2012
DOI: 10.1016/j.protcy.2012.05.017
|View full text |Cite
|
Sign up to set email alerts
|

Intrusion Detection using Naive Bayes Classifier with Feature Reduction

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
134
0
3

Year Published

2015
2015
2021
2021

Publication Types

Select...
7
2

Relationship

0
9

Authors

Journals

citations
Cited by 381 publications
(137 citation statements)
references
References 10 publications
0
134
0
3
Order By: Relevance
“…In their paper proposed in 2012, S. Mukherjee and N. Sharma [21] designed a technique called Feature-Vitality Based Reduction Method (FVBRM) using a Naïve Bayes classifier. FVBRM identifies important features by using a sequential search approach, starting with all features, one feature is removed at a time until the accuracy of the classifier reaches some threshold.…”
Section: Description Of Nsl-kddmentioning
confidence: 99%
“…In their paper proposed in 2012, S. Mukherjee and N. Sharma [21] designed a technique called Feature-Vitality Based Reduction Method (FVBRM) using a Naïve Bayes classifier. FVBRM identifies important features by using a sequential search approach, starting with all features, one feature is removed at a time until the accuracy of the classifier reaches some threshold.…”
Section: Description Of Nsl-kddmentioning
confidence: 99%
“…In [6] the authors reduced the number of input features in order to propose an efficient and effective IDS. They reduced the features using four different feature selection methods and used Naïve Bayes classification algorithm as the classifier to evaluate the results.…”
Section: Related Workmentioning
confidence: 99%
“…Generally speaking, the basic idea of intrusion detection can be mainly classified into two categories including signature-based detection [3] and anomaly detection [4]. The former is also called pre-knowledge or active detection method.…”
Section: Introductionmentioning
confidence: 99%
“…One is to cut the training and predicting time as much as possible, and the other is to eliminate the data redundancy and irrelevancy. According to [15], the mainstreamed typical feature selecting methods include filter method and wrapper method [3,16] which are based on retaining features and removing features respectively.…”
Section: Introductionmentioning
confidence: 99%