Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 9 de 9
Article in Chinese | WPRIM | ID: wpr-879069


Spatial distribution uniformity is the critical quality attribute(CQA) of Ginkgo Leaves Tablets, a variety of big brand traditional Chinese medicine. The evaluation of the spatial distribution uniformity of active pharmaceutical ingredients(APIs) in Ginkgo Leaves Tablets is important in ensuring their stable and controllable quality. In this study, hyperspectral imaging technology was used to construct the spatial distribution map of API concentration based on three prediction models, further to realize the visualization research on the spatial distribution uniformity of Ginkgo Leaves Tablets. The region of interest(ROI) was selected from each Ginkgo Leaves Tablet, with length and width of 50 pixels, and a total of 2 500 pixels. Each pixel had 288 spectral channels, and the number of content prediction data could reach 1×10~5 for a single sample. The results of the three models showed that the Partial Least Squares(PLS) model had the highest prediction accuracy, with calibration set determination coefficient R_(pre)~2 of 0.987, prediction set determination coefficient R_(pre)~2 of 0.942, root mean square error of calibration(RMSEC) of 0.160%, and root mean square error of prediction(RMSEP) of 0.588%. The classical least-squares(CLS) model had a greater prediction error, with the RMSEP of 0.867%. Multivariate Curve Resolution-Alternating Least Square(MCR-ALS) model showed the worst predictive ability among the three models, and it couldn't realize content prediction. Based on the prediction results of PLS and CLS models, the spatial distribution map of APIs concentration was obtained through three-dimensional data reconstruction. Furthermore, histogram method was used to evaluate the spatial distribution uniformity of API. The data showed that the spatial distribution of APIs in Ginkgo Leaves Tablets was relatively uniform. The study explored the feasibility of visualization of spatial distribution of Ginkgo Leaves Tablets based on three models. The results showed that PLS model had the highest prediction accuracy, and MCR-ALS model had the lowest prediction accuracy. The research results could provide a new strategy for the visualization method of quality control of Ginkgo Leaves Tablets.

Calibration , Ginkgo biloba , Least-Squares Analysis , Medicine, Chinese Traditional , Plant Leaves , Quality Control , Spectroscopy, Near-Infrared , Tablets
Article in Chinese | WPRIM | ID: wpr-879065


The spatial distribution uniformity of valuable medicines is the critical quality attribute in the process control of Tongren Niuhuang Qingxin Pills. With the real world sample of the mixed end-point powder of Tongren Niuhuang Qingxin Pills as the research object, hyperspectral imaging technology was used to collect a total of 32 400 data points with a size of 180 pix×180 pix. Spectral angle matching(SAM), classical least squares and mixed tuned matched filtering(MTMF) were used to identify the spatial distribution of rare medicines. MTMF model showed higher identification accuracy, therefore the spatial distribution of the blended intermediates was identified based on the MTMF model. The histogram method was also used to evaluate the spatial distribution uniformity of rare medicines. The results showed that the standard deviation was 4.78, 6.5, 3.48, 1.96, and 3.00 respectively for artificial bezoar, artificial musk, Borneol, Antelope horn and Buffalo horn; the variance was 22.8, 42.3, 12.1, 3.82, and 9.00, and the skewness was 1.26, 1.71, 0.06,-0.86, and 1.04, respectively. The final results showed that the most even blending was achieved in concentrated powder of Borneol, Antelope horn and Buffalo horn, followed by artificial bezoar, and last artificial musk. A visualization method was established for quality attributes of distribution uniformity in blending process of Tongren Niuhuang Qingxin Pills. It could provide evidences of quality control methods in the mixing process of big brand traditional Chinese medicine.

Drugs, Chinese Herbal , Medicine, Chinese Traditional , Powders , Quality Control
Article in Chinese | WPRIM | ID: wpr-878957


