This paper presents a real-time multiresolution approach for respiratory motion modeling. The proposed methodology utilizes a hybrid approach that combines wellknown linear identification methods with a novel Global-Local Orthogonal Mapping (GLO-MAP) network. Further, adaptation laws are derived using the recent advances in adaptive control to adapt for respiration models in real-time from imagery data. Finally, the effectiveness of the proposed technique is illustrated by testing them on patient's chest motion data captured by imagery data of external markers.
|Title of host publication||2007 IEEE/NIH Life Science Systems and Applications Workshop|
|Number of pages||4|
|ISBN (Print)||978-1-4244-1812-1, 978-1-4244-1813-8|
|Publication status||Published - 08.09.2008|
|Event||2007 IEEE/NIH Life Science Systems and Applications Workshop - Bethesda, United States|
Duration: 08.11.2007 → 09.11.2007
Conference number: 73187