Multi-stage Feature Selection for On-Line Flow Peer-to-Peer Traffic Identification

Abdalla, Bushra Mohammed Ali; Jamil, Haitham A.; Hamdan, Mosab; Bassi, Joseph Stephen; Ismail, Idris; Marsono, Muhammad Nadzir

doi:10.1007/978-981-10-6502-6_44

Cited by 6 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The key challenge for selecting features is preserving the appropriate features subset for accurate traffic identification. Traffic classification accuracy is associated with a small number of appropriate features [17], [19]- [21]. Various FS methods select various sets of significant features, but they do not always select the same number of significant features.…”

Section: Challenges In Feature Selection For Traffic Classificationmentioning

confidence: 99%

“…Nonetheless, it is not always so in practice because not every feature is informative and useful. Some statistical flow features may not be relevant and uninformative, while others may have high inter-correlation with each other features and thus redundant [17], [18]. The use of less significant traffic features affects the efficiency and accuracy of network traffic classification [17], [19]- [21].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Edge Computing Intelligence Using Robust Feature Selection for Network Traffic Classification in Internet-of-Things

et al. 2020

Self Cite

View full text Add to dashboard Cite

Section: Challenges In Feature Selection For Traffic Classificationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Edge Computing Intelligence Using Robust Feature Selection for Network Traffic Classification in Internet-of-Things

et al. 2020

Self Cite

View full text Add to dashboard Cite

“…Online features are extracted and online features with IAT and without IAT as suggested in our previous work [28] are selected. For the UNIBS and PAM datasets, the features are extracted based on the first five packets statistic of each flow.…”

Section: Dataset Preprocessingmentioning

confidence: 99%

Impact of Packet Inter-arrival Time Features for Online Peer-to-Peer (P2P) Classification

Abdalla¹,

Hamdan²,

Mohammed³

et al. 2018

IJECE

Self Cite

View full text Add to dashboard Cite

Identification of bandwidth-heavy Internet traffic is important for network administrators to throttle high-bandwidth application traffic. Flow features based classification have been previously proposed as promising method to identify Internet traffic based on packet statistical features. The selection of statistical features plays an important role for accurate and timely classification. In this work, we investigate the impact of packet inter-arrival time feature for online P2P classification in terms of accuracy, Kappa statistic and time. Simulations were conducted using available traces from University of Brescia, University of Aalborg and University of Cambridge. Experimental results show that the inclusion of inter-arrival time (IAT) as an online feature increases simulation time and decreases classification accuracy and Kappa statistic.

show abstract

“…This method is challenged by high resource requirements, its inefficiency on encrypted traffic and privacy related issues. Host behaviour-based [14,16], and flow features-based [11,17] which analyse packet flow [18] and flow duration are alternative approaches that do not require payload inspection [12]. Recently, methods using Transport Layer Statistics features and Machine Learning approaches have been developed [19], and there are continuous studies toward improving their performance.…”

Section: Introductionmentioning

confidence: 99%

Internet data traffic analysis for identifying usage trends on each day of the week in a university

Adekitan

Awosope

2020

IJEECS

View full text Add to dashboard Cite

<p><em>Internet data traffic monitoring and management are important requirements for ensuring top notch quality of service in a network. Data traffic logs contain useful hidden information that can be harnessed and interpreted as a resource for making informed network management decisions. In this study, logged internet data traffic for both the upload and download traffic in a university for one year was analysed using statistics and partial least squares approach to structural equation modelling (PLS-SEM). Time series plots, statistical properties and trends for each day of the week over a 51-week period were developed. The result shows that the most data was downloaded on Thursdays while the most upload occurred on Mondays. A path model was developed using Smart PLS3, and the performance of the model was evaluated using the construct reliability and validity of the model. The results reveal that the weekly variance is majorly accounted for by usage variations on Tuesdays, Fridays and Saturdays. An overall model R-square value of 0.876 was observed.</em></p>

show abstract

Multi-stage Feature Selection for On-Line Flow Peer-to-Peer Traffic Identification

Cited by 6 publications

References 22 publications

Edge Computing Intelligence Using Robust Feature Selection for Network Traffic Classification in Internet-of-Things

Edge Computing Intelligence Using Robust Feature Selection for Network Traffic Classification in Internet-of-Things

Impact of Packet Inter-arrival Time Features for Online Peer-to-Peer (P2P) Classification

Internet data traffic analysis for identifying usage trends on each day of the week in a university

Contact Info

Product

Resources

About