【摘要】 目的 优化牙釉质电子顺磁共振（EPR）谱拟合程序。 方法 将牙釉质EPR谱拟合程序中的RIS-BGS偏移量设置为定参，取优化值；增加手动拟合功能，可以将参数初始值直接代入高斯模型得到拟合谱。 结果 将牙釉质EPR谱拟合程序中RIS-BGS偏移量设置为定参后，其优化值为0.529，减少了变参数量；采用手动拟合功能有助于调整参数初始值；在自动拟合程序对于个别样品谱不能给出正确结果情况时，仍然可以通过手动拟合来得到一个近似的拟合结果。 结论 优化了EPR谱拟合程序的应用过程。【Abstract】 Objective To optimize the enamel electron paramagnetic resonance (EPR) spectrum fitting procedure. Methods RIS-BGS offset was set as a determined parameter in enamel EPR spectrum fitting program, and an optimized value was given for RIS-BGS offset. A manual fitting function was designed that can substite the initutial value into the Gaussian model function directly. Results RIS-BGS offset was set as a determined parameter, the optimized value of which was 0.529. The number of parameters decreased; the manual fitting function maked it easier to select initial values for parameters. When the auto fitting program failed to give a correct result for some EPR spectrum, a fitting result could still be obtained with the manual fitting method. Conclusion The application of the spectrum fitting procedure can be optimized.
The in-vivo electron paramagnetic resonance (EPR) method can be used for on-site, rapid, and non-invasive detection of radiation dose to casualties after nuclear and radiation emergencies. For in-vivo EPR spectrum analysis, manual labeling of peaks and calculation of signal intensity are often used, which have problems such as large workload and interference by subjective factors. In this study, a method for automatic classification and identification of in-vivo EPR spectra was established using support vector machine (SVM) technology, which can in-batch and automatically identify and screen out invalid spectra due to vibration and dental surface water interference during in-vivo EPR measurements. In this study, a spectrum analysis method based on genetic algorithm optimization neural network (GA-BPNN) was established, which can automatically identify the radiation-induced signals in in-vivo EPR spectra and predict the radiation doses received by the injured. The experimental results showed that the SVM and GA-BPNN spectrum processing methods established in this study could effectively accomplish the automatic spectra classification and radiation dose prediction, and could meet the needs of dose assessment in nuclear emergency. This study explored the application of machine learning methods in EPR spectrum processing, improved the intelligence level of EPR spectrum processing, and would help to enhance the efficiency of mass EPR spectra processing.