Open AccessESR temperature compensation algorithm based on BP neural network
Author(s) -
Li Liu,
Xiaohui Chen,
Yuqing Wu
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/768/7/072098
Subject(s) - compensation (psychology) , artificial neural network , erythrocyte sedimentation rate , sedimentation , atmospheric temperature range , temperature measurement , computer science , range (aeronautics) , artificial intelligence , biological system , algorithm , materials science , physics , thermodynamics , surgery , medicine , biology , psychology , paleontology , sediment , psychoanalysis , composite material
Erythrocyte sedimentation rate (ESR) is an important medical test parameter, changes in ESR value can reflect changes in the condition,ESR measurements are susceptible to ambient temperature.This paper proposes a temperature compensation algorithm for ESR measurement based on BP neural network,temperature compensation can be ESR value detection result,to further improve the measurement accuracy erythrocyte sedimentation rate.Firstly, a neural network model of ESR temperature compensation is established. Secondly, learning training samples of the network are obtained and the sample data is pre-processed and network trained. Finally, the network prediction effect is tested to generate an optimal ESR temperature compensation network model.The algorithm proposed in this article can use the neural network method to correct the erythrocyte sedimentation measurement value, and can quickly and accurately achieve temperature compensation of the erythrocyte sedimentation value. This algorithm not only makes the accuracy of the compensation link within the measurement tolerance range, but also for the temperature without training Points have predictive compensation effects.