X射线荧光光谱结合多元分类模型鉴别橡胶鞋底  

Identification of Rubber Soles by X-ray Fluorescence Spectroscopy Combined with Multiple Classification Model

作　　者：林凡琦 姜红[1] 王嘉庚 满吉 LIN Fanqi;JIANG Hong;WANG Jiageng;MAN Ji(College of Investigate,People’s Public Security University of China,Beijing 100038;Fengtai Branch of Beijing Municipal Public Security Bureau,Beijing 100071;Beijing Huayi Hongsheng Technology Limited Company,Beijing 100123)

机构地区：[1]中国人民公安大学侦查学院,北京100038 [2]北京市公安局丰台分局,北京100071 [3]北京华仪宏盛技术有限公司,北京100123

出　　处：《分析科学学报》2022年第2期214-218,共5页Journal of Analytical Science

基　　金：中国人民公安大学基本科研业务费重点项目(No.2021JKF212)。

摘　　要：为了实现对不同种类的橡胶鞋底样本的快速鉴别,利用X射线荧光光谱法对50个橡胶鞋底样本进行快速无损检测并建立数学分类模型。为探寻最佳建模方法,以鞋的种类作为因变量,分别利用多层感知器神经网络(MLP)、二元logistic回归、fisher判别分析建立分类模型。相比较3种分类模型,MLP模型对不同种类橡胶鞋底分类准确率最高,总体分类准确率达94%,对于皮鞋的区分率达100%。结果表明,利用X射线荧光光谱结合多层感知器神经网络模型,可实现对橡胶鞋底样本的准确鉴别与区分,能够为实际侦查鉴定工作提供借鉴。For the rapid classification of different types of rubber sole samples,50 rubber sole samples were tested by X-ray fluorescence spectroscopy.In order to explore the best modeling method,the type of shoes was taken as the dependent variable,and the classification model was established by multi-layer perceptrone(MLP) neural network,binary logistic regression and Fisher discriminant analysis.Among the three classification models,MLP model has the highest classification accuracy for different types of rubber soles,with an overall classification accuracy of 94% and a distinguishing rate of 100% for leather shoes.The results show that X-ray fluorescence spectroscopy combined with MLP model can be used to accurately identify and distinguish rubber sole samples,which can provide reference for the actual forensic identification work.

关 键 词：X射线荧光光谱 橡胶鞋底 多层感知器神经网络 鉴别检验 

分 类 号：O657.34[理学—分析化学]