2020
DOI: 10.1007/978-981-15-2693-0_14
|View full text |Cite
|
Sign up to set email alerts
|

The Impact of Different Feature Scaling Methods on Intrusion Detection for in-Vehicle Controller Area Network (CAN)

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2020
2020
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(6 citation statements)
references
References 19 publications
0
6
0
Order By: Relevance
“…MMS, defined by Equation 1 is known to be the most commonly used normalization technique, but its drawback is hinged on its inability to handle outliers completely; thus, it may lead to some values being extremely small. For this reason, we adopted the QT method proposed in [44].…”
Section: B Database Description Transformation and Image Generationmentioning
confidence: 99%
“…MMS, defined by Equation 1 is known to be the most commonly used normalization technique, but its drawback is hinged on its inability to handle outliers completely; thus, it may lead to some values being extremely small. For this reason, we adopted the QT method proposed in [44].…”
Section: B Database Description Transformation and Image Generationmentioning
confidence: 99%
“…Among the normalization techniques, minmax and quantile normalization are the two commonly used methods that can convert data values to the same range. As min-max normalization does not handle outliers well and may cause most data samples to have extremely small values, quantile normalization is used in the proposed framework [15]. The quantile normalization method transforms the feature distribution to a normal distribution and re-calculates all the features values based on the normal distribution.…”
Section: B Data Description and Transformationmentioning
confidence: 99%
“…The quantile normalization method transforms the feature distribution to a normal distribution and re-calculates all the features values based on the normal distribution. Therefore, the majority of variable values are close to the median values, which is effective in handling outliers [15].…”
Section: B Data Description and Transformationmentioning
confidence: 99%
“…Results on all datasets revealed that when the z-score technique is applied, the ANN produces the best performance. Also (Lokman et al, 2019), have shown the effect of different normalization techniques on the accuracy performance of anomaly detection in cyberattacks.…”
Section: Literature Reviewmentioning
confidence: 99%