Combination optimization-based near-infrared non-invasive blood glucose detection wavelength variable screening method

Abstract

The invention provides a combination optimization-based near-infrared non-invasive blood glucose detection wavelength variable screening method. The method comprises the following steps of firstly obtaining transmissivity spectral data of human blood glucose detection by adopting LED near-infrared light sources with different wavelengths; secondly selecting an optimal variable group in groups by using a continuous projection algorithm, a genetic algorithm and a gradual selection algorithm for multiple pieces of wavelength variable data by taking a root-mean-square error as an index in combination with linear regression modeling; thirdly performing scoring on each group of variables through a weighted scoring method; and finally recombining three groups of variables, sorting comprehensive scores in sequence from high to low, and selecting first few variables with highest scores as final auxiliary variables. According to an algorithm, a most effective wavelength combination is extracted through weighted combination optimization for the problem of an over-fitting phenomenon of a model due to excessive wavelength variables in regression modeling; and the variables are accurately selected, so that the model can be greatly simplified, the calculation complexity of the model is lowered, and the prediction capability and the real-timelines and robustness of non-invasive blood glucose detection are improved.

Description

technical field [0001] The invention belongs to the technical field of non-invasive blood sugar detection by near-infrared light transmission, and in particular relates to a method for selecting a near-infrared wavelength variable using a combination optimization algorithm for non-invasive blood sugar detection of a human body. Background technique [0002] In recent years, with the development of chemometrics and the improvement of the design and manufacture of optical components, the concept and practice of near-infrared (NIR, Near infrared) spectral analysis technology for non-invasive detection of human blood sugar have become more and more mature. The regression model between the LED near-infrared light source transmission method and the blood sugar concentration of the human body can be used to predict the blood sugar concentration of the human body. There are many LEDs with different wavelengths to choose from in engineering applications. In the modeling of NIR combi...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above-mentioned technical problems that the single search method will fall into local optimum and the model robustness is not strong when selecting variables, the present invention provides a method for selecting wavelength variables based on weighted combination optimization. Based on the projection algorithm and the genetic algorithm, a more reasonable and more robust wavelength variable is screened out therefrom. The present invention includes the following steps:

Images