References in periodicals archive ?
The results show that CVNN can be used for contingency evaluation purpose.
Firstly, we compare the performance of CVNN and RSNN with different number of sequences in FS.
As is shown in figure 7 and figure 8, CVNN is more effective than RSNN in both cases.
The reason is that, for fixed memory amounts, more samples in RSNN and more CVs in CVNN can be generated for small length sequence set.
We propose a comprehensive processing method CVNN to solve this problem based on CV structure concept.
Since all three cluster ensemble methods get perfect partition results on synthetic data set, we only compare CVNN indices of different ensemble methods on ACT2 data set, which is presented in Table 1.
In Table 1, the smaller values of CVNN of our new method also show that new approach has better partition results on ACT2 data set.
In addition, we set the clusters' number from 14 to 24 as the input of spectral embedding and applied CVNN to estimate the most plausible number of clusters.
The values of "+CVNN" are the average clusters' numbers decided by the CVNN cluster validity index.
Acronyms browser ?
Full browser ?