To identify Glycyrrhizae Radix et Rhizoma from different geographical origins, spectrum and image features were extracted from visible and near-infrared(VNIR, 435-1 042 nm) and short-wave infrared(SWIR, 898-1 751 nm) ranges based on hyperspectral imaging technology. The spectral features of Glycyrrhizae Radix et Rhizoma samples were extracted from hyperspectral data and denoised by a variety of pre-processing methods. The classification models were established by using Partial Least Squares Discriminate Analysis(PLS-DA), Support Vector Classification(SVC) and Random Forest(RF). Meanwhile, Gray-Level Co-occurrence matrix(GLCM) was employed to extract textural variables. The spectrum and image data were implemented from three dimensions, including VNIR and SWIR fusion, spectrum and image fusion, and comprehensive data fusion. The results indicated that the spectrum in SWIR range performed better classification accuracy than VNIR range. Compared with other four pre-processing methods, the second derivative method based on Savitzky-Golay(SG) smoothing exhibited the best performance, and the classification accuracy of PLS-DA and SVC models were 93.40% and 94.11%, separately. In addition, the PLS-DA model was superior to SVC and RF models in terms of classification accuracy and model generalization capability, which were evaluated by confusion matrix and receiver operating characteristic curve(ROC). Comprehensive data fusion on SPA bands achieved a classification accuracy of 94.82% with only 28 bands. As a result, this approach not only greatly improved the classification efficiency but also maintained its accuracy. The hyperspectral imaging system, a non-invasively, intuitively and quickly identify technology, could effectively distinguish Glycyrrhizae Radix et Rhizoma samples from different origins.

Drugs, Chinese Herbal , Hyperspectral Imaging , Technology
Article in Chinese | WPRIM | ID: wpr-878778


In the 21 st century, the rise of artificial intelligence(AI) marks the arrival of the intelligence era or the era of Industry 4.0. In addition to the rapid development of computer and electronic information science, machine learning, as the core intelligence of AI, provides a new methodology for the modernization of traditional Chinese medicine. The algorithms of machine learning include support vector machine(SVM), extreme learning machine(ELM), convolutional neural network(CNN), and recurrent neural network(RNN). The combination of machine learning algorithms and hyperspectral imaging analysis could be used for the identification of fake and inferior herbs, the origin of herbs and the content determination of bioactive ingredients in herbs, which has largely solved the difficulty in strictly controlling the quality of traditional Chinese medicine. The integration of high spectral imaging(HSI) and deep lear-ning will make the predicted results more reliable and suitable for analysis of great amounts of samples. This paper summarizes the application of hyperspectral imaging technology(HSI) and machine learning algorithms in the field of traditional Chinese medicine in recent years, focuses on the principles of hyperspectral imaging technology, preprocessing methods and deep learning algorithms, and gives the prospects of evolution of hyperspectral imaging technology in the field.

Algorithms , Artificial Intelligence , Deep Learning , Hyperspectral Imaging , Medicine, Chinese Traditional , Neural Networks, Computer
Ciênc. rural (Online) ; 50(3): e20190731, 2020. tab, graf
Article in English | LILACS-Express | LILACS | ID: biblio-1089569


ABSTRACT: Chlorophyll is a major factor affecting photosynthesis; and consequently, crop growth and yield. In this study, we devised a chlorophyll-content detection model for millet leaves in different stages of growth based on hyperspectral data. The hyperspectral images of millet leaves were obtained under a wavelength range of 380-1000 nm using a hyperspectral imager. Threshold segmentation was performed with near-infrared (NIR) reflectance and normalized difference vegetation index (NDVI) to intelligently acquire the regions of interest (ROI). Furthermore, raw spectral data were preprocessed using multivariate scatter correction (MSC). A correlation coefficient-successive projections algorithm (CC-SPA) was used to extract the characteristic wavelengths, and the characteristic parameters were extracted based on the spectral and image information. A partial least squares regression (PLSR) prediction model was established based on the single characteristic parameter and multi-characteristic parameter fusion. The determination coefficient (Rv 2) and the root-mean-square error (RMSEv) of the validation set for the multi-characteristic parameter fusion model were reported to be 0.813 and 1.766, respectively, which are higher than those obtained by the single characteristic parameter model. Based on the multi-characteristic parameter fusion, an attention-convolutional neural network (attention-CNN) (Rv 2 = 0.839, RMSEv = 1.451, RPD = 2.355) was established, which is more effective than the PLSR (Rv 2 = 0.813, RMSEv = 1.766, RPD = 2.167) and least squares support vector machine (LS-SVM) models (Rv 2 = 0.806, RMSEv = 1.576, RPD = 2.061). These results indicated that the combination of hyperspectral imaging and attention-CNN is beneficial to the application of nutrient element monitoring of crops.

