KLASIFIKASI HALAMAN WEB UNTUK ANAK MENGGUNAKAN METODE WEIGHTED VOTING SUPPORT VECTOR MACHINE
| Main Author: | Anwar, Maulidya Yuniarti |
|---|---|
| Format: | Thesis NonPeerReviewed Book |
| Bahasa: | eng |
| Terbitan: |
, 2019
|
| Subjects: | |
| Online Access: |
http://eprints.umm.ac.id/54515/43/PENDAHULUAN.pdf http://eprints.umm.ac.id/54515/2/BAB%20I.pdf http://eprints.umm.ac.id/54515/3/BAB%20II.pdf http://eprints.umm.ac.id/54515/4/BAB%20III.pdf http://eprints.umm.ac.id/54515/5/BAB%20IV.pdf http://eprints.umm.ac.id/54515/6/BAB%20V.pdf http://eprints.umm.ac.id/54515/44/POSTER.pdf http://eprints.umm.ac.id/54515/ |
Daftar Isi:
- Nowadays internet users are increasing along with the rapid advancement of technology. Internet users themselves are not only adults but many of them are school-age children who have not been able to sort web pages according to their age, for this reason parents need to control internet access for their children. Of course, parents will have difficulty choosing web pages that are appropriate for their child's age due to the large number of web pages. To overcome these problems needed a system that can classify web pages automatically. With this system, of course, it can also make web pages accessed by children more controlled according to their age. Therefore, in this study the classification of children's web pages was performed automatically using the WVSVM algorithm. To find out the performance of WVSVM, in this study the test results of the WVSVM algorithm will be compared with the results of testing the LSA-SVM and WPFS-SVM algorithms. By using the confusion matrix, the results show that WVSVM is superior to the other two algorithms, which get 74% for accuracy, 76% for precision, 68% for recall and f-measure by 71%, the test results are the results of classification using the RBF kernel and data ratio of 80:20.