Time Series Mining Approach for Noninvasive Intracranial Pressure Assessment: An Investigation of Different Regularization Techniques
Los Angeles, CA
March 31, 2009 to April 2, 2009
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/CSIE.2009.861
A data mining framework has been proposed to estimate intracranial pressure (ICP) non-invasively in our previous work. In the corresponding approach, the feature vector extracted from arterial blood pressure (ABP) and flow velocity (FV) is translated to the estimated errors by the mapping function for each entry in the database. In this paper, three different mapping function solutions, linear least squares (LLS), truncated singular value decomposition (TSVD) and standard Tikhonov regularization (STR) are systemically tested to compare the possible effects of different solutions on the non-invasive ICP estimation. The conducted comparison demonstrated that the selection of mapping function solution actually influences the estimation. Among the tested three solutions for mapping function, TSVD and STR show better ICP estimation performance with smaller ICP errors than LLS.
Non-invasive ICP estimation, Mapping function, Data mining, Least square, Singular value decomposition, Standard Tikhonov regularization
Peng Xu, Shadnaz Asgari, Marvin Bergsneider, Shaozhi Wu, "Time Series Mining Approach for Noninvasive Intracranial Pressure Assessment: An Investigation of Different Regularization Techniques", CSIE, 2009, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, pp. 382-386, doi:10.1109/CSIE.2009.861