KLASIFIKASI KELAHIRAN PREMATUR MENGGUNAKAN ALGORITMA C4.5 DENGAN MENERAPKAN INFORMATION GAIN DAN CORRELATION – BASED FEATURE SELECTION
| Main Author: | Wiranata, Jojo |
|---|---|
| Format: | Thesis NonPeerReviewed Book |
| Bahasa: | eng |
| Terbitan: |
, 2018
|
| Subjects: | |
| Online Access: |
http://eprints.umm.ac.id/44557/1/PENDAHULUAN.pdf http://eprints.umm.ac.id/44557/2/BAB%20I.pdf http://eprints.umm.ac.id/44557/3/BAB%20II.pdf http://eprints.umm.ac.id/44557/4/BAB%20III.pdf http://eprints.umm.ac.id/44557/5/BAB%20IV.pdf http://eprints.umm.ac.id/44557/6/BAB%20V.pdf http://eprints.umm.ac.id/44557/ |
Daftar Isi:
- The birth of premature babies in Indonesia is still one of the very high cases. Data from some hospitals shows a presentation of between 14-20% of all treated babies. This situation is mainly due to socio-economic problems experienced by most Indonesians. There are also several factors and health problems that can trigger premature labor, unhealthy mothers, smoking, pregnancy history, fetal condition, psychological condition. Therefore the authors intend to conduct research on the classification of premature birth using C4.5 algorithm and apply the feature selection method to know influence in the process of classification. After doing research, accuracy using C4.5 algorithm without feature selection of 92.67%, using CFS get 90.67% accuracy and using IG obtained 88.67% accuracy. From the tests that have been done show that the use of C4.5 algorithm in the process of premature birth classification can be used in the process classification. However, the use of feature selection methods produces a little accuracy below that does not use feature selection.