Library

Comparing Feature Extraction techniques using SVM for Early Fault Classification in NFV context

Networks are adopting virtualization techniques and thus, become large distributed software-driven systems. Ensuring Quality of Service (QoS) in such complex environments is critical and arduous especially now. We need to detect and correct expeditiously the issues as well as to understand systems behavior i.e. need for Root Cause Analysis. In this paper, we propose a comparative study of two Feature Extraction (FE) approaches for Early Fault Classification combined with two Support Vector Machine (SVM) algorithms while having preliminary symptoms in a Network Function Virtualization (NFV) based environment. We use data generated with a stimulus-based approach in such a context, and we compare two existing FE techniques in combination with SVM. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are applied to features for early fault classification. LDA in combination with SVM leads to an accuracy of 90%.

Computer ScienceEngineering
View graphSource

Paper

Full text

PDF

Comparing Feature Extraction techniques using SVM for Early Fault Classification in NFV context

Semantic Scholar · Computer Science · 2021

Abstract

Networks are adopting virtualization techniques and thus, become large distributed software-driven systems. Ensuring Quality of Service (QoS) in such complex environments is critical and arduous especially now. We need to detect and correct expeditiously the issues as well as to understand systems behavior i.e. need for Root Cause Analysis. In this paper, we propose a comparative study of two Feature Extraction (FE) approaches for Early Fault Classification combined with two Support Vector Machine (SVM) algorithms while having preliminary symptoms in a Network Function Virtualization (NFV) based environment. We use data generated with a stimulus-based approach in such a context, and we compare two existing FE techniques in combination with SVM. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are applied to features for early fault classification. LDA in combination with SVM leads to an accuracy of 90%.

Source of record · Semantic Scholar

Similar papers

Machine Learning Approaches to Early Fault Detection and Identification in NFV ArchitecturesArij Elmajed, A. Aghasaryan, É. Fabre2020 · IEEE Conference on Network Softwarization · 12 citations In Library
Comparative Analysis of Network Fault Classification Using Machine LearningJunichi Kawasaki, Genichi Mouri, Yusuke Suzuki2020 · IEEE/IFIP Network Operations and Management Symposium · 13 citations In Library
Fault classification in the architecture of virtual machine using deep learningAjay Rawat, Anupama Mishra, Hind Alsharif et al.2025 · Scientific Reports · 1 citation In Library
A Nonlinear Support Vector Machine-Based Feature Selection Approach for Fault Detection and Diagnosis: Application to the Tennessee Eastman ProcessMelis Onel, C. Kieslich, E. Pistikopoulos2018 · AIChE journal. American Institute of Chemical Engineers · 82 citations In Library
Fault Detection and Diagnosis in Automotive Control Systems using Machine LearningAnil Pandurang Jawalkar, Sanjeev Kumar, Ram Deshmukh et al.2023 In Library
Anomaly Detection and Localization in NFV Systems: an Unsupervised Learning ApproachSeyed Soheil Johari, Nashid Shahriar, M. Tornatore et al.2022 · IEEE/IFIP Network Operations and Management Symposium · 16 citations In Library
Vertical Split Learning-Based Identification and Explainable Deep Learning-Based Localization of Failures in Multi-Domain NFV SystemsFatima Ezzeddine, Omran Ayoub, Davide Andreoletti et al.2023 · Conference on Network Function Virtualization and Software Defined Network · 8 citations In Library
Machine Learning-Based Anomaly Detection in NFV: A Comprehensive SurveySehar Zehra, Ummay Faseeha, Hassan Jamil Syed et al.2023 · Italian National Conference on Sensors · 40 citations In Library
Combined morphology and SVM-based fault feature extraction technique for detection and classification of transmission line faultsRevati Godse, S. Bhat2020 · Turkish J. Electr. Eng. Comput. Sci. · 9 citations In Library
Detection of Misuse Attack in NFV Networks Using Machine LearningAli Khalid Ali, W. Bhaya2021 · Journal of Physics: Conference Series · 0 citations In Library
© 2026 NYSGPT2525 LLC