Compare time series mining approaches for mapping function assessment

To estimate intracranial pressure (ICP) noninvasively, a data mining framework was proposed in our previous work. In the procedure, the mapping function plays an important role to estimate ICP based on the feature vector extracted from arterial blood pressure (ABP) and flow velocity (FV), which is translated to the estimated errors by the mapping function for each entry in the database. In this paper, the different mapping function solutions, linear least squares (LLS), total least squares (TLS) 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. In our previous studies, STR is a better solution for mapping function. Among the tested three solutions for mapping function in this paper, the STR method still shows to be superior to the methods of LLS and TLS.