Abstract
The purpose of cuff-less blood pressure estimation is to realize a continuous monitoring blood pressure. Many studies, however, can be applied only to certain conditions such as when applying the rest and physical load, they are not always available in the daily life. Blood pressure and pulse wave are changed under the several influences, for example room temperature, biological rhythm (seasons and time), the measurement attitude, diet, and so on. Here the important thing is that the relationship between the variations of the pulse wave and blood pressure is different. Using an estimator which is modeled from the increasing blood pressure by physical load, it is difficult to estimate the correct variation of blood pressure influenced by other factors. In this study, we show a difference of relationship between the blood pressure variability and photoplethysmograph features by each factor, such as the load and temperature and diet and season. It becomes an important finding in cuff-less blood pressure estimation. Furthermore, it is shown that the estimation accuracy increases by considering separately the model for each blood pressure variation factors.
