EUVIMEDEUVIMED entdecken
Crossref

Advanced Network Traffic Visualization and Anomaly Detection Using PCA-MDS Integration and Histogram Gradient Boosting Regression

Sudhakara Reddy Peram, Rajendra Kattunga

Journal of Artificial intelligence and Machine Learning · 2023

DOI: 10.55124/jaim.v1i3.281 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial intelligence and Machine Learning, 2023. Verfasst von Sudhakara Reddy Peram und 1 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As organizations increasingly rely on computer networks for their daily operations, network traffic visualization has become increasingly important. The complexity and volume of raw network traffic data pose significant challenges to human interpretation, forcing the need to transform numerical data into understandable visual formats. This study addresses these challenges by introducing an innovative approach that combines multiple visualization techniques and machine learning methods to improve network traffic analysis and anomaly detection. The research explores four primary visualization approaches: data filtering and transformation, pixel-based techniques, graph-based representations, and integrated multi-view systems. A new method is proposed that incorporates Principal component analysis (PCA) and multidimensional scaling (MDS) serve as efficient techniques for dimensionality reduction, and colour mapping techniques. The system analyses key network performance metrics, including traffic load (MBps), latency (ms), packet loss percentage, and jitter (ms), to provide comprehensive network monitoring capabilities. To improve the prediction accuracy, histogram gradient boosting regression is used, providing excellent performance in handling large-scale datasets with missing values and categorical features. The combined approach demonstrates significant advantages over traditional methods such as t-SNE, especially in preserving multidimensional properties and managing extensive data volumes. This research contributes to more efficient network management through improved network security, improved anomaly detection capabilities, and advanced visualization and machine learning integration. Keywords: Network traffic visualization, anomaly detection, principal component analysis, multidimensional scaling, histogram gradient boosting regression, dimensionality reduction, network security, packet loss, machine learning, data visualization

Zitieren

APA

Peram, S. R., & Kattunga, R. (2023). Advanced Network Traffic Visualization and Anomaly Detection Using PCA-MDS Integration and Histogram Gradient Boosting Regression. Journal of Artificial intelligence and Machine Learning. https://doi.org/10.55124/jaim.v1i3.281

Vancouver

Peram SR, Kattunga R. Advanced Network Traffic Visualization and Anomaly Detection Using PCA-MDS Integration and Histogram Gradient Boosting Regression. Journal of Artificial intelligence and Machine Learning. 2023. doi:10.55124/jaim.v1i3.281

BibTeX
@article{Peram2023,
  author = {Peram, Sudhakara Reddy and Kattunga, Rajendra},
  title = {Advanced Network Traffic Visualization and Anomaly Detection Using PCA-MDS Integration and Histogram Gradient Boosting Regression},
  journal = {Journal of Artificial intelligence and Machine Learning},
  year = {2023},
  doi = {10.55124/jaim.v1i3.281}
}
Kostenlos starten →