首页|New Findings from Jiangsu University Update Understanding of Robotics and Machin e Learning (Accurate Identification of Cadmium Pollution In Peanut Oil Using Mic rowave Technology Combined With Svm-rfe)
New Findings from Jiangsu University Update Understanding of Robotics and Machin e Learning (Accurate Identification of Cadmium Pollution In Peanut Oil Using Mic rowave Technology Combined With Svm-rfe)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on Robotics and Machine Lea rning have been published. According to news reporting out of Zhenjiang, People' s Republic of China, by NewsRx editors, research stated, "A qualitative identifi cation method of heavy metal cadmium concentration in peanut oil with microwave detection technology was presented. Initially, on the basis of national standard s, the configured samples were classified into three categories: negative, which did not exceed the national standard; weak positive, which slightly exceeded th e national standard; and strong positive, which far exceeded the national standa rd." Financial support for this research came from National Key Research and Developm ent Program of China. Our news journalists obtained a quote from the research from Jiangsu University, "Then, the obtained transmission index was subjected to data dimensionality red uction, using three feature dimensionality reduction methods, namely Principal c omponent analysis (PCA) strategy, recursive feature elimination (RFE) algorithm, and RFE-PCA algorithm, respectively, and the dimensionality-reduced data were u sed as inputs to establish the random forest (RF) classification model, and the results showed that the three feature dimensionality reduction methods could ach ieve better prediction results. Among them, the RFEPCA- RF model has the best pr ediction performance, at this time, the RFE algorithm retains 35 feature points and number of principal components (PCs) is 7. Next, the structure of RFE model is optimized, and the SVM-RFE-PCA-RF model is constructed by using support vecto r machines (SVM) as its weight allocator and the analysis of the results of its running 50 times reveals that the discriminative accuracy of the prediction set reaches 100% for 31 times, which meets the requirement of high-pre cision qualitative identification of three types of samples."
ZhenjiangPeople's Republic of ChinaA siaRobotics and Machine LearningAlgorithmsCadmiumDimensionality Reductio nEmerging TechnologiesHeavy MetalsMachine LearningTechnologyTransition ElementsJiangsu University
NETL
NSTL
