Classification of Chinese Herbal Medicine by Laser-Induced Breakdown Spectroscopy with Principal Component Analysis and Artificial Neural Network

Investigating the mechanistic impact of pork soft tissue preparation techniques on the classification precision of laser-induced breakdown spectroscopy

The investigation of the mechanism underlying the impact of biological soft tissue sample preparation methods on laser-induced breakdown spectroscopy (LIBS) signals can enhance the stability of LIBS signals. Our study focused on four specific preparation methods applied to pork samples: rapid freezing, fresh slicing, drying, and pressing. The influence of various preparation techniques on the signal-to-noise ratio and fluctuation of Ca, Na, Mg, and CN bands within the sample spectra was assessed. The signal-to-noise ratios for samples that were dried and pressed notably improved. And the pressing method effectively mitigated the uneven distribution of pork tissue components, displaying superior spectral line stability. To explain this phenomenon, we used the Saha-Boltzmann diagram to estimate the plasma temperature. Remarkably, there was a significant reduction in plasma temperature fluctuations across four pressed samples, with a standard deviation of 108.53. Furthermore, we undertook a classification analysis employing support vector machine models to corroborate the generalization efficacy of the sample preparation technique. Dried and pressed samples demonstrated notably higher classification accuracy, precision, and recall (all >93%) compared to frozen and fresh samples, where these metrics remained below 86%. The performance of the SVM model was ultimately evaluated using Receiver Operating Characteristic (ROC) curves and the Area Under the Curve (AUC). The AUC for the frozen, fresh, dried, and pressed samples was 0.854, 0.907, 0.989, and 0.996, respectively. The findings revealed that the pressing method exhibited superior performance, followed by drying, fresh slicing, and freezing, in descending order of effectiveness.

Identification of Pepper Leaf Diseases Based on TPSAO-AMWNet

Pepper is a high-economic-value agricultural crop that faces diverse disease challenges such as blight and anthracnose. These diseases not only reduce the yield of pepper but, in severe cases, can also cause significant economic losses and threaten food security. The timely and accurate identification of pepper diseases is crucial. Image recognition technology plays a key role in this aspect by automating and efficiently identifying pepper diseases, helping agricultural workers to adopt and implement effective control strategies, alleviating the impact of diseases, and being of great importance for improving agricultural production efficiency and promoting sustainable agricultural development. In response to issues such as edge-blurring and the extraction of minute features in pepper disease image recognition, as well as the difficulty in determining the optimal learning rate during the training process of traditional pepper disease identification networks, a new pepper disease recognition model based on the TPSAO-AMWNet is proposed. First, an Adaptive Residual Pyramid Convolution (ARPC) structure combined with a Squeeze-and-Excitation (SE) module is proposed to solve the problem of edge-blurring by utilizing adaptivity and channel attention; secondly, to address the issue of micro-feature extraction, Minor Triplet Disease Focus Attention (MTDFA) is proposed to enhance the capture of local details of pepper leaf disease features while maintaining attention to global features, reducing interference from irrelevant regions; then, a mixed loss function combining Weighted Focal Loss and L2 regularization (WfrLoss) is introduced to refine the learning strategy during dataset processing, enhancing the model's performance and generalization capabilities while preventing overfitting. Subsequently, to tackle the challenge of determining the optimal learning rate, the tent particle snow ablation optimizer (TPSAO) is developed to accurately identify the most effective learning rate. The TPSAO-AMWNet model, trained on our custom datasets, is evaluated against other existing methods. The model attains an average accuracy of 93.52% and an F1 score of 93.15%, demonstrating robust effectiveness and practicality in classifying pepper diseases. These results also offer valuable insights for disease detection in various other crops.

