Abstracting Steady Qualitative Descriptions over Time from Noisy, High-Frequency Data

ing Steady Qualitative Descriptions over Time from Noisy, High-Frequency Data Silvia Miksch, Andreas Seyfang, Werner Horn, Christian Popow 1 Institute of Software Technology, University of Technology, Vienna, fsilvia, [email protected] 2 Department of Medical Cybernetics and Arti cial Intelligence, University of Vienna [email protected] 3 Austrian Research Institute for Arti cial Intelligence, Vienna 4 Department of Pediatrics, University of Vienna [email protected] Abstract. On-line monitoring at neonatal intensive care units produces On-line monitoring at neonatal intensive care units produces high volumes of data. Numerous devices generate data at high frequency (one data set every second). Both, the high volume and the quite high error-rate of the data make it essential to reach at higher levels of description from such raw data. These abstractions should improve the medical decision making. We will present a time-oriented data-abstraction method to derive steady qualitative descriptions from oscillating highfrequency data. The method contains tunable parameters to guide the sensibility of the abstraction process. The bene ts and limitations of the di erent parameter settings will be discussed.