In lighting design in buildings, the conventional algorithms may cause significant calculation error of light energy distribution and may not ensure illumination uniformity. In this paper, the radiation method in comp...
详细信息
The recognition of accelerative and decelerative patterns in the fetal heart rate (FHR) is one of the tasks carried out manually by obstetricians when they analyze cardiotocograms for information respecting the fetal ...
详细信息
The recognition of accelerative and decelerative patterns in the fetal heart rate (FHR) is one of the tasks carried out manually by obstetricians when they analyze cardiotocograms for information respecting the fetal state. However, any delay in the detection of an anomaly and in subsequent clinical intervention obviously increases the risk of problems arising during birth or in the early months of life. For this reason it is essential for any computerized detection system to function in real time. The classical approaches to this problem have focused on the development of algorithmic models which, however, pose problems in terms of their adaptation to the baseline of the signal. In order to overcome this problem, an approach based on artificial neural networks (ANNs) formed by a multilayer perceptron (MLP) has been developed. However, since the system utilizes the FHR signal as direct input, an anterior stage has had to be incorporated that applies a principal component analysis (PCA) so as to make the system independent of the signal baseline. Furthermore, the introduction of multiresolution into the PCA has resolved other problems that were detected in the application of the system. Presented in this paper are the results of a validation of these systems-henceforth designated the PCA-MLP and multiresolution principal component analysis (MR-PCA) systems-against three clinical experts.
暂无评论