Text

VISUALISASI PDF MALWARE MENGGUNAKAN CLUSTERING K-MEANS PADA LAYANAN GARUDA KEMDIKBUD DIKTI SEBAGAI AGREGATOR NASIONAL

---

Penilaian

---

K-Means clustering is a method to grouping data based on the similarity of features and detect the hidden patterns in dataset. The dataset is from GARUDA Repository which contains raw data of PDF files. GARUDA dataset extraction process used static analysis method. The data extraction process produced twenty�one features using PDFiD. GARUDA dataset has a multi-class and imbalanced data, therefore a SMOTE process is required. K-Means succeed to grouping 3 clusters with silhouette score is 0,71311. A best validation result is using K-Means label and support with Logistic Regression model at 5-Fold. The accuracy of K�Means label is 94,66%, hence K-Means labeling is better than GARUDA labeling that only obtained the accuracy of 87,16%.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307000285	T86535	T865352023	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T865352023

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer., 2023

Collation

xiii, 51 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.840 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Jurusan Sistem Komputer
Malware

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment