Identification of medically and forensically relevant flies using a decision treelearning method

@#Blow flies, flesh flies, and house flies can provide excellent evidence for forensic entomologists and are also essential to the fields of public health, medicine, and animal health. In all questions, the correct identification of fly species is an important initial step. The usual methods based on morphology or even molecular approaches can reach their limits here, especially when dealing with larger numbers of specimens. Since machine learning already plays a major role in many areas of daily life, such as education, business, industry, science, and medicine, applications for the classification of insects have been reported. Here, we applied the decision tree method with wing morphometric data to construct a model for discriminating flies of three families [Calliphoridae, Sarcophagidae, Muscidae] and seven species [Chrysomya megacephala (Fabricius), Chrysomya rufifacies (Macquart), Chrysomya (Ceylonomyia) nigripes Aubertin, Lucilia cuprina (Wiedemann), Hemipyrellia ligurriens (Wiedemann), Musca domestica Linneaus, and Parasarcophaga (Liosarcophaga) dux Thomson]. One hundred percent overall accuracy was obtained at a family level, followed by 83.33% at a species level. The results of this study suggest that non-experts might utilize this identification tool. However, more species and also samples per specimens should be studied to create a model that can be applied to the different fly species in Thailand.

Study on the material basis of cold and hot properties of traditional Chinese medicines in Lamiaceae based on pattern recognition / 药学学报

To study the material basis of cold and hot properties of traditional Chinese medicines (TCMs) in Lamiaceae and to establish a cold and hot properties identification model, a database of material components of TCMs in Lamiaceae was established. A three-level classification system of material components was used to obtain the material basis of cold and hot properties of the Lamiaceae family by using data mining methods such as frequency analysis, association rule analysis, logistic regression, and feature selection. Several identification models were established to recognize the cold and hot properties. The chi-square test results showed that the material composition ratios of cold and hot properties were significantly different at the first-level, second-level, and third-level classification (P < 0.05), and the differences varied as the levels of substance classification changed. The average coefficients of variation were 42.30%, 79.07%, and 91.51% at the first-level, second-level, and third-level classification levels, respectively. In other words, in terms of the percentage differences in material composition ratio, the first-level was smaller than the second-level, and the second-level was smaller than the third-level. The results of the association rule analysis showed that under the third-level classification, there were many effective association rules, and 27 core groups and 34 specific groups of chemical components were obtained based on these rules. 15 decisive groups were obtained from the feature selection results. Multinomial logistic regression analysis was used to successfully establish a cold and hot properties identification model with an overall accuracy of 89%. The material basis of cold and hot properties of TCMs in Lamiaceae is different and intersect with each other. Twenty-seven groups of chemical components, such as bicyclic diterpenes, are the core groups of cold and hot properties, of which 15 groups are the decisive groups. The cold and hot properties are often characterized by the interaction of multiple classes of substances, and a single class of substances often cannot be used to characterize the properties. The organic combination of multiple classes of substances is the material basis of cold and hot properties.

Origin identification of Polygonatum cyrtonema based on hyperspectral data / 中国中药杂志

In this study, visual-near infrared(VNIR), short-wave infrared(SWIR), and VNIR + SWIR fusion hyperspectral data of Polygonatum cyrtonema from different geographical origins were collected and preprocessed by first derivative(FD), second derivative(SD), Savitzky-Golay smoothing(S-G), standard normalized variate(SNV), multiplicative scatter correction(MSC), FD+S-G, and SD+S-G. Three algorithms, namely random forest(RF), linear support vector classification(LinearSVC), and partial least squares discriminant analysis(PLS-DA), were used to establish the identification models of P. cyrtonema origin from three spatial scales, i.e., province, county, and township, respectively. Successive projection algorithm(SPA) and competitive adaptive reweighted sampling(CARS) were used to screen the characteristic bands, and the P. cyrtonema origin identification models were established according to the selected characteristic bands. The results showed that(1)after FD preprocessing of VNIR+SWIR fusion hyperspectral data, the accuracy of recognition models established using LinearSVC was the highest, reaching 99.97% and 99.82% in the province origin identification model, 100.00% and 99.46% in the county origin identification model, and 99.62% and 98.39% in the township origin identification model. The accuracy of province, county, and township origin identification models reached more than 98.00%.(2)Among the 26 characteristic bands selected by CARS, after FD pretreatment, the accuracy of origin identification models of different spatial scales was the highest using LinearSVC, reaching 98.59% and 97.05% in the province origin identification model, 97.79% and 94.75% in the county origin identification model, and 90.13% and 87.95% in the township origin identification model. The accuracy of identification models of different spatial scales established by 26 characteristic bands reached more than 87.00%. The results show that hyperspectral imaging technology can realize accurate identification of P. cyrtonema origin from different spatial scales.

