Poetra, Muhammad Andika Pratamawanda and Sutedi, Sutedi (2022) ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST). Masters thesis, Institut Informatika dan Bisnis Darmajaya.
![[img]](http://repo.darmajaya.ac.id/style/images/fileicons/text.png) |
Text
1. Cover Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-2.pdf Download (440kB) |
|
Text
2. Halaman Persetujuan Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-2.pdf Download (210kB) |
|
Text
3. Halaman Pengesahan Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-2.pdf Download (188kB) |
|
Text
4. Abstrak Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST).pdf Download (163kB) |
|
Text
5. Daftar Isi Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-2.pdf Download (59kB) |
|
Text
6. Bab I Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-3.pdf Download (152kB) |
|
Text
7. Bab II Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-4.pdf Download (328kB) |
|
Text
8. Bab III Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-5.pdf Download (112kB) |
|
Text
9. Bab IV Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-6.pdf Download (1MB) |
|
Text
10. Bab V Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-7.pdf Download (87kB) |
|
Text
11. Daftar Pustaka Tesis 1821210030 ANALISIS LEVEL ADAPTASI SISWA TERHADAP PEMBELAJARAN ONLINE MENGGUNAKAN ORANGE (K-NEAREST NEIGBOR, TREE, CN2 RULE INDUCTION, DAN RANDOM FOREST)-8.pdf Download (79kB) |
Abstract
This study uses Orange Data Mining tools because of their superiority in terms of visualization, where Orange provides many widgets that can be placed on the canvas that can link between the widgets we have chosen, making it easier for users to be able to process data automatically and also intuitively. Where Orange is used for algorithms namely K-Nearest Neigbor, Tree, CN2 Rule Inducer, and Random Forest to be able to find out which algorithm can provide the highest accuracy results, which can then be used to predict what factors influence student adaptation to online learning in accordance with factors contained in the “Students' Adaptability Level Prediction in Online Education using Machine Learning Approaches” dataset. The analysis step that will be carried out in this study begins with collecting data sources from Kagle, then conducting a training dataset using Orange, which in this case uses four algorithms, namely: K-Nearest Neigbor, Tree, CN2 Rule Induction, and Random Forest. Then a comparison of the accuracy values of the four algorithms is carried out so that it can be seen which algorithm has the highest accuracy value, so that it can be used to find out what factors influence the level of adaptation of online learning students. In this study the CN2 Rule Inducer algorithm has the highest accuracy value of 92.4%, while the highest accuracy value in previous research is the Random Forest algorithm which is 89.63%. With reference to the magnitude of the Accuracy value obtained by the CN2 Rule Inducer model and the visualization results using the Distribution widget, it is obtained that Load Shedding, Location, and Financial Condition are the most influential factors in students' adaptation to online learning. Key words: Orange Data Mining, Online Learning, K-Nearest Neigbor, Tree, CN2 Rule Inducer, Random Forest
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | Ilmu Komputer eTheses |
| Divisions: | Pasca Sarjana > Magister Teknologi Informasi |
| Depositing User: | Mr Muhammad Andika Pratamawanda Poetra - |
| Date Deposited: | 21 Dec 2022 03:16 |
| Last Modified: | 21 Dec 2022 03:16 |
| URI: | http://repo.darmajaya.ac.id/id/eprint/10114 |
Actions (login required)
 |
View Item |