Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : PROSIDING SEMINAR NASIONAL

MODEL PENGAMBILAN KEPUTUSAN DALAM PREDIKSI KASUS TUBERKULOSIS MENGGUNAKAN REGRESI LOGISTIK BERBASIS BACKWARD ELIMINATION Ratih Sari Wardani; Purwanto -
PROSIDING SEMINAR NASIONAL & INTERNASIONAL 2014: PROSIDING SEMINAR NASIONAL HASIL - HASIL PENELITIAN & PENGABDIAN
Publisher : Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (147.441 KB)

Abstract

The purpose of this study is to obtain a predictive model in cases of Tuberculosis (TB) using alogistic regression based on backward elimination. The study is conducted through literaturereview, collecting secondary data of 200 patients of Pulmonary Tuberculosis aged more than 15years.  Data is collected from BKPM Semarang, Central Java. The data consist ofcharacteristics, anamnesis, physical examination, laboratory test results data and radiologicalexamination. Logistic regression based  on backward elimination model has better accuracythan logistic regression without attribute selection.Kata kunci : Tuberkulosis, Regresi Logistik, Backward Elimination, Prediksi
MODEL DIAGNOSIS TUBERKULOSIS MENGGUNAKAN k-NEAREST NEIGHBOR BERBASIS SELEKSI ATRIBUT Ratih Sari Wardani; Purwanto -
PROSIDING SEMINAR NASIONAL & INTERNASIONAL 2015: Prosiding Bidang MIPA dan Kesehatan The 2nd University Research Colloquium
Publisher : Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1133.273 KB)

Abstract

The objective of this paper is to obtain a diagnosis model of Tuberculosis (TB) using k-Nearest Neighbor based on feature selection. Data is collected from BKPM Semarang, Central Java. The data consist of characteristics, anamnesis, physical examination, laboratory test results, radiological examination, duration of cough and sputum color. The results indicate that the k-Nearest Neighbor based on backward elimination model improvements as high as 78.66% % compared to individual models.Keywords: k-Nearest Neighbor, backward ellimination , Tuberkulosis, diagnosis, pengambilan keputusan