Lintang, Dewi Aprilia (2025) Empirical test performance comparison of post dimension reduction classification algorithm based on Independent Component Analysis (ICA) / Dewi Aprilia Lintang</p>. Diploma thesis, Universitas Negeri Malang.
Full text not available from this repository.Abstract
p This study compares the performance of the Na iuml ve Bayes and Random Forest algorithms after the application of dimensionality reduction using Independent Component Analysis (ICA). ICA is employed to extract independent features from datasets to reduce attribute redundancy without losing significant information. The evaluation aims to analyze the extent to which dimensionality reduction affects the accuracy of both algorithms and to determine which algorithm performs more optimally after ICA implementation. The experimental results indicate that the application of ICA has a varying impact on model accuracy. In some datasets dimensionality reduction improves accuracy whereas in most cases it leads to a decline in performance particularly in the Random Forest algorithm. This suggests that while ICA can simplify data structures it may also remove important information that supports classification performance. Based on the findings it can be concluded that ICA does not always enhance classification model accuracy. The impact of dimensionality reduction depends on the characteristics of the dataset and the algorithm used. Therefore careful consideration is required when selecting a dimensionality reduction method to ensure optimal benefits without significantly compromising model accuracy. /p
| Item Type: | Thesis (Diploma) |
|---|---|
| Divisions: | Fakultas Teknik (FT) > Departemen Teknik Elektro (TE) > S1 Teknik Informatika |
| Depositing User: | library UM |
| Date Deposited: | 02 May 2025 04:29 |
| Last Modified: | 09 Sep 2025 03:00 |
| URI: | http://repository.um.ac.id/id/eprint/400196 |
Actions (login required)
 |
View Item |