Fathurahman

DOI: https://doi.org/10.30872/eksponensial.v14i1.1031

Abstract

The Naive Bayes method is one of the data mining methods used in classifying data and predicting future opportunities based on experience or previous data. This method was proposed by British scientist Thomas Bayes using a branch of mathematics known as probability theory. One of the diseases that can be detected using the classification using the Naive Bayes method is Tuberculous (TB). Tuberculous is an infectious respiratory disease caused by the bacterium Mycobacterium Tuberculosis. The purpose of this study was to determine the results and accuracy of the classification of Tuberculous disease using the Naive Bayes method in one of the health service units, namely Puskesmas Petung, Penajam Paser Utara. The results showed that data mining classification using the Naive Bayes method was appropriate in classifying Tuberculous. For training and testing data, divided into 90:10, the accuracy rate is 87.5%, categorized as Excellent Classification. As for the training and testing data divided into 70:30, the accuracy rate is 90.9%, classified as Excellent Classification.

Downloads

Download data is not yet available.

References

Buani, D. P. (2016). Optimasi Algoritma Naïve Bayes dengan Menggunakan Algoritma Genetika untuk Prediksi Kesuburan (Fertility). Jurnal Evolusi , 4(1), 54-63.
Dewi, A. (2016). Komparasi 5 Metode Algoritma Klasifikasi Data Mining Pada Prediksi Keberhasilan Pemasaran Produk Layanan Perbankan. Jurnal Techno Nusa Mandiri, 8(1), 7-9.
Ekata, Tyagi, P. K., dan Gupta, S. (2016). Diagnosis of Pulmonary Tuberculous using Fuzzy Inference System. IEEE Second International Innovative Applications of Computational Intelligence on Power, Energy and Controls with their Impact on Humanity, 3-7. doi: 10.1109/CIPECH.2016.7918726.
Gorunescu, F. (2011). Data Mining: Concepts, Model and Techniques. Romania.
Han, J. dan M. Kamber. (2006). Data Mining Concepts and Techniques Second Edition. San Francisco: Morgan Kaufmann.
Hermawati. (2013). Data Mining. Yogyakarta: Penerbit ANDI.
Imanidanantoyo, A. I., Ananta, A. Y., & Kirana, A. P. (2020). Implementasi Naive Bayes Dan Pos Tagging Menggunakan Metode Hidden Markov Model Viterbi Pada Analisa Sentimen Terhadap Akun Twitter Presiden Joko Widodo Di Saat Pandemi COVID-19. Seminar Informatika Aplikatif Polinema, 235–241.
Kementerian Kesehatan Republik Indonesia. (2021). Profil Kesehatan IndonesiaTahun 2020. Jakarta : Kementerian Kesehatan RI.
Kusrini, dan Luthfi, E.M. (2009). Algoritma Data Mining. Yogyakarta : CV. Andi Offset.
Prasetyo, E., (2012). Data Mining Konsep dan Aplikasi Menggunakan Matlab. Yogyakarta: Andi Offset.
Rosandy, T. (2016). Perbandingan Metode Naive Bayes Classifier dengan Metode Decison Tree (C4.5) Untuk Menganalisa Kelancaran Pembiayaan (Study Kasus: KSPPS/BMT Al-Fadhila). Jurnal TIM Darmajaya, 2(1), 52-62.
Saiyar, Amrin Hafdiarsya. (2018). Aplikasi Diagnosa Penyakit Tuberculosis Menggunakan Algoritma Naive Bayes. Jurnal Riset Komputer, 5(5), 498-502.
Saleh, Alfa. (2015). Implementasi Metode Klasifikasi Naïve Bayes Dalam Memprediksi Besarnya Penggunaan Listrik Rumah Tangga. Jakarta: Sumber Utama.
Saputra, Rizal Amegia dan Widodo, Prabowo. (2014). Komparasi Algoritma Klasifikasi Data Mining untuk Memprediksi Penyakit Tuberculosis (TB). Prosiding Seminar Nasional Inovasi dan Tren, 120-126.
Saputra, Rizal Amegia. (2014). Penerapan Algoritma Naive Bayes Untuk Prediksi Penyakit Tuberculous. Jurnal Swabumi, 1(1), 18-23.