中文关键词:红外光谱轮胎橡胶K近邻种类鉴别 英文关键词:IR spectratire rubberKNNidentification 基金项目:

作者	单位	E-mail
桑国通	中国人民公安大学刑事科学技术学院 北京	15210028033@163.com
廖晓曦	中国人民公安大学国际警务执法学院 北京
何欣龙	中国人民公安大学刑事科学技术学院 北京
王继芬	中国人民公安大学刑事科学技术学院 北京	Email:wangjifen58@126.com

摘要点击次数:1525 全文下载次数:0 中文摘要: 在法庭科学领域,轮胎橡胶颗粒的检验鉴别对交通肇事和一些诉讼案件的侦破尤为重要,针对传统取样分析技术会破坏物证的问题和综合考察样本在多变量多维度上的差异性,提出基于红外光谱法结合K近邻算法无损识别轮胎橡胶的鉴别方法。采集不同品牌的样本,对其光谱进行自动基线校正和归一化操作,采用Savitsky-Golay算法平滑去噪,通过降维实现对840个原始特征到5个识别特征的高效筛选,运用训练样本为测试样本的方法进行交互验证,选取K值为1,“特征3”为主要自变量,“特征4”、“特征5”、“特征2”和“特征1”为协变量作为分类参数,按重要性加权特征进行计算样本之间的距离,建立分类模型,模型总分类准确率达83.56%,区分效果良好,结合样本红外谱图展开进一步分析,最终成功将73类样本分为了10类。结果表明,利用红外光谱检测和K近邻算法可实现对轮胎橡胶颗粒的识别与分类,普适性和高效性较强,具有一定的借鉴和参考意义。 英文摘要: In forensic science, it is particularly important for the rapid detection of traffic accidents and some lawsuits to identify the tire rubber. A method, non-destructive identification of tire rubber based on infrared spectroscopy and radial basis function neural network, is proposed based on the problem of traditional sampling and analysis techniques would destroy the physical evidence and the comprehensive consideration of multi-variable and multi-dimensional differences in samples. Collected different brands samples, performed automatic baseline correction and normalization on their spectra, and used the Savitsky-Golay algorithm to smooth denoise. Dimension reduction method is used to achieve efficient screening of 840 original features to 4 identification features. Using cross-validation of training samples for test samples and Selecting the K value of 1, "Feature 3" as the main independent variable, and "Feature 4", "Feature 5", "Feature 2", and "Feature 1" as covariates as classification parameters. Calculating the distance between samples according to the weighted feature of importance to establish a classification model. The total classification accuracy rate is 83.56%, and the result is well. Finally, 73 samples were successfully divided into 10 categories. The results show that combing the IR spectral detection and KNN can identify the tire rubber spectra. Which has a strong universality and high efficiency, it has certain reference and reference significance. 查看全文查看/发表评论下载PDF阅读器 相关附件：版权转让声明书支持信息修改说明 -->