CLASSIFICATION PREDICTION DATA PROCESSING METHOD FOR PHOTOPLETHYSMOGRAPHY-BASED BLOOD PRESSURE MEASUREMENT DEVICE

摘要

A classification prediction data processing method for a photoplethysmography-based blood pressure measurement device, comprising the following steps: extracting features from acquired photoplethysmography signals, and recording corresponding blood pressure values (S100); classifying the blood pressure values according to common blood pressure range intervals and providing classification labels (S200); dividing the classified blood pressure value data into training data and test data, and selecting a classification algorithm to construct a classification training model (S300); for the successfully created classification training model, using the test data to perform classification prediction, collecting statistics on the classification prediction accuracy, and adjusting and optimizing the classification training model according to the accuracy (S400); and invoking the optimized classification training model to predict the category of a blood pressure value interval of a test object, so as to obtain the category of the blood pressure value interval, thereby predicting the blood pressure value (S500). Said method can lower the prediction difficulty while maintaining the prediction accuracy, reducing the influence of the randomness of actually measured data on measurement.