Introducing DBSCAN in the singular spectrum analysis procedure

Abstract

This work proposes using DBSCAN to recognition of noise components of eigentriples in the grouping stage of SSA. The DBSCAN is a modern (revised in 2013) and expert method at to identify noise through regions of lower density. The hierarchical clustering method was the last innovation in noise recognition in SSA approach, implemented on package RSSA. However, it repeated in the literature that the hierarquical clustering method is very sensitive to noise, is unable to separate it correctly, and should not be used in clusters with varying densities and neither works well in clustering time series of different trends. Unlike, the density based clustering methods are effective in separating the noise from the data and dedicated to work well on data from different densities. This work shows better efficiency of DBSCAN over the others methods already used in this stage of SSA, because it allows considerable reduction of noise and provides better forecasting. The result is supported by experimental evaluations realized for simulated stationary and non-stationary series. The proposed combination of methodologies also was applied successfully to forecasting a real series of winds speed.