RESUMO: A clorofila é um fator importante que afeta a fotossíntese e, consequentemente, o crescimento e o rendimento das culturas. Neste estudo, um modelo de detecção de conteúdo de clorofila é construído para folhas de milheto em diferentes estágios de crescimento, com base em dados hiperespectrais. As imagens hiperespectrais dos diferentes estágios de crescimento das folhas de milheto foram obtidas para 380-1000 nm, utilizando um gerador de imagens hiperespectrais. Uma segmentação de limiar foi realizada com refletância no infravermelho próximo (NIR) e índice de vegetação com diferença normalizada (NDVI) para adquirir de forma inteligente as regiões de interesse (ROI). Além disso, os dados espectrais brutos foram pré-processados usando o método de correção de dispersão multivariada (MSC). Um algoritmo de projeção de coeficiente de correlação sucessivo (CC-SPA) foi utilizado para extrair os comprimentos de onda característicos, e os parâmetros característicos foram extraídos com base nas informações espectrais e de imagem. O modelo de previsão de regressão parcial dos mínimos quadrados (PLSR) foi estabelecido com base nos parâmetros de característica única e na fusão de parâmetros de característica múltipla. O coeficiente de determinação (Rv2) e o erro quadrático médio da raiz (RMSEv) do conjunto de validação para o modelo de fusão de parâmetros com várias características foram obtidos como 0,813 e 1,766, sendo melhores do que os do modelo de parâmetro de característica única. Com base na fusão de parâmetros com várias características, foi estabelecida uma rede neural atenção-convolucional (atenção-CNN) (Rv2 = 0,839, RMSEv = 1,451, RPD = 2,355) mais eficaz que o PLSR (Rv2 = 0,813, RMSEv = 1,766, RPD = 2,167) e mínimos quadrados que suportam modelos de máquina de vetores (LS-SVM) (Rv2 = 0,806, RMSEv = 1,576, RPD = 2,061). Estes resultados indicam que o modelo atenção-CNN atinge uma previsão efetiva do teor de clorofila nas folhas de milheto usando os dados hiperespectrais. Além disso, esta pesquisa demonstra que a combinação de imagens hiperespectrais e a atenção-CNN se mostra benéfica para a aplicação do monitoramento dos elementos nutricionais das culturas.

Article in Chinese | WPRIM | ID: wpr-498054


Rapid detection and classification of bacteria colonies ( Escherichia coli, Listeria monocytogens and Staphylococcus aureus) were investigated by using hyperspectral imaging. The hyperspectral reflectance images (390-1040 nm ) of bacterial colonies on agar plates were collected. Bacterial spectra were extracted automatically based on the masks produced by segmenting a band difference image using the OTSU method. Full wavelength and simplified PLS-DA models were established for classification of bacterial colonies. For the full wavelength model, the overall correct classification rate ( OCCR) and confident OCCR for the prediction set were 100% and 95. 9%, respectively. Besides, competitive adaptive reweighted sampling ( CARS), genetic algorithm ( GA ) and least angle regression-least absolute shrinkage and selection operator ( LARS-Lasso) were used to select feature wavelengths for the development of simplified models. Among them, the CARS-model outperformed the other two in terms of precision, stability and classification accuracy with OCCR and confident OCCR of 100% and 98. 0% for the prediction set, respectively. It was demonstrated that hyperspectral imaging was an effective technology for nondestructive detection of bacterial colonies with high accuracy and high speed. The allocated feature wavelengths by CARS could lay theoretical basis for developing low cost multispectral imaging systems for bacterial colony detection.

Article in English | WPRIM | ID: wpr-812139


It has been reported that hyperspectral data could be employed to qualitatively elucidate the spatial composition of tablets of Chinese medicinal plants. To gain more insights into this technology, a quantitative profile provided by near infrared (NIR) spectromicroscopy was further studied by determining the glycyrrhizic acid content in licorice, Glycyrrhiza uralensis. Thirty-nine samples from twenty-four different origins were analyzed using NIR spectromicroscopy. Partial least squares, interval partial least square (iPLS), and least squares support vector regression (LS-SVR) methods were used to develop linear and non-linear calibration models, with optimal calibration parameters (number of interval numbers, kernel parameter, etc.) being explored. The root mean square error of prediction (RMSEP) and the coefficient of determination (R(2)) of the iPLS model were 0.717 7% and 0.936 1 in the prediction set, respectively. The RMSEP and R(2) of LS-SVR model were 0.515 5% and 0.951 4 in the prediction set, respectively. These results demonstrated that the glycyrrhizic acid content in licorice could barely be analyzed by NIR spectromicroscopy, suggesting that good quality quantitative data are difficult to obtain from microscopic NIR spectra for complicated Chinese medicinal plant materials.

