Seismic events discrimination using a new FLVQ clustering model

In this paper, the LVQ (Learning Vector Quantization) model and its variant s are regarded as the clustering tools to discriminate the natural seismic events (earthquakes) from the artificial ones (nuclear explosions). The stu dy is based on the six spectral features of the P-wave spectra computed fro m the short period teleseismic recordings. The conventional LVQ proposed by Kohenen [2] and also the Fuzzy LVQ (FLVQ) models proposed by Sakuraba [16] and Bezdek [2] are all tested on a set of 26 earthquakes and 24 nuclear ex plosions using the leave-one-out testing strategy. The primary experimental results have shown that the shapes, the number and also the overlaps of th e clusters play an important role in seismic classification. The results al so showed how an improper feature space partitioning would strongly weaken both the clustering and recognition phases. To improve the numerical result s, a new combined FLVQ algorithm is employed in this paper. The algorithm i s composed of two nested sub-algorithms. The inner sub-algorithm tries to g enerate a well-defined fuzzy partitioning with the fuzzy reference vectors in the feature space. To achieve this goal, a cost function is defined as a function of the number, the shapes and also the overlaps of the fuzzy refe rence vectors. The update rule tries to minimize this cost function in a st epwise learning algorithm. On the other hand, the outer sub-algorithm tries to find an optimum value for the number of the clusters, in each step. For this optimization in the outer loop, we have used two different criteria. In the first criterion, the newly defined "fuzzy entropy" is used while in the second criterion, a performance index is employed by generalizing the H untsberger formula [10] for the learning rate, using the concept of fuzzy d istance. The experimental results of the new model show a promising improve ment in the error rate, an acceptable convergence time, and also more flexi bility in boundary decision making.