A Review of Classification Approaches Using Support Vector Machine in Intrusion Detection

Kausar, Noreen; Belhaouari, Samir Brahim; Abdullah, Azween; Ahmad, Iftikhar; Hussain, Muhammad

doi:10.1007/978-3-642-25462-8_3

Cited by 22 publications

(18 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, good results indicate that the generalization relationship establishment between class labels and data representation is easy. Based on structural risk minimization, the SVM avoids the local minimum and provides better generalization abilities than other classification algorithms[ 40 ]. Although 1-NN is highly restricted in terms of the forms of data distribution in the representation space[ 41 ], it is derived from density estimation technology and simply assigns test data to the same class as the nearest point from the training set.…”

Section: Methodsmentioning

confidence: 99%

Locally Embedding Autoencoders: A Semi-Supervised Manifold Learning Approach of Document Representation

Wei

Luo

et al. 2016

PLoS ONE

View full text Add to dashboard Cite

Topic models and neural networks can discover meaningful low-dimensional latent representations of text corpora; as such, they have become a key technology of document representation. However, such models presume all documents are non-discriminatory, resulting in latent representation dependent upon all other documents and an inability to provide discriminative document representation. To address this problem, we propose a semi-supervised manifold-inspired autoencoder to extract meaningful latent representations of documents, taking the local perspective that the latent representation of nearby documents should be correlative. We first determine the discriminative neighbors set with Euclidean distance in observation spaces. Then, the autoencoder is trained by joint minimization of the Bernoulli cross-entropy error between input and output and the sum of the square error between neighbors of input and output. The results of two widely used corpora show that our method yields at least a 15% improvement in document clustering and a nearly 7% improvement in classification tasks compared to comparative methods. The evidence demonstrates that our method can readily capture more discriminative latent representation of new documents. Moreover, some meaningful combinations of words can be efficiently discovered by activating features that promote the comprehensibility of latent representation.

show abstract

Section: Methodsmentioning

confidence: 99%

Locally Embedding Autoencoders: A Semi-Supervised Manifold Learning Approach of Document Representation

Wei

Luo

et al. 2016

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…SVM is the most useful technique of Machine learning [3,13]. An SVM plays effective role as a classification technique in a problem, such as signal processing, often providing a huge enhancement over challenging methods [4,18,29].…”

Section: Support Vector Machine (Svm)mentioning

confidence: 99%

Machine Learning for Cyber Threat Detection

More¹

2020

IJATCSE

View full text Add to dashboard Cite

In recent years, anomaly detection has more importance in networking domains. Machine learning is very effective in anomaly detection to improve accuracy in classification. To ensure automated and effective cyber threat detection, analysis of security logs from the dataset is required. Usage of the internet increases cyber-attacks and at present, the cyber security situation is pessimistic. Use of social media and networking has increased in daily life, nowadays all are learning and working by using the internet but on the other hand, it becomes serious security threats problem. Thus the development of the Intrusion Detection System (IDS) is essential to provide an extra level of security. Cyber threat is an important issue faced by all organizations. However, it has difficult to use machine learning algorithms for threat detection analysis, due to huge number of negative threats detection, especially in the case of large scale environments. In this paper, we surveyed clustering and classification of machine learning algorithms. Using machine learning algorithms cyber threats and false detection rates are reduced which increases the performance of the system.

show abstract

“…Under the first class, referred to as B S ucc , the arrested block cases are grouped, while the passing block cases are found to the second class, B Fail . As dealing with two classes, a Support Vector Machine (SVM), was used for creating the meta-model (Brereton and Lloyd, 2010;Kausar et al, 2011). The second meta-model was developed with reference to the B Fail cases with the aim to predict the block kinetic energy reduction due to the block-barrier interaction.…”

Section: The Meta-modeling Approachmentioning

confidence: 99%

Introducing Meta-models for a More Efficient Hazard Mitigation Strategy with Rockfall Protection Barriers

et al. 2018

View full text Add to dashboard Cite

The paper presents a new approach to assess the effecctiveness of rockfall protection barriers, accounting for the wide variety of impact conditions observed on natural sites. This approach makes use of meta-models, considering a widely used rockfall barrier type and was developed from on FE simulation results. Six input parameters relevant to the block impact conditions have been considered. Two meta-models were developed concerning the barrier capability either of stopping the block or in reducing its kinetic energy. The outcome of the parameters range on the meta-model accuracy have been also investigated. The results of the study reveal that the meta-models effective in reproducing with accuracy the response of the barrier to any impact conditions, providing a formidable tool to support the design of these structures. Furthermore, allowing to accomodate the effects of the impact conditions on the prediction of the block-barrier interaction, the approach can be successfully used in combination with rockfall trajectory simulation tools to improve rockfall quantitative hazard assessment and optimise rockfall mitigation strategies.

show abstract

A Review of Classification Approaches Using Support Vector Machine in Intrusion Detection

Cited by 22 publications

References 19 publications

Locally Embedding Autoencoders: A Semi-Supervised Manifold Learning Approach of Document Representation

Locally Embedding Autoencoders: A Semi-Supervised Manifold Learning Approach of Document Representation

Machine Learning for Cyber Threat Detection

Introducing Meta-models for a More Efficient Hazard Mitigation Strategy with Rockfall Protection Barriers

Contact Info

Product

Resources

About