Calibration , Drugs, Chinese Herbal , Chemistry , Glycyrrhiza , Chemistry , Glycyrrhizic Acid , Least-Squares Analysis , Microscopy , Methods , Spectroscopy, Near-Infrared , Methods
Article in Chinese | WPRIM | ID: wpr-471239


The growing interest of the pharmaceutical industry in Near Infrared-Chemical Imaging (NIR-CI) is a result of its high usefulness for quality control analyses of drugs throughout their production process (particularly of its non-destructive nature and expeditious data acquisition).In this work,the concentration and distribution of the major and minor components of pharmaceutical tablets are determined and the spatial distribution from the internal and external sides has been obtained.In addition,the same NIR-CI allowed the coating thickness and its surface distribution to be quantified.Images were processed to extract the target data and calibration models constructed using the Partial Least Squares (PLS) algorithms.The concentrations of Active Pharmaceutical Ingredient (API) and excipients obtained for uncoated cores were essentially identical to the nominal values of the pharmaceutical formulation.But the predictive ability of the calibration models applied to the coated tablets decreased as the coating thickness increased.

Rev. colomb. cienc. pecu ; 23(1): 9-16, mar. 2010. graf
Article in English | LILACS | ID: lil-559529


This paper presents an optimal emission filter of the fluorescence imaging system to detect skintumors on poultry carcasses. The secure production of disease-free meat is crucial in the mass productionenvironment. The fluorescence spectra have been gaining the practical use in many areas because thefluorescence response is very sensitive in detecting trace elements. The spectral features of the specimenare embedded across broad spectral bands and have been analyzed in various methods. We apply thelinear discriminant analysis to determine the emission filter of fluorescence imaging system. It providesthe optimal attenuation of emission wavelengths in terms of discriminant power. The attenuation valuesprioritize wavelengths to select significant spectral bands. With the optimal filter, skin tumor parts ofchicken carcasses are enhanced saliently in resultant fluorescence images.

La producción de carne libre de enfermedades es crucial en producción pecuaria intensiva. Losespectros de fluorescencia se han estado usando en forma práctica en muchas áreas, ya que la respuestade fluorescencia es muy sensible para detectar elementos traza. Este artículo presenta un óptimo filtrode emisión para el sistema de imágenes de fluorescencia utilizado para detectar tumores cutáneos encanales de pollo. Las características espectrales de la muestra --insertas en bandas espectrales amplias- sehan analizado por varias metodologías. En este artículo aplicamos el análisis lineal discriminante paradeterminar el filtro de emisión del sistema de imágenes por fluorescencia, mediante el cual se obtiene laatenuación optima de las ondas de emisión en términos de poder discriminante. Los valores de atenuaciónpriorizan las longitudes de onda para seleccionar las bandas espectrales más significativas. Gracias a lautilización de este filtro optimizado, los tumores cutáneos existentes en la canal de pollo son magnificados,de modo que se alcanzan a diferenciar perfectamente en las imágenes de fluorescencia resultantes.

A produção de carne livre de doenças é crucial em produção pecuária intensiva. Os espectros defluorescência temse estado utilizando em forma prática em muitas áreas, já que a resposta da fluorescênciaé muito sensível para detectar elementos traça. Este artículo apresenta um óptimo filtro de emissão parao sistema de imagens de fluorescência utilizado para detectar tumores cutâneos em carcaças de frangos.As características espectrais da amostra, insertas em bandas espectrais amplas são utilizadas por variasmetodologias. Neste artículo aplicamos a análises linear discriminante para determinar o filtro de emissãodo sistema de imagens por fluorescência, mediante o qual obtém-se a atenuação óptima das ondas deemissão em termos de poder discriminante. Os valores de atenuação dão prioridade às longitudes deonda para seleccionar as bandas espectrais mais significativas. Graças à utilização do filtro optimizado,os tumores cutâneos existentes na carcaça de frango são magnificados, de fato que são diferenciadosperfeitamente nas imagens de fluorescência resultantes.

Animals , Birds/injuries , Neoplasms/veterinary , Spectrometry, Fluorescence