Identification of Kidney-Yang Deficiency Syndrome in Osteoporosis Patients Based on Rule Ensemble Method of Bagging Combining LASSO Regression / 中国实验方剂学杂志

ObjectiveTo investigate the identification of kidney Yang deficiency syndrome of patients with osteoporosis（OP）， and to form the clinical syndrome identification rules of traditional Chinese medicine（TCM）. MethodBasic information， etiology， clinical symptoms and other characteristics of 982 OP patients were included， and statistical tests were used to screen the variables associated with kidney Yang deficiency syndrome. Taking the decision tree as the base model， bootstrap aggregation algorithm（Bagging algorithm） was utilized to establish the classification model of kidney Yang deficiency syndrome in OP， generating numerous rules and removing redundancy. Combining least absolute shrinkage and selection operator（LASSO） regression to screen key rules and integrate them to construct an identification model， achieving the identification of kidney Yang deficiency syndrome in OP patients. ResultEighteen key identification rules were screened out， and of these， where 11 rules with regression coefficients>0 correlated positively with the kidney Yang deficiency syndrome， the rule with the highest coefficient was chilliness（present）&feverish sensation over the palm and sole（absent）. The other 7 rules with regression coefficients<0 correlated negatively with the syndrome， the rule with the lowest coefficient was reddish tongue（present）&diarrhea（absent）&deficiency of endowment（absent）. According to the regression coefficients of each key rule， variables with importance>0.2 were ranked as chilliness， reddish tongue， feverish sensation over the palm and sole， cold limbs， clear urine， diarrhea， deficiency of endowment， prolonged illness. The results of the partial dependence analysis of the identification model showed that compared to OP patients without chilliness， those with chilliness（present） had a 0.266 8 higher probability of being identified as having kidney Yang deficiency syndrome， indicating that this variable had the highest impact on identification of the syndrome. Similarly， compared to OP patients without reddish tongue， those with reddish tongue had a 0.141 9 lower probability of being identified as having kidney Yang deficiency syndrome， indicating that this variable had the highest impact on identifying non-kidney Yang deficiency syndrome. The accuracy， sensitivity， specificity and area under receiver operating characteristic curve（AUC） of the established kidney Yang deficiency syndrome identification model in the test set were 0.865 9， 0.853 7， 0.872 0 and 0.931 5， respectively. ConclusionA precise identification model of OP kidney Yang deficiency syndrome is conducted basing on the rule ensemble method of Bagging combining LASSO regression， and the screened key rules can explain the identification process of kidney Yang deficiency syndrome. In this research， according to the regression coefficients of rules， the importance and partial dependence of variables， combined with the thinking of TCM， the influence of patient characteristics on the identification of syndromes is described， so as to reveal the primary and secondary syndromes of identification and assist the clinical identification of kidney Yang deficiency syndrome.

Analysis on Feasibility of Electronic Nose Technology for Rapid Identification of Bletillae Rhizoma and Its Approximate Decoction Pieces / 中国实验方剂学杂志

