one class SVM
时间: 2024-01-10 07:08:49 浏览: 15
One-class SVM (Support Vector Machine) is a machine learning algorithm used for anomaly detection. It is a type of unsupervised learning algorithm that learns a boundary of the normal data points in a dataset and classifies any new data point as either normal or anomalous based on its position relative to this boundary.
It requires only one class of data points for training, which is the normal class. It then learns a decision boundary that separates the normal data points from the rest of the dataset. Any data point that falls outside this boundary is considered an anomaly or outlier.
One-class SVM is commonly used in applications such as fraud detection, intrusion detection, and fault detection in industrial systems. It is also useful for detecting rare events and anomalies in large datasets where the normal class is well-defined.