PERBANDINGAN METODE DISKRETISASI UNTUK BERBAGAI MACAM ALGORITMA MACHINE LEARNING
| Main Authors: | , FATHUL IHSAN, , Noor Akhmad Setiawan, ST., MT., Ph.D. |
|---|---|
| Format: | Thesis NonPeerReviewed |
| Terbitan: |
[Yogyakarta] : Universitas Gadjah Mada
, 2013
|
| Subjects: | |
| Online Access: |
https://repository.ugm.ac.id/127507/ http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=67765 |
Daftar Isi:
- Most of the information now is still in the form of data. If a data is characterized as recorded facts, then information is a pattern, or expectations that underlie the data. There is a lot of information in the data and information that could be potentially important but yet to be discovered or articulated so that it takes an algorithm to find such information. Existing algorithms include Naive-Bayes, C4.5 and RIPPER. This algorithms require discrete data in the form that it takes discretization. In discretizing there are some methods such as Boolean reasoning, Entropy and Equal Frequency Bining. This study aimed to evaluate the effect of three methods of discretization, the Boolean reasoning, Entropy and Equal Frequency Bining to the Naive-Bayes classifier, C4.5 and RIPPER. Results obtained is found the discretization methods that are most effective for the classifier algorithms that are studied.