We propose that discriminant clusters identify the representative structures in each class, and common clusters represent the similarities between classes.
Then, clusters with a fairly equal mix of feature vectors from different classes are identified as overlapped clusters and labeled as common clusters (i.e., K c clusters).
From the entire clusters, 25% were assigned as common clusters and the remaining clusters labeled class normal or abnormal as explained in hard labeling scheme.
Two types of clusters are identified: discriminant clusters which mainly consist of feature vectors from one specific class, and common clusters which are a mixture of features from different classes.
In order to quantify the significance of the overlap between different classes, the clusters with more that 30% of overlap are assigned to the common clusters, and the remaining clusters are identified as the discriminant clusters.
Although the advantage of the hard and fuzzy labeling is the identification of the representative clusters for each class and discriminating them from the common clusters, the method requires that each class contributes with the same number of feature vectors.
A test signal is classified as a class e signal, if the majority of its test feature vectors (i.e., excluding the feature vectors assigned to common clusters) belong to class e.
This method applied an unsupervised clustering to the feature vectors from all the different classes, and then used a supervised labeling method to select two types of clusters: discriminant and common clusters.
The label of the above cluster is assigned to each test feature, and is used to determine the class f → test belongs to: f → test ∈ Class e if α u f = e, (10) Once all the feature vectors in a test signal are labeled, the feature vectors that are assigned to common clusters are excluded and the labeling of the remaining feature vectors are used to classify the signal.
A test signal is classified as a class e signal, if the majority of its test feature vectors (i.e., excluding the feature vectors assigned to common clusters) belong to class e. Cluster f → test, the cluster, which each test feature belongs to, is found as the nearest cluster based on ED criterion: Cluster f → test = arg Min i u = 1, …, K, f → test − C → u, = u f, (9).
A few subjects contributed multiple ICs to one or more of the common clusters.
