Small targets detection based on hierarchical clustering;

A new hierarchical clustering algorithm based on tree edit distance;

Combined unsupervised image segmentation using watershed and hierarchical clustering with MRF;

Based on the multi-dimensional approximate periodic pattern, we present an algorithm to mine multi-dimensional temporal approximate periodicity with the algorithm of hierarchical cluster, then applies to the stock data.

An equivalence relation ≡HCov is proposed based on the Data Cube s semantics and the dimension s hierarchy of its pattern, and then on the basis of the equivalence relation, proceeds the data cube to hierarchical cluster.

The result, normally overpredicted by traditional Environment Envelope Model, is improved by using hierarchical cluster arith- metic that can reduce the influence caused by outliers.

This paper presental a secondary classification method based on 1-a-1 SVM classification algorithm after a general overview of typical methods for a multiclass SVM.

Thus a modified classification method of multi-class SVM is proposed, and a secondary classification based on OAO-SVU classification is implemented, thus improving the mixing degree between among the classes with multiple erroneously-classified samples.