摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑发布了关于食品研究的新研究结果。根据NewsRx编辑在中国杭州的新闻报道，研究表明：“石斛是一种高效的中药材，不同品种的功效和价格差异很大。因此，对石斛进行有效分类至关重要。”本研究的资助单位包括浙江科技大学科学研究基金会.记者从浙江农工大学的研究中得到一句话：“然而，现有的菊属植物的鉴定方法大多难以同时达到无损和高效的目的，这使得真正满足工业产品离子的需要成为一个挑战。”将激光诱导击穿光谱(LIBS)与多元模型相结合,对10个石斛品种进行分类,从3个圆形药用区块采集每个石斛品种的LIBS光谱数据,在数据分析阶段,首先利用高斯滤波和叠加相关系数特征选择对LIBS光谱数据进行预处理,然后利用多元模型对不同树枝状石斛品种进行分类。结果表明，与支持向量机(SVM)、随机森林(RF)和k最近neighbors(KNN)相比，该方法的分类精度分别提高了14%、20%和20%，并与添加主成分分析(PCA)的MS三种模型(SVM、RF和KNN)的分类精度分别提高了10%、10%和17%。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New study results on food research have been publ ished. According to news reporting out of Hangzhou, People’s Republic of China, by NewsRx editors, research stated, “Dendrobium, a highly effective traditional Chinese medicinal herb, exhibits significant variations in efficacy and price am ong different varieties. Therefore, achieving an efficient classification of Den drobium is crucial.” Funders for this research include Scientific Research Foundation of Zhejiang A A nd F University. Our news reporters obtained a quote from the research from Zhejiang A& F University: “However, most of the existing identification methods for Dendrobi um make it difficult to simultaneously achieve both non-destructiveness and high efficiency, making it challenging to truly meet the needs of industrial product ion. In this study, we combined Laser-Induced Breakdown Spectroscopy (LIBS) with multivariate models to classify 10 varieties of Dendrobium. LIBS spectral data for each Dendrobium variety were collected from three circular medicinal blocks. During the data analysis phase, multivariate models to classify different Dendr obium varieties first preprocess the LIBS spectral data using Gaussian filtering and stacked correlation coefficient feature selection. Subsequently, the constr ucted fusion model is utilized for classification. The results demonstrate that the classification accuracy of 10 Dendrobium varieties reached 100% . Compared to Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Ne ighbors (KNN), our method improved classification accuracy by 14%, 20%, and 20%, respectively. Additionally, it outperfor ms three models (SVM, RF, and KNN) with added Principal Component Analysis (PCA) by 10 %, 10%, and 17%.”
NETL
NSTL