Perfomance of Kernel SOM considering Adjacency for Damage Evaluation

We evaluated clustering perfomance of Kernel SOM considering adjacency within the obtained map upon Acoustic Emission (AE) waves involved in damage such as crack, friction and collision. Here, we employed Kullback-Leibler (KL) kernel that is based on a distance between probability distributions as a distance between frequency spectrum distributions. Also standard clustering measures, e.g., cluster purity and F-measure, are extended so as to consider adjacency within the map obtained by SOM. Using simulated AE data sets, we confirmed the KL kernel performs the best among the several standard kernels in terms of F-measure. Also we discussed about separability and density of classes together with the visualized maps. 1. は じ め に