ObjectiveTo investigate the feasibility of applying electronic nose technology to rapidly identify Bletillae Rhizoma and its approximate decoction pieces. MethodA total of 134 batches of Bletillae Rhizoma and its approximate decoction pieces， including 45 batches of Bletillae Rhizoma， 30 batches of Gastrodiae Rhizoma， 30 batches of Polygonati Odorati Rhizoma and 29 batches of Bletillae Ochraceae Rhizoma， were collected as test samples. The olfactory sensory data of the samples were collected by PEN3 electronic nose as the independent variable（X）. Based on the identification results of the 2020 edition of Chinese Pharmacopoeia and local standards， as well as the high performance liquid chromatography（HPLC） fingerprint and original purchase information of 134 batches of the decoction pieces， the benchmark data Y of the identification model were obtained， and four chemometric methods of principal component analysis-discriminant analysis（PCA-DA）， partial least squares-discriminant analysis（PLS-DA）， least square-support vector machine（LS-SVM） and K-nearest neighbor（KNN） were used to establish the binary identification model for 45 batches of Bletillae Rhizoma and 89 batches of non-Bletillae Rhizoma and the quadratic identification model of the four kinds of decoction pieces， that is， Y=F（X）. ResultAfter leave-one-out cross validation， the positive discrimination rates of the above four models were 97.01%， 97.01%， 98.51% and 97.01% in the binary identification， and 97.76%， 89.55%， 98.51% and 97.01% in the quadratic identification， respectively. The highest positive discrimination rate could reach 98.51% for the binary and quadratic identification models， and LS-SVM algorithm is both the optimal one， the most suitable kernel functions were chosen as radial basis function and linear kernel function， respectively. The optimal models discriminated well with no unclassified samples. ConclusionElectronic nose technology can accurately and rapidly identify Bletillae Rhizoma and its approximate decoction pieces， which can provide new ideas and methods for rapid quality evaluation of other decoction pieces.

Nucleosides-based identification model for Fritillariae Cirrhosae Bulbus / 中国中药杂志

A high performance liquid chromatography( HPLC) method was established for the fast,and precise determination of ten nucleosides in Fritillariae Cirrhosae Bulbus and its counterfeits. Then multivariate statistical analyses,such as clustering analysis,principal component analysis( PCA),and Fisher' s linear discriminant analysis( LDA),were conducted to establish a discriminant function model for an integrated analysis. The results indicated that data acquisition time of a single sample was shortened within 16 min by the HPLC method. In the range of 5-1 000 mg·kg~(-1),the mass concentrations of all nucleosides exhibited good linear relationships with the corresponding peak areas( R2> 0. 999). The spiked recoveries were in the range of 93. 83%-108. 9% with RSDs of0. 12%-1. 3%( n = 5). The limit of quantitation( LOQ) was 0. 98-4. 13 mg·kg~(-1). As revealed by the clustering analysis,Fritillariae Cirrhosae Bulbus and the counterfeits could be discriminated into two clusters based on the content of nucleosides. Fisher's LDA could achieve this discrimination,while PCA dimension reduction failed. The accuracy of the discriminant function model established on the screened characteristic indicators reached 97. 5%. The present study proposed a new identification method of Fritillariae Cirrhosae Bulbus with one-dimensional indicators,which is simple,accurate,and reliable. It can provide a scientific basis for further optimizing the identification techniques for Fritillariae Cirrhosae Bulbus and inspiration for quality control strategy development of Chinese medicinal materials.

Identification of Pseudostellaria Radix from Different Producing Regions and Habitat Processing Methods Based on Electronic Nose Technology / 中国药学杂志

OBJECTIVE: Pseudostellaria Radix, due to its sketchy description and individual difference during the odor evaluation, fails to come to researchers' attention. To analyze the odor of the Pseudostellaria Radix samples from different habitat processing methods and areas, and apply electronic nose technology to creating a new method for the determination of Pseudostellaria Radix. METHODS: According to the response values obtained by using electronic nose technology, two multivariate statistical methods to the data to distinguish the samples collected from different areas and habitat processing methods were applied. From the aspect of response values, the sunned Pseudostellaria Radix after boiling get lower values than the sunned ones, while the values of the samples from different producing origins vary very slightly. RESULTS: The results of the multivariate statistical methods show that principal component analysis (PCA) can differ the sunned samples from the sunned ones after boiling. With regard to the sunned ones after boiling, there is no significant difference among the three boiling time groups from 30 s to 120 s. While the two discrimination models constructed during the discriminant factor analysis (DFA) have respectively favorable identification ability in habitat processing methods and producing areas. CONCLUSION: The electronic nose technology can be used to express the odor of Pseudostellaria Radix, and in combination with multivariate statistical methods, it can differentiate Pseudostellaria Radix from different areas and habitat processing methods.

