Research on the recognition method of blood circulation system based on pulse wave

Konferenz: BIBE 2019 - The Third International Conference on Biological Information and Biomedical Engineering
20.06.2019 - 22.06.2019 in Hangzhou, China

Tagungsband: BIBE 2019

Seiten: 9Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Su, Zimei; Yao, Junyi; Deng, Bin; Shen, Zhanqiu (Institute of Sensor and Reliability Engineering, Harbin University of Science and Technology, Harbin, China)

This paper proposes a recognition method of the blood circulation system on the basis of pulse wave: the Expectation-Maximization algorithm(EM) is used to solve the Gaussian Mixture Model to obtain the pulse wave characteristic parameters by the Gaussian Mixture Model fits the pulse wave, and the pulse wave feature date set is established. The Gradient Boosting Decision Tree algorithm identifies the operating state of the blood circulation system. The following two questions are studied by using the pulse wave feature date set. 1: When the pulse wave is fitted with several Gaussian components, the blood circulation system recognition is the best. 2: Which of the pulse wave characteristic parameters represented by the Gaussian Mixture Model is most closely related to the blood circulation system operating state.