Prediction and Tracking Changes in Bio-medical Sensor Data

Summary form only given. Both our preliminary works [1], [2], on biomedical sensor signal processing, have focused on abdominal tumor motion traces. In stereotactic radiotherapy for thoracic and abdominal tumors, respiratory motion management is crucial for improving efcacy of treatment, while minimizing risk to heathy tissue and organs. Since tumor motion exhibits dynamic variation in characteristics, between and within patients, our first work concentrated on predicting imminent anomalous or irregular tumor motion ahead of its occurrence, and our second work consists of analysis of behavioral distribution of tumor motion, used for patient grouping with the aim to improve treatment planning. We propose to develop a module that will automatically decide, which methods/parameter to use based on the signal type. For example, often the initial step for signal processing involves dividing the sensorstime-series into segments and also we proposed a variable length segmentation method and compared its performance against a segmentation method that divided the signal at fixed and equal interval of length, L. Depending on user input or persistent memory (storing past experience or expert opinion) associated with the module, the module will decide which segmentation to use on the current signal. If it decides that the best way to proceed would which segmentation to use on the current signal. If it decides that the best way to proceed would be to use fixed length segmentation, then it will use a variation of genetic programming to determine the best value L.