The new trajectory outlier detection,proposed in this paper,can be used to determine whether two trajectories are globally matched by calculating the local matching degree between every base comparing unit pairs.

While using Hough transform in dim and small target trajectory detection,there will be some problems,such as short trajectory may be submerged,peaks be blurred and no information about the lines\' ends.

Attribute selection-based and support vector machine for anomaly detection;

Network anomaly detection based on attributes similarity and cloud model;

Unsupervised anomaly detection based on a multi-layer perceptron;

Research on method of network abnormal detection based on Hurst parameter estimation;

Protected scheme for email virus based on abnormal detection

This paper proposes one kind of network intrusion and abnormal detection models on the basis of a network supporting vector machine,which can inspect network intrusion and abnormal detection with the class II categorized ability of support vector machine(SVM).

Continuous outlier detection over evolving data streams.;

Efficient outlier detection method based on Voronoi diagram;

Application of structural damage diagnosis using density-based outlier detection;

Design and implementation of anomaly detecting engine for inter-domain routing system;

In order to reduce the impact of sampled traffic on network anomaly detecting,a novel method with variable sampling rates in traffic sampling is proposed.