J-Icon : Jurnal Komputer dan Informatika
Vol 5 No 2 (2017): Oktober 2017

CASE BASED REASONING UNTUK MENDIAGNOSA PENYAKIT KEHAMILAN MENGGUNAKAN COSINE SIMILARITY

Adelysa P Gitaswara (Universitas Nusa Cendana)
Sebastianus Adi Santoso Mola (Universitas Nusa Cendana)
Emerensiana S.Y Pandie (Universitas Nusa Cendana)



Article Info

Publish Date
31 Oct 2017

Abstract

The application of case-based reasoning in diagnosing pregnancy deseases is motivated by the lack of number of obstetricians. The use of CBR aims to solve new problems by adapting the solutions contained in the previous case, by calculating the level of similarity. Calculation of similarity value using cosine similarity method, with threshold equal to 100%. This system can diagnose 6 diseases, 28 existing symptoms. System outbreaks of illness experienced by patients based on symptoms induced by non-specialist medical personnel, as well as handling solutions accompanied by a presentation of similarities with previous cases to indicate the degree of truth of possible diagnosis. Based on the results of case testing, the results obtained: the system can retrieve the exact old case and have used the cosine similarity methodology correctly, shown with 100% accuracy results, and using 104 cases is optimal enough to diagnose 6 illnesses shown with average results Similarity to 20 cases is 90%.

Copyrights © 2017






Journal Info

Abbrev

jicon

Publisher

Subject

Computer Science & IT

Description

J-ICON : Jurnal Komputer dan Informatika focuses on the areas of computer sciences, artificial intelligence and expert systems, machine learning, information technology and computation, internet of things, mobile e-business, e-commerce, business intelligence, intelligent decision support systems, ...