• Corpus ID: 197638503

Implementasi Data Mining dengan Seleksi Fitur untuk Klasifikasi Serangan pada Intrusion Detection System ( IDS )

@inproceedings{Mongkareng2017ImplementasiDM,
  title={Implementasi Data Mining dengan Seleksi Fitur untuk Klasifikasi Serangan pada Intrusion Detection System ( IDS )},
  author={Donny Mongkareng and Noor Akhmad Setiawan and Adhistya Erna Permanasari},
  year={2017}
}
System and network security with only firewall device installed is not enough to prevent the attack. Increased attacks has caused very large data to be analyzed , existing Internet network security system has limitations on the ability to adapt large amounts of data and types of new various attacks. The use of Intrusion Detection System (IDS) combined with a firewall installation has become a standard security system and network. Research on Intrusion Detection System (IDS) currently is still… 

Analisis Data Log IDS Snort dengan Algoritma Clustering Fuzzy C-Means

TLDR
The result of analysis shows that the observed network security system is still vulnerable as IDS Snort records 30% of medium risk attacks and the evaluation with Modified Partition Coefficient obtains clustering validity value of 98%.

Forecasting Pneumonia Toddler Mortality Using Comparative Model ARIMA and Multilayer Perceptron

TLDR
A predictive model for the next period of pneumonia under-five mortality in Indonesia showed that the MLP method was superior to ARIMA, with a hidden layer value of 2.2, a learning rate of 0.3, and an error percentage of 1.27%.

Klasifikasi Jenis serangan DOS dan Probing pada IDS menggunakan metode K- Nearest Neighbor

IDS (Intrusion Detection System ) adalah sebuah aplikasi perangkat keras atau perangkat lunak yang otomatis bekerja untuk memonitor kejadian pada sebuah jaringan komputer dan sekaligus menganalisais

SELEKSI ATRIBUT PADA ALGORITMA RADIAL BASIS FUNCTION NEURAL NETWORK MENGGUNAKAN INFORMATION GAIN

Abst rak : Salah satu metode jaringan syaraf tiruan yang sering digunakan untuk klasifikasi data adalah jaringan RBF karena arsitektur yang sederhana dan pembelajaran jaringan yang cepat. Klasifikasi

Klasifikasi Kemampuan Perawatan Diri Anak dengan Disabilitas Menggunakan Neural Network dan Greedy Stepwise Sebagai Seleksi Fitur

Disabilitas merupakan gangguan, keterbatasan aktivitas dan pembatasan partisipasi. Disabilitas disebut juga interaksi antara individu dengan kondisi kesehatan seperti (Cerebral palsy, sindrom Down

Student's Skills Competency Test Prediction Using C4.5 Algorithm

  • Ultach EnriJ. JamanM. Ananda
  • Education
    Proceedings of the Proceedings of the 7th Mathematics, Science, and Computer Science Education International Seminar, MSCEIS 2019, 12 October 2019, Bandung, West Java, Indonesia
  • 2020
TLDR
The purpose of the research is to find out how competent the students' in their vocation as well as new strategies for educators in providing more effective learning by using C4.5 algorithm combining with feature selection.

References

SHOWING 1-10 OF 35 REFERENCES

Intrusion Detection System Using Data Mining Technique : Support Vector Machine

TLDR
The experimental results show that the authors can reduce extensive time required to build SVM model by performing proper data set pre-processing, and attack detection rate of SVM is increased and False Positive Rate (FPR) is decrease.

Penerapan Metode Support Vector Machine pada Sistem Deteksi Intrusi secara Real-time

TLDR
Based on the test result, the sistem can help system administrator to build a model or pattern automaticaly with high accuracy, high attack detection rate, and low false positive rate and also can run in real-time environment.

Performance Analysis Of Different Feature Selection Methods In Intrusion Detection

TLDR
A comparative analysis of different feature selection methods are presented on KDDCUP’99 benchmark dataset and their performance are evaluated in terms of detection rate, root mean square error and computational time.

Analysis of KDD '99 Intrusion Detection Dataset for Selection of Relevance Features

TLDR
Rough set degree of dependency and dependency ratio of each class were employed to determine the most discriminating features for each class and empirical results show that seven features were not relevant in the detection of any class.

Feature Selection for Intrusion Detection Using Random Forest

TLDR
Results show that the Random Forest based proposed approach can select most important and relevant features useful for classification, which reduces not only the number of input features and time but also increases the classification accuracy.

Selection of Relevant Feature for Intrusion Attack Classification by Analyzing KDD Cup 99

TLDR
In this paper, KDD ’99 intrusion detection dataset is evaluated to find out most important and relevant features.

A Novel Approach to Intrusion Detection System using Rough Set Theory and Incremental SVM

TLDR
RST (Rough Set Theory) and Incremental SVM (Support Vector Machine) to detect intrusions are used and the features selected by RST will be sent to SVM model to learn and test respectively.

Anomaly Based Network Intrusion Detection with Unsupervised Outlier Detection

TLDR
This paper applies one of the efficient data mining algorithms called random forests algorithm in anomaly based NIDSs, and presents the modification on the outlier detection algorithm of random forests that is comparable to previously reported unsupervised anomaly detection approaches evaluated over the KDD' 99 dataset.

DATA MINING IN NETWORK SECURITY-TECHNIQUES & TOOLS : A RESEARCH PERSPECTIVE

TLDR
A supervise d learning based Intrusion Detection System (IDS) to identify the intruders, attackers in a network is proposed and covers the most significant advances and emerging research issues in the field of data mining in network security.

Selecting Features for Intrusion Detection: A Feature Relevance Analysis on KDD 99

TLDR
To substantiate the performance of machine learning based detectors that are trained on KDD 99 training data, the relevance of each feature is investigated and information gain is employed to determine the most discriminating features for each class.