2018 · 33 citations · 5 references
ComputingComputer ScienceData MiningFeature EngineeringMachine LearningAnomaly DetectionClassificationEnsemble LearningEnsemble MethodsFault DetectionFeature SelectionAccuracyAnomaly ClassificationBest-first SearchFeature Selection For ClassificationHealth MonitoringMonitoring SystemsRandom Forest Classification
Anomaly Detection is widely used in applications related but not limited to intrusion detection, fault detection, fraud detection, health monitoring systems and many other places. The overall efficiency of these applications depends on the classification algorithm that is chosen. An efficient classification algorithm can thus greatly improve the accuracy of these applications. This paper proposes a hybrid approach involving Random Committee and Random Tree techniques for anomaly classification, resulting in most encouraging accuracy values. The proposed scheme is followed after the preprocessing phase that involves Feature Selection using Correlated Feature Selection (CFS) algorithm with the Best-First Search technique.
5
Hamed Haddad Pajouh, Reza Javidan, Raouf Khayami et al. · IEEE Transactions on Emerging Topics in Computing · 2016 · 493 citations · Full text
Generic Feature Extraction for Classification using Fuzzy C - Means Clustering
K. G. Srinivasa, Ameet Singh, Anju Thomas et al. · 2005 · 16 citations
ADE: An ensemble approach for early Anomaly Detection
Teodora Sandra Buda, Haytham Assem, Lei Xu · 2017 · 16 citations
Robust regression for anomaly detection
Ziyu Wang, Jiahai Yang, Chenxi Li · 2017 · 14 citations