Skripsi
PENGARUH REDUKSI FITUR MENGGUNAKAN SVD PADA PENGKLASIFIKASIAN KNN
High-dimensional data is a data that has many attributes, one of them is internet traffic data. This research used heart disease data with 76 attributes. If the heart disease data is going to be classified, a dimensional reduction technique is needed, because conventional classification algorithms work better in handling low dimensional data. Dimension reduction techniques are classified into 2 types, feature selection and feature extraction. This study will compare the implementation of the Singular Value Decomposition (SVD) algorithm as a feature selection for KNN classification algorithm. The results obtained by ANOVA shows insignificant differences on the value of accuracy, precision, and recall. However, in terms of computation time, the combination of SVD and KNN is proven to be faster than the KNN itself.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2107003602 | T432172 | T432172021 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available