This Author published in this journals
All Journal Jurnal Gaussian
Nur Dihyah
Departemen Statistika, Fakultas Sains dan Matematika, Universitas Diponegoro

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

IMPLEMENTASI ALGORITMA FUZZY K-NEAREST NEIGHBOR UNTUK KLASIFIKASI PENYAKIT DIARE Nur Dihyah; Budi Warsito; Iut Tri Utami
Jurnal Gaussian Vol 15, No 1 (2026): Jurnal Gaussian
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/j.gauss.15.1.255-263

Abstract

Diarrhea is digestive disruption retrieved by defecation that become more fluid and occur over three times a day. The prevalence of diarrhea in Indonesia is public health problem with high cases. Diarrhea management is carried out with rehydration efforts by administering oral rehydration salts at puskesmas. Diarrhea is classified into 2 types, namely acute diarrhea (mild) and chronic diarrhea (severe). Puskesmas only handles mild diarrhea so that a method is needed to classify diagnosis of diarrhea that occurs at puskesmas appropriately so that diagnosis of acute diarrhea is not misclassified into chronic diarrhea. This research implements Fuzzy K-Nearest Neighbor procedure for Diarrhea Classification. Fuzzy K-Nearest Neighbor incorporates fuzzy logic and K-Nearest Neighbor in the classification practice. The advantage of Fuzzy K-Nearest Neighbor is data will have membership value in each data class so that it further strengthens reason for data to enter predicted class. Data is processed by applying Shiny Package in Rstudio to create Graphical User Interface (GUI-R) so that it makes it easier for researchers to process data. The results obtained highest classification accuracy at K = 3 with accuracy of 80.19% and specificity of 85.45% so that Fuzzy K-Nearest Neighbor was able to classify diarrhea well.