A rapid identification of authenticity and specifications of Chinese medicine Fritillariae Cirrhosae Bulbus based on E-eye technology / 中国中药杂志

The quality of traditional Chinese medicine tablets is correlated with clinical efficacy and drug safety, and plays a great role in promoting the development of traditional Chinese medicine. However, the existing traditional artificial identification and modern instrument detection in terms of accuracy and timeliness have both advantages and disadvantages. Therefore, how to quickly and accurately identify the quality of traditional Chinese medicine tablets has become a high-profile issue. The purpose of this paper is to explore the feasibility of the application of electronic eye technology in the study of rapid identification of traditional Chinese medicine quality. A total of 80 batches of samples were collected and tested by Fritillariae Cirrhosae Bulbus for traditional empirical identification(M_1) and modern pharmacopeia(M_2). The optical data was collected from electronic eyes, and the chemical metrology was used to establish suitable discrimination models(M_3). Four authenticity and commodity specification models, namely identification analysis(DA), minimum bidirectional support vector machine(LS-SVM), partial minimum two-multiplier analysis(PLS-DA), main component analysis identification analysis(PCA-DA), were established, respectively. The accuracies of the authenticity identification models were 82.5%, 90.0%, 96.2% and 93.8%, while the accuracies of the commodity specification identification models were 89.3%, 96.0%, 90.7% and 97.3%, respectively. The models were well judged, the authenticity identification was based on the final identification model of PLS-DA, and the commodity specification was based on the final identification model of PCA-DA. There was no significant difference between its accuracy and M_1, and the time of determination was much shorter than M_2(P<0.01). Therefore, electronic-eye technology could be used for the rapid identification of the quality of Fritillariae Cirrhosae Bulbus.

Challenge and solution to medical damage idntification / 中国法医学杂志

By the end of 2017, the Supreme People's Court issue a judical interpretation called Tort law of China·Medical damage liability. It formulates some new rules about identification. It stipulates qualification of new appraiser; clears requirement of medical fault judgment; clears the requirement of causal relationship; defines procedure of medical damage identification and so on. However, there exist the dual identification model. Under the new rules, medical damage identification will face new challenges, especially some stipulates about qualification of appraisers, and expert assistants' views become the basis of the verdict. Those will effect medical examiners' working directly in China. So, I put forward following suggestions: ①Medical identification must be scientific, public welfare, normative.②It is trend for medical damage identification back to peer review. ③A unified library of clinical expert appraisers should be establised. ④We should reasearch the theorys, principles and methods of medical damege identification.

A consideration on screening of allelochemicals by using "knock-out/in" of targeting ingredients based on identification model of medicinal effect / 中国中药杂志

This paper clarified in detail the definition, characteristics of allelopathy and its association with consecutive monoculture problem.Most of studies have indicated that it is critical to parse the formation mechanisms of consecutive monoculture problem that identification of allelochemicals and verification of its function. Here, we proposed a new approach to separate and identify the allelochemical group precisely and effectively, in which the "knock-out/in" methods of targeting ingredients in the model of medicinal effect identification and quality control were applied. This method will contribute to deep understanding plant allelopathy, and provide theoretical basis and technical support for alleviating consecutive monoculture problems simultaneously.

Application of Multivariate Statistical Analysis in Amino Acids Compositions and Cold-Heat Nature of Traditional Chinese Medicine / 世界科学技术-中医药现代化

This study was aimed to find the correlation between amino acid compositions and Cold-Heat Nature of traditional Chinese medicine (TCM) in order to provide basis for the research of TCM natural theory. A total of 17 kinds of amino acid were determined by application before column derivatization reaction and high-perfor-mance liquid chromatography (HPLC) and the tryptophan was determined by UV method. The data were collected for analysis by Fisher method in PAST software. The best statistical identification model was determined. And the Cold-Hot medicine property markers (CHMP-markers) were determined. The results showed that the discriminant function established by Fisher method based on 18 kinds of amino acid contents has good identification ability, and the accuracy of the Fisher discriminant analysis is 82%. Support vector machine (SVM) is the best statistical identification model . The cold and heat markers were analyzed by SVM . The cold nature material bases in-clude Glu, Gly, Arg, Thr, Ala, Tyr, Val, Ile and lys. And the heat nature material bases contain Asp, Ser, His, Pro, Met, Cys, Leu, Phe and Trp. It was concluded that there is relationship between 18 kinds of amino acid contents and the Cold-Heat nature of TCM .