Recognition of Pulse Wave Feature Points and Non-invasive Blood Pressure Measurement

Humans have a variety of pulse waveforms based on their physiological state. The recognition of the feature points of the pulse wave is very helpful in analyzing the body's physiological and pathological conditions and in preventing and diagnosing cardiovascular diseases. This paper proposes an accurate recognition algorithm of the feature points based on wavelet analysis and time domain characteristics of the pulse wave. Further, this study examines the Hidden Markov Model and performs non-invasive blood pressure estimation on a number of subjects. The experiments show that the algorithm can effectively identify the feature points of the pulse wave. The results of the model are consistent with the actual measurement results and the correlation coefficient reached 96 %, which indicates that the algorithm is significant as a method for non-invasive blood pressure monitoring.