An adaptive combination of adaptive filters for plant identification

In this paper, we propose to adaptively combine two LMS adaptive transversal filters for plant identification. One of the filters has a high and the other a low adaption step, in order to combine good tracking capabilities under (fast) change conditions with a reduced convergence error along stationary periods. A brief discussion of the characteristics of the combination is included, emphasizing that it allows the possibility of dealing with "intermediate" rate of change situations, in opposition to (implicit or explicit) switching mechanisms. A selected illustrative simulation example shows the effectiveness of this approach. Some complementary lines of research are indicated, from the points of view of improving the algorithm and of extending the fields of application.