支持向量机
主成分分析
人工智能
稳健性(进化)
模式识别(心理学)
随机森林
计算机科学
混淆矩阵
太赫兹辐射
极限学习机
物理
化学
人工神经网络
光学
生物化学
基因
摘要
This article uses terahertz (THz) spectroscopy combined with Ramp-SVM to distinguish different sources of traditional Chinese medicine. The spectra of four different herbs (Curcuma Wenyujin, Curcuma phaeocaulis,Curcuma longa,Curcuma kwangsiensis) were obtained in the range of 0.5-2THz. Apply principal component analysis (PCA) to reduce the dimensionality of the original spectral information. Three classification algorithms, Support Vector Machine (SVM), Extreme Learning Machine (ELM) and Random Forest (RF) are used to distinguish herbs. Compared with the above models, Ramp-SVM has good robustness and high accuracy. The confusion matrix is combined with the classification accuracy to evaluate the performance of the three classification algorithms. The Ramp-SVM method achieves 95% prediction accuracy. The experimental results show that the combination of terahertz spectroscopy and chemometric algorithm is an effective method to quickly identify Same-based Chinese Medicine.
科研通智能强力驱动
Strongly Powered by AbleSci AI