Eliyen, Kunti (2017) Klasifikasi Pada Virtual Patient Case Menggunakan Learning Vector Quantization. Magister thesis, Universitas Brawijaya.
Abstract
Dalam pendidikan kedokteran ada berbagai macam ujian yang diterapkan. Salah satunya adalah ujian Objective Stucture Clinical Examinations (OSCE). OSCE adalah alat untuk menilai komponen kompetensi klinik seperti history taking, pemeriksaan fisik, procedural skill, ketrampilan komunikasi, interpretasi hasil laboratorium, manajemen dan lain-lain yang diuji menggunakan checklist yang telah disetujui dan mahasiswa akan mengikuti beberapa station. OSCE merupakan bagian dari penilaian yang bertujuan untuk menilai kompetensi dan ketrampilan klinis mahasiswa secara objektif dan terstruktur. Pada penelitian ini akan dikembangkan sistem penilaian otomatis diagnosis pasien virtual yang dapat digunakan oleh mahasiswa sebagai self assessment agar mahasiswa memiliki kesiapan dalam menghadapi ujian OSCE. Proses sistem evaluasi pada penelitian yang akan dilakukan adalah dengan mengadakan simulasi kasus pada pasien virtual. Dalam sistem tersebut mahasiswa diberikan beberapa keluhan pasien yang berhubungan dengan penyakit gigi pasien, kemudian mahasiswa melakukan pemeriksaan pada pasien, mendiagnosis penyakit pasien dan menentukan perawatan yang akan diterima pasien. Penilaian yang dilakukan menerapkan konsep klasifikasi menggunakan Learning Vector Quantization dan k-Nearest Neighbor. Pada uji coba yang dilakukan dengan kedua metode tersebut didapatkan hasil terbaik menggunakan LVQ dengan data learning sebanyak 135 data dan nilai α = 0,1 menghasilkan nilai akurasi sebesar 98,8%. Sedangkan pada k-NN diperoleh nilai klasifikasi terbaik yaitu nilai akurasi sebesar 89,28% pada saat menggunakan data learning sebanyak 135 data dan nilai k = 3.
English Abstract
In medical education there are various tests applied. One of them is the Objective Stucture Clinical Examinations (OSCE) exam. The OSCE is a tool for assessing the components of clinical competence such as history taking, physical examination, procedural skills, communication skills, interpretation of laboratory results, management and others tested using approved checklists and students attending multiple stations. The OSCE is part of an assessment aimed at assessing students' objective and structured competency and clinical skills. In this research will be developed automatic patient diagnosis system which can be used by students as self assessment so that students have readiness in facing OSCE examination. The process of evaluation system in the research that will be done is to conduct case simulations on virtual patients. In the system students are given some patient complaints related to dental disease of the patient, then the student performs the examination on the patient, diagnose the patient's illness and determine the treatment that will be received by the patient. The appraisal applied the classification concept using Learning Vector Quantization and k-Nearest Neighbor. In the experiments conducted with both methods obtained the best results using LVQ with data learning as much as 135 data and the value of α = 0.1 to produce an accuracy of 98.8%. While on k-NN obtained best classification value that is accuracy equal to 89,28% when using data learning as 135 data and value k = 3.
Item Type: | Thesis (Magister) |
---|---|
Identification Number: | TES/006.32/ELI/k/2017/041708256 |
Uncontrolled Keywords: | SIGNAL PROCESSING - DIGITAL TECHNIQUES, COMPUTER ENGINERING, CINICAL COMPETENCE, NEAREST NEIGHBOR ANALYSIS (statistics) |
Subjects: | 000 Computer science, information and general works > 006 Special computer methods > 006.3 Artificial intelligence > 006.32 Neural nets (neural networks) |
Divisions: | S2/S3 > Magister Teknik Elektro, Fakultas Teknik |
Depositing User: | Nur Cholis |
Date Deposited: | 20 Sep 2017 06:22 |
Last Modified: | 06 Nov 2020 13:04 |
URI: | http://repository.ub.ac.id/id/eprint/2784 |
Text
1. Bagian Depan.pdf Restricted to Repository staff only Download (315kB) |
|
Text
2. BAB I.pdf Restricted to Repository staff only Download (95kB) |
|
Text
3. BAB II.pdf Restricted to Repository staff only Download (222kB) |
|
Text
4. BAB III.pdf Restricted to Repository staff only Download (379kB) |
|
Text
5. BAB IV.pdf Restricted to Repository staff only Download (240kB) |
|
Text
6. BAB V.pdf Restricted to Repository staff only Download (734kB) |
|
Text
7. BAB VI.pdf Restricted to Repository staff only Download (86kB) |
|
Text
8. DAFTAR PUSTAKA.pdf Restricted to Repository staff only Download (169kB) |
Actions (login required)
View Item |