A Fast Lane Approach to {LMS} Prediction of Respiratory Motion Signals

Type of publication:  Artikel
Zeitschrift: Biomedical Signal Processing and Control
Band: 3
Nummer: 4
Jahr: 2008
Seiten: 291-299
Notiz: Motion Compensation in Radiosurgery
DOI: 10.1016/j.bspc.2008.06.001
Abriss: As a tool for predicting stationary signals, the Least Mean Squares (LMS) algorithm is widely used. Its improvement, the family of normalised LMS algorithms, is known to outperform this algorithm. However, they still remain sensitive to selecting wrong parameters, being the learning coefficient mu and the signal history length M. We propose an improved version of both algorithms using a Fast Lane Approach, based on parallel evaluation of several competing predictors. These were applied to respiratory motion data from motion-compensated radiosurgery. Prediction was performed using arbitrarily selected values for the learning coefficient mu in ]0,0:3] and the signal history lengthM in [1, 15]. The results were compared to prediction using the globally optimal values of mu and M found using a grid search. When the learning algorithm is seeded using locally optimal values (found using a grid search on the first 96 s of data), more than 44% of the test cases outperform the globally optimal result. In about 38% of the cases, the result comes to within 5% and, in about 9% of the cases, to within 5–10% of the global optimum. This indicates that the Fast Lane Approach is a robust method for selecting the parameters mu and M.
Nutzerfelder: owner={ernst}, timestamp={2008.01.24}, file={esds_08.pdf:esds_08.pdf:PDF}
Schlagworte: LMS, Parameter selection, Radiosurgery, Respiratory motion prediction
Autoren: Ernst, Floris
Schlaefer, Alexander
Dieterich, Sonja
Schweikard, Achim
  • esds_08.pdf