MCCM: multi-scale feature extraction network for disease classification and recognition of chili leaves

Currently, foliar diseases of chili have significantly impacted both yield and quality. Despite effective advancements in deep learning techniques for the classification of chili leaf diseases, most existing classification models still face challenges in terms of accuracy and practical application in disease identification. Therefore, in this study, an optimized and enhanced convolutional neural network model named MCCM (MCSAM-ConvNeXt-MSFFM) is proposed by introducing ConvNeXt. The model incorporates a Multi-Scale Feature Fusion Module (MSFFM) aimed at better capturing disease features of various sizes and positions within the images. Moreover, adjustments are made to the positioning, activation functions, and normalization operations of the MSFFM module to further optimize the overall model. Additionally, a proposed Mixed Channel Spatial Attention Mechanism (MCSAM) strengthens the correlation between non-local channels and spatial features, enhancing the model's extraction of fundamental characteristics of chili leaf diseases. During the training process, pre-trained weights are obtained from the Plant Village dataset using transfer learning to accelerate the model's convergence. Regarding model evaluation, the MCCM model is compared with existing CNN models (Vgg16, ResNet34, GoogLeNet, MobileNetV2, ShuffleNet, EfficientNetV2, ConvNeXt), and Swin-Transformer. The results demonstrate that the MCCM model achieves average improvements of 3.38%, 2.62%, 2.48%, and 2.53% in accuracy, precision, recall, and F1 score, respectively. Particularly noteworthy is that compared to the original ConvNeXt model, the MCCM model exhibits significant enhancements across all performance metrics. Furthermore, classification experiments conducted on rice and maize disease datasets showcase the MCCM model's strong generalization performance. Finally, in terms of application, a chili leaf disease classification website is successfully developed using the Flask framework. This website accurately identifies uploaded chili leaf disease images, demonstrating the practical utility of the model.

Application of PLS-NN model based on mid-infrared spectroscopy in the origin identification of Cornus officinalis

Mid-infrared spectroscopy has been increasingly used as a nondestructive analytical technique in Chinese herbal medicine identification in recent years. In this study, a new chemometric model named as PLS-NN model was proposed based on the mid-infrared spectral data of Cornus officinalis samples from 11 origins. It was realized by combining the partial least squares and neural networks for the identification of the origin of Chinese herbal medicines. First, we extracted features from the spectral data in 3448 bands using the partial least squares method, and extracted 122 components that contained more than 95% of the information. Then, we trained the PLS-NN model by neural network using the extracted components as inputs and the corresponding origin classes as outputs. Finally, based on an external test set, we evaluated the generalization ability of the PLS-NN model using metrics such as accuracy, F1-Score and Kappa coefficient. The results show that the PLS-NN model performs well in all three metrics when compared to models such as Decision trees, Support vector machine, Partial least squares Discriminant analysis, and Naive bayes. The model not only realizes the dimensionality reduction of full-spectrum data and improves the training efficiency of the model, but also has higher accuracy compared with the full-spectrum data model. The PLS-NN model was applied to identify the origin of Cornus officinalis with an accuracy of 91.9%.

Rapid classification of whole milk powder and skimmed milk powder by laser-induced breakdown spectroscopy combined with feature processing method and logistic regression

Whole milk powder and skimmed milk powder are suitable for different groups of people due to their differences in composition. Therefore, a rapid classification method for whole milk powder and skimmed milk powder is urgently needed. In this paper, a novel strategy based on laser-induced breakdown spectroscopy (LIBS) and feature processing methods combined with logistic regression (LR) was constructed for the classification of milk powder. A LR classification model based on mini-batch gradient descent (MGD) was employed first. As indicated by the research results, the accuracy of the MGD-LR model for the milk powder samples in the test set is 96.33% and the modeling time is 33.07 s. The modeling efficiency is low and needs to be improved. Principal components analysis (PCA) and mutual information (MI) were used as feature processing methods to reduce the high dimensional LIBS data into fewer features for improving the modeling efficiency of the classification model. The research results indicate that the accuracy of the PCA-MGD-LR model and the MI-MGD-LR model for the test set of milk powder samples was 99.33% and 99.67%, respectively. Compared with MGD-LR model, the modeling efficiency of PCA-MGD-LR and MI-MGD-LR models has increased by 89.7% and 74.8%, respectively. The results fully demonstrate the feasibility of rapid milk powder classification based on LIBS and feature processing methods combined with LR, and it will provide a new technology for the identification and classification of milk powder.

