Each node on the spherical lattice corresponds to a cluster of input vectors that lie in close spatial proximity within the original feature space, and neighbouring nodes on the lattice represent cluster centres with a high degree of vector similarity.
It is worth mentioning that the aforementioned feature selection approaches differ from the subject of our study as the former selects the uncorrelated feature elements in a feature vector to increase the accuracy rate, while the latter keeps all the feature elements and identifies the cluster of feature vectors that are unrelated to the discrimination between classes.
Thus, -means is linear in all relevant factors: iterations, number of clusters, number of vectors and dimensionality of the space.
It can be seen that, in general, there is agreement between the EC and the vector-based classifications; clusters of similar vectors tend to contain enzymes with the same EC 1st number.
This method uses the clustering of feature vectors that consist of parameter vectors corresponding to local datasets and average spatial position of each one.
The considered configurations, instead of assigning each individual to a single cluster, are lists of vectors (one for each individual) carrying their probability to belong to each cluster.
This paper mainly concerns the possibility to improve the clustering of feature vectors because as mentioned earlier, the bottleneck of clustering-based approaches is feature vectors clustering.
We have seen however that the clustering of 15D-5BLC vectors in the unsupervised Kohonen map or the clustering of 18D-5BLC/BLC6 18D-5BLC/BLC6e supervectorsap, are far from perfect in we expecthe a map jusupervised separate clusters for the 27 classes of LC6.
Following the clustering of feature vectors ζ, the original data can be classified by using the correspondence between each feature vector ζ j and a number of original data.
The fuzzy stochastic model is created by combining the fuzzy clusters of input vectors with the radial basis activation functions in the stochastic neural network.
