Respiratory motion prediction using moving window based online training approach for LS-SVM

Prediction of respiratory motion to ablate tumors in chest and abdominal region is non-trivial because of the presence of intra-trace variabilities and irregularities. In recent past, several signal processing methods have been developed to model and predict respiratory motion. However, their prediction performance is susceptible to prediction horizons, irregularities and intra-trace variabilities. To counter these limitations and hence to enhance the prediction performance, in this paper, we proposed a moving window based online training approach for least squares support vector machines (LS-SVM) for respiratory motion prediction. To validate the proposed method, experiments have been conducted on ten real-respiratory motion traces. Results show that, the proposed online approach reduces prediction error compared to the conventional LS-SVM. Further, results demonstrate that the proposed approach provides better prediction performance than existing respiratory motion prediction methods.