Anomaly detection using a class of supervised and unsupervised learning algorithms

Abstract

Translate Article

Anomaly detection is a concept that has been studied for many decades now, and many frameworks and algorithms are proposed after that. Intrusion can occur in any scenario, so identifying one becomes a vital task. The reverberation of not detecting these outliers can be severe and can result in a huge loss. In this chapter, we concentrate on identifying an anomaly using supervised and unsupervised learning techniques, for instance support vector machine (SVM), artificial neural network (ANN), long short-term memory recurrent neural network (LSTM-RNN), isolation forest, and K-means clustering algorithm. Four real-world open-source datasets are studied for this purpose, and a statistical method known as the adaptive threshold is utilized for the detection of anomalous data points in these datasets. Several regression metrics are obtained for the datasets, and anomalies corresponding to these datasets are compared with unsupervised learning algorithms.