Name
Title | ||
|---|---|---|
Improved Blood Pressure Estimation Using Photoplethysmography Based on Ensemble Method |
Abstract | ||
|---|---|---|
Many noninvasive continuous blood pressure measurements using photoplethysmography (PPG) are still inadequate in terms of accuracy and stability, which hinders the practical application of this method. This paper proposes a model based on ensemble method for BP estimation using PPG. A number of blood pressure calculation base-models is built on the same training data. These base-models are used to estimate the blood pressure and the results of each base-model are processed synthetically with clustering. Stepwise regression and artificial neural networks (ANN) are used to build base-models within the ensemble model respectively. Compared to single model, the accuracy and stability of blood pressure (BP) estimation are expected to improve further with this method. University of Queensland vital signs dataset [8], which contains a variety of vital signs data recorded from patients undergoing anesthesia, is used to verify the effectiveness of the proposed method. We employed it to estimate systolic blood pressure (SBP), diastolic blood pressure (DBP) and mean blood pressure (MBP). It could be confirmed that the estimation accuracy and stability of the proposed method is higher than that with single model. In order to extract the feature points of the PPG signal whose quality is poor, a robust feature extraction method is proposed. This method can effectively extract the characteristic information in the experiment. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1109/ISPAN-FCST-ISCC.2017.42 | 2017 14th International Symposium on Pervasive Systems, Algorithms and Networks & 2017 11th International Conference on Frontier of Computer Science and Technology & 2017 Third International Symposium of Creative Computing (ISPAN-FCST-ISCC) |
Keywords | Field | DocType |
Blood pressure estimation,Ensemble model,Stepwise regression,ANN,PPG,Feature extraction | Stepwise regression,Ensemble forecasting,Pattern recognition,Photoplethysmogram,Computer science,Vital signs,Feature extraction,Artificial intelligence,Blood pressure,Cluster analysis,Artificial neural network | Conference |
Volume | ISBN | Citations |
2017-November | 978-1-5386-0841-8 | 0 |
PageRank | References | Authors |
0.34 | 4 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Junjun Pan | 1 | 3 | 1.44 |
| Yue Zhang | 2 | 20 | 5.10 |