Salt Tolerance Evaluation of Cucumber Germplasm under Sodium Chloride Stress

Cucumber (Cucumis sativus L.) is an important horticultural crop worldwide. Sodium (Na+) and chloride (Cl-) in the surface soil are the major limiting factors in coastal areas of Shandong Province in China. Therefore, to understand the mechanism used by cucumber to adapt to sodium chloride (NaCl), we analyzed the phenotypic and physiological indicators of eighteen cucumber germplasms after three days under 100 and 150 mM NaCl treatment. A cluster analysis revealed that eighteen germplasms could be divided into five groups based on their physiological indicators. The first three groups consisted of seven salt-tolerant and medium salt-tolerant germplasms, including HLT1128h, Zhenni, and MC2065. The two remaining groups consisted of five medium salt-sensitive germplasms, including DM26h and M1-2-h-10, and six salt-sensitive germplasms including M1XT and 228. A principal component analysis revealed that the trend of comprehensive scores was consistent with the segmental cluster analysis and survival rates of cucumber seedlings. Overall, the phenotype, comprehensive survival rate, cluster analysis, and principal component analysis revealed that the salt-tolerant and salt-sensitive germplasms were Zhenni, F11-15, MC2065, M1XT, M1-2-h-10, and DM26h. The results of this study will provide references to identify or screen salt-tolerant cucumber germplasms and lay a foundation for breeding salt-tolerant cucumber varieties.

Pepper leaf disease recognition based on enhanced lightweight convolutional neural networks

Pepper leaf disease identification based on convolutional neural networks (CNNs) is one of the interesting research areas. However, most existing CNN-based pepper leaf disease detection models are suboptimal in terms of accuracy and computing performance. In particular, it is challenging to apply CNNs on embedded portable devices due to a large amount of computation and memory consumption for leaf disease recognition in large fields. Therefore, this paper introduces an enhanced lightweight model based on GoogLeNet architecture. The initial step involves compressing the Inception structure to reduce model parameters, leading to a remarkable enhancement in recognition speed. Furthermore, the network incorporates the spatial pyramid pooling structure to seamlessly integrate local and global features. Subsequently, the proposed improved model has been trained on the real dataset of 9183 images, containing 6 types of pepper diseases. The cross-validation results show that the model accuracy is 97.87%, which is 6% higher than that of GoogLeNet based on Inception-V1 and Inception-V3. The memory requirement of the model is only 10.3 MB, which is reduced by 52.31%-86.69%, comparing to GoogLeNet. We have also compared the model with the existing CNN-based models including AlexNet, ResNet-50 and MobileNet-V2. The result shows that the average inference time of the proposed model decreases by 61.49%, 41.78% and 23.81%, respectively. The results show that the proposed enhanced model can significantly improve performance in terms of accuracy and computing efficiency, which has potential to improve productivity in the pepper farming industry.

Feasibility Study on the Classification of Persimmon Trees' Components Based on Hyperspectral LiDAR

Intelligent management of trees is essential for precise production management in orchards. Extracting components' information from individual fruit trees is critical for analyzing and understanding their general growth. This study proposes a method to classify persimmon tree components based on hyperspectral LiDAR data. We extracted nine spectral feature parameters from the colorful point cloud data and performed preliminary classification using random forest, support vector machine, and backpropagation neural network methods. However, the misclassification of edge points with spectral information reduced the accuracy of the classification. To address this, we introduced a reprogramming strategy by fusing spatial constraints with spectral information, which increased the overall classification accuracy by 6.55%. We completed a 3D reconstruction of classification results in spatial coordinates. The proposed method is sensitive to edge points and shows excellent performance for classifying persimmon tree components.

