Respiratory Motion Estimation with Hybrid Implementation - Prediction and Classification of Respiratory Motion - page 65

Chapter 4
Respiratory Motion Estimation
with Hybrid Implementation
The extended Kalman filter (EKF) can be used for the purpose of training
nonlinear neural networks to perform desired input-output mappings. To improve
the computational requirements of the EKF, Puskorius et al. proposed the
decoupled extended Kalman filter (DEKF) as a practical remedy for the proper
management of computational resources. This approach, however, sacrifices
computational accuracy of estimates because it ignores the interactions between
the estimates of mutually exclusive weights. To overcome such a limitation,
therefore, we proposed hybrid implementation based on EKF (HEKF) for respi-
ratory motion estimate, which uses the channel number for the mutually exclusive
groups and the coupling technique to compensate the computational accuracy.
Moreover, the authors restricted to a DEKF algorithm for which the weights
connecting inputs to a node are grouped together. If there are multiple input
training sequences with respect to time stamp, the complexity can increase by the
power of input channel number. To improve the computational complexity, we
split the complicated neural network into a couple of the simple neural networks to
adjust separate input channels. The experiment results validated that the prediction
overshoot of the proposed HEKF was improved by 62.95 % in the average pre-
diction overshoot values. The proposed HEKF showed the better performance by
52.40 % improvement in the average of the prediction time horizon. We have
evaluated that a proposed HEKF can outperform DEKF by comparing the pre-
diction overshoot values, the performance of tracking estimation value and the
normalized root mean squared error (NRMSE).
4.1 Introduction
The problem of predicting the moving objects with a given reference trajectory is a
common estimate problem [ 1 - 5 ]. Kalman filters can be widely used in many
industrial electronics for the state estimation and prediction [ 6 - 14 ]. Due to
increasingly complex dynamical systems, a variety of methodologies has
been proposed based on the Kalman filter and its hybrid approach [ 15 - 19 ].