Analysis of Feature Selection Approaches in Large Scale Cyber Intelligence Data with Deep Learning

Ahmetoglu, Huseyin; Daş, Resul

doi:10.1109/siu49456.2020.9302200

Cited by 4 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Cloud Computing senaryosunda güvenlik duvarına bir uyarı sistemi eklemeyi önerdiler ve modelin başarısını artırmak için NSGA-II algoritmasını kullanmışlardır. Bir başka çalışmamızda [8] oylamaya dayalı öznitelik seçimi yaklaşımını IDS için hem ikili hem de çoklu sınıflandırma için önerdik. Altı farklı öznitelik seçim yönteminde en çok oyu almış öznitelikler DNN kullanılarak sınıflandırılmış ve ikili sınıflandırma için 8 öznitelikle yüzde 92 başarı elde edilmiştir.…”

Section: Literatürdeki İlgili çAlışmalarunclassified

“…Gömülü öznitelik seçimi ise filtre ve sarmalayıcı tekniklerinin oluşturduğu hibrit bir yaklaşımdır. İçerisinde barındırdığı bayes ve karar ağacı sınıflandırıcıları ile model için en etkili öznitelikler seçilebilir [8]. Bu çalışmada ise sezgisel ve sığ makine öğrenmesi tekniklerinden oluşan sarmalayıcı bir yaklaşım önerilmektedir.…”

Section: öZnitelik Seçim Yöntemleriunclassified

See 1 more Smart Citation

Genetic Feature Selection Approach in Detection of Web Application Attacks Using Machine Learning Methods

Ahmetoglu

Daş

2021

Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi

View full text Add to dashboard Cite

Applications on the Internet have some coding-related security concerns. Weaknesses or vulnerabilities allow criminals to gain direct and public access to databases to steal sensitive data. This study proposes an approach based on heuristic feature selection and machine learning for easier and more accurate detection of web application attacks with hybrid intrusion detection systems. Web application attacks and benign flow examples in CIC-IDS2017 and CSE-CIC-IDS2018 datasets were combined after a series of data preprocessing stages, and a new dataset was created. Using Genetic Algorithm and LogisticRegression, mean square error and feature count optimization were performed, and the results were tested with five different machine learning algorithms. When the results obtained were examined, it was observed that the success rate in classification remained at the level of 99%, although the number of features was reduced by 85%

show abstract

Section: Literatürdeki İlgili çAlışmalarunclassified

Section: öZnitelik Seçim Yöntemleriunclassified

Genetic Feature Selection Approach in Detection of Web Application Attacks Using Machine Learning Methods

Ahmetoglu

Daş

2021

Türkiye Bilişim Vakfı Bilgisayar Bilimleri Ve Mühendisliği Dergisi

View full text Add to dashboard Cite

show abstract

“…However, even though the selected features have the highest correlation with the class labels, they may still be correlated with each other and contain redundant information, leading to the loss of useful information from the original feature subset [25]. Therefore, to obtain the best feature subset with strong representational capabilities, DL models, due to their powerful adaptive information extraction capabilities, have been widely applied in feature selection across various scenarios [26][27][28]. To further enhance the performance of DL models in specific tasks, the attention mechanism (AM) [29] has been introduced into the field of DL.…”

Section: Introductionmentioning

confidence: 99%

Attention features selection oversampling technique (AFS-O) for rolling bearing fault diagnosis with class imbalance

Han,

Wang,

Shen

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

When using data-driven methods for fault diagnosis of mechanical rotating components such as gears and bearings, there is a problem of class imbalance in the lifecycle data collected by sensors. The most commonly used method to address this issue is the synthetic minority over-sampling technique, which synthesizes samples in the feature space, but its blind synthesis may lead to redundant features in the synthetic samples. To avoid this deficiency, this paper proposes a feature-weighted oversampling method called AFS-O (Attention Features Selection Oversampling Technique). First, time–frequency domain features are extracted from the full lifecycle data of bearings to construct an initial subset of features, which serves the input to AFS. Then, AFS is then used to obtain the distribution of feature selection patterns and generate feature weights to determine the inclusion or exclusion of each feature, thereby constructing an optimal subset of features. Finally, the optimal feature subset is synthetically oversampled to achieve class-balanced data, which is then fed into a classifier. AFS-O is applied to the rolling bearing accelerated lifetime dataset from Xi’an Jiaotong University. Experimental results demonstrate that AFS-O outperforms other state-of-the-art synthetic oversampling algorithms in terms of Gmean, F 2 score , and Recall, confirming the effectiveness of the proposed method.

show abstract

Intelligent Computing Techniques for Sustainable Cybersecurity: Enhancing Threat Detection and Response

Praneeth,

Shyashyankhareddy,

Niranjan

2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Analysis of Feature Selection Approaches in Large Scale Cyber Intelligence Data with Deep Learning

Cited by 4 publications

References 7 publications

Genetic Feature Selection Approach in Detection of Web Application Attacks Using Machine Learning Methods

Genetic Feature Selection Approach in Detection of Web Application Attacks Using Machine Learning Methods

Attention features selection oversampling technique (AFS-O) for rolling bearing fault diagnosis with class imbalance

Intelligent Computing Techniques for Sustainable Cybersecurity: Enhancing Threat Detection and Response

Contact Info

Product

Resources

About