Origin identification of Cornus officinalis based on PCA-SVM combined model

Infrared spectroscopy can quickly and non-destructively extract analytical information from samples. It can be applied to the authenticity identification of various Chinese herbal medicines, the prediction of the mixing amount of defective products, and the analysis of the origin. In this paper, the spectral information of Cornus officinalis from 11 origins was used as the research object, and the origin identification model of Cornus officinalis based on mid-infrared spectroscopy was established. First, principal component analysis was used to extract the absorbance data of Cornus officinalis in the wavenumber range of 551~3998 cm-1. The extracted principal components contain more than 99.8% of the information of the original data. Second, the extracted principal component information was used as input, and the origin category was used as output, and the origin identification model was trained with the help of support vector machine. In this paper, this combined model is called PCA-SVM combined model. Finally, the generalization ability of the PCA-SVM model is evaluated through an external test set. The three indicators of Accuracy, F1-Score, and Kappa coefficient are used to compare this model with other commonly used classification models such as naive Bayes model, decision trees, linear discriminant analysis, radial basis function neural network and partial least square discriminant analysis. The results show that PCA-SVM model is superior to other commonly used models in accuracy, F1 score and Kappa coefficient. In addition, compared with the SVM model with full spectrum data, the PCA-SVM model not only reduces the redundant variables in the model, but also has higher accuracy. Using this model to identify the origin of Cornus officinalis, the accuracy rate is 84.8%.

Machine learning in analytical spectroscopy for nuclear diagnostics [Invited]

Analytical spectroscopy methods have shown many possible uses for nuclear material diagnostics and measurements in recent studies. In particular, the application potential for various atomic spectroscopy techniques is uniquely diverse and generates interest across a wide range of nuclear science areas. Over the last decade, techniques such as laser-induced breakdown spectroscopy, Raman spectroscopy, and x-ray fluorescence spectroscopy have yielded considerable improvements in the diagnostic analysis of nuclear materials, especially with machine learning implementations. These techniques have been applied for analytical solutions to problems concerning nuclear forensics, nuclear fuel manufacturing, nuclear fuel quality control, and general diagnostic analysis of nuclear materials. The data yielded from atomic spectroscopy methods provide innovative solutions to problems surrounding the characterization of nuclear materials, particularly for compounds with complex chemistry. Implementing these optical spectroscopy techniques can provide comprehensive new insights into the chemical analysis of nuclear materials. In particular, recent advances coupling machine learning methods to the processing of atomic emission spectra have yielded novel, robust solutions for nuclear material characterization. This review paper will provide a summation of several of these recent advances and will discuss key experimental studies that have advanced the use of analytical atomic spectroscopy techniques as active tools for nuclear diagnostic measurements.

Application of Laser-Induced Breakdown Spectroscopy and Chemometrics for the Quality Evaluation of Foods with Medicinal Properties: A Review

Laser-induced Breakdown Spectroscopy (LIBS) is becoming an increasingly popular analytical technique for characterizing and identifying various products; its multi-element analysis, fast response, remote sensing, and sample preparation is minimal or nonexistent, and low running costs can significantly accelerate the analysis of foods with medicinal properties (FMPs). A comprehensive overview of recent advances in LIBS is presented, along with its future trends, viewpoints, and challenges. Besides reviewing its applications in both FMPs, it is intended to provide a concise description of the use of LIBS and chemometrics for the detection of FMPs, rather than a detailed description of the fundamentals of the technique, which others have already discussed. Finally, LIBS, like conventional approaches, has some limitations. However, it is a promising technique that may be employed as a routine analysis technique for FMPs when utilized effectively.

Authentication of Herbal Medicines Based on Modern Analytical Technology Combined with Chemometrics