[Identification of Curcuma herbs using XGBoost algorithm in electronic nose odor fingerprint].

This article aims to identify four commonly applied herbs from Curcuma genus of Zingiberaceae family,namely Curcumae Radix( Yujin),Curcumae Rhizoma( Ezhu),Curcumae Longae Rhizoma( Jianghuang) and Wenyujin Rhizoma Concisum( Pianjianghuang). The odor fingerprints of those four herbal medicines were collected by electronic nose,respectively. Meanwhile,XGBoost algorithm was introduced to data analysis and discriminant model establishment,with four indexes for performance evaluation,including accuracy,precision,recall,and F-measure. The discriminant model was established by XGBoost with positive rate of returning to 166 samples in the training set and 69 samples in the test set were 99. 39% and 95. 65%,respectively. The top four of the contribution to the discriminant model were LY2/g CT,P40/1,LY2/Gh and LY2/LG,the least contributing sensor was T70/2. Compared with support vector machine,random forest and artificial neural network,XGBoost algorithms shows better identification capacity with higher recognition efficiency. The accuracy,precision,recall and F-measure of the XGBoost discriminant model forecast set were 95. 65%,95. 25%,93. 07%,93. 75%,respectively. The superiority of XGBoost in the identification of Curcuma herbs was verified. Obviously,this new method could not only be suitable for digitization and objectification of traditional Chinese medicine( TCM) odor indicators,but also achieve the identification of different TCM based on their odor fingerprint in electronic nose system. The introduction of XGBoost algorithm and more excellent algorithms provide more ideas for the application of electronic nose in data mining for TCM studies.

[Accurate identification of Psammosilene tunicoides and its confused species by systematic identification method].

OBJECTIVE: To develop an effective identification method for accurately discriminating Psammosilene tunicoides and its confused species by the combined method of microscopic identification and molecular identification, so-called systematic identification of Chinese materia medica (SICMM). METHOD: P. tunicoides and its confused species were accurately discriminated by SICMM method, which was established by comprehensively use of microscopic identification and DNA identification method. The DNA identification included the following analysis: the BLAST alignment, specific bases and N-J phylogenetic tree analysis. RESULT: The cluster crystals were not observed in P. tunicoides, but great deals of them were found in Silene viscidula. Further more, big differences of ITS sequence were observed and analyzed between P. tunicoides and its confused specie of S. viscidula. CONCLUSION: The system method is a scientific and accurate method for the identification of P. tunicoides and its counterfeit species.

Rapid discrimination of Chinese red ginseng and Korean ginseng using an electronic nose coupled with chemometrics.

Red ginseng is a precious and widely used traditional Chinese medicine. At present, Chinese red ginseng and Korean ginseng are both commonly found on the market. To rapidly and nondestructively discriminate between Chinese red ginseng and Korean ginseng, an electronic nose coupled with chemometrics was developed. Different red ginseng samples, including Chinese red ginseng (n=30) and Korean ginseng (South Korean red ginseng and North Korean red ginseng n=26), were collected. The metal oxide sensors on an electronic nose were used to measure the red ginseng samples. Multivariate statistical analyses, including principal component analysis (PCA), discriminant factorial analysis (DFA) and soft independent modeling of class analogy (SIMCA), were employed. All of the samples were analyzed by PCA. Most of the samples were used to set up DFA and SIMCA models, and then the remaining samples (Nos. 9, 10, 17, 18, 29, 30, 34, 43, 44, 50, and 51) were projected onto the DFA and SIMCA models in the form of black dots to validate the models. The results indicated that Chinese red ginseng and Korean ginseng were successfully discriminated using the electronic nose coupled with PCA, DFA and SIMCA. The checking scores of the DFA and SIMCA models were 100. The samples projected onto the DFA and SIMCA models were all correctly discriminated. The DFA and SIMCA models were robust. Electronic nose technology is a rapid, accurate, sensitive and nondestructive method to discriminate between Chinese red ginseng and Korean ginseng.