Image of PENERAPAN MULTI-CLASSIFICATION SERANGAN SIBER DENGAN METODE NAÏVE BAYES DAN CHI-SQUARE FEATURE SELECTION

Skripsi

PENERAPAN MULTI-CLASSIFICATION SERANGAN SIBER DENGAN METODE NAÏVE BAYES DAN CHI-SQUARE FEATURE SELECTION

Penilaian

0,0

dari 5
Penilaian anda saat ini :  

The Naïve Bayes method has proven effective in detecting, evaluating, and performing multi-classification of cyberattacks. By leveraging the Chi-Square Feature Selection algorithm, accuracy can be improved by selecting the most relevant features for detecting attacks, enabling classification based on their types. The datasets used for testing and multi-classification include CIC-IDS2018, CIC-IDS2017, ISCX2012, and KDD-CUP 1999 in CSV format. The implementation of Chi-Square Feature Selection successfully achieved high F1-Score values on each dataset, considering the datasets are imbalanced. Optimal results were obtained with an 80:20 ratio for CIC-IDS2017 and 2018 datasets, a 20:80 ratio for ISCX 2012 dataset, and a 70:30 ratio for KDD-CUP 1999 dataset. Besides the appropriate ratio selection, the choice of model also plays a crucial role, where the Gaussian Naïve Bayes model is effective for CIC-IDS2018 and ISCX 2012 datasets, while the Multinomial Naïve Bayes model performs better for CIC-IDS2017 and KDD-CUP 1999 datasets. Validation confirms the importance of selecting a Naïve Bayes model that matches the dataset characteristics, key to achieving optimal performance in cyberattack detection. With a careful approach to feature selection, data ratio, and model choice, the system can produce accurate and efficient results in detecting cyberattacks.

Availability
Inventory Code Barcode Call Number Location Status
2407002623T143678T1436782024Central Library (References)Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1436782024
Publisher
Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya.,
Collation
vi, 46 hlm.; ilus; tab; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
004.07
Content Type
Text
Media Type
unmediated
Carrier Type
-
Edition
-
Subject(s)
Prodi Sistem Komputer
Specific Detail Info
-
Statement of Responsibility
Other version/related

No other version available

File Attachment
Comments
You must be logged in to post a comment