DEVICE FOR GENERATING ANEMIA DETECTION MODELS, ANEMIA DETECTION DEVICES, METHODS FOR GENERATING ANEMIA DETECTION MODELS, ANEMIA DETECTION METHODS

Abstract

The invention refers to a device that generates anomaly-determining models. It creates the first anomaly-determining model by calculating the mean and variance of each variable in the case where the maximum value of the correlation between variables is less than a predetermined value for K L-dimensional vectors in an L-dimensional variable space. It creates the second anomaly-determining model by performing principal component analysis and calculating the coefficient of variation of the principal component in the case where the maximum value of the correlation between variables is greater than or equal to a predetermined value. It creates an M-dimensional vector structure comprising M types of simultaneous variables and generates a third anomaly-determining model by performing principal component analysis on multiple M-dimensional vectors and calculating the coefficient of variation of the principal component in the case where the time series signals during normal operation have M types (M > 2).