Name
Title | ||
|---|---|---|
Health status monitoring for ICU patients based on locally weighted principal component analysis. |
Abstract | ||
|---|---|---|
•The approach of LWPR-PCA is first introduced into the field of health status monitoring and achieves the best monitoring performance in terms of adaptability to the changes in patient status and sensitivity to abnormality.•Some improvement measures are given on status monitoring when using MPCA, and a self-adapting model is tried to be established.•Compared with the latest reported method L-PCA, LWPR-PCA can achieve superior performance in terms of both the fault detection rate (FDR) and false alarm rate (FAR). |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1016/j.cmpb.2017.12.019 | Computer Methods and Programs in Biomedicine |
Keywords | Field | DocType |
Adaptive online monitoring,Intensive care unit (ICU),Locally weighted projection regression (LWPR),Principal component analysis (PCA) | Computer vision,Statistic,Computer science,Partial least squares regression,Vital signs,Patient status,Kernel principal component analysis,Artificial intelligence,Intensive care,Principal component analysis,Machine learning,Computational complexity theory | Journal |
Volume | ISSN | Citations |
156 | 0169-2607 | 0 |
PageRank | References | Authors |
0.34 | 19 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yangyang Ding | 1 | 2 | 0.71 |
| Xin Ma | 2 | 112 | 14.29 |
| Youqing Wang | 3 | 220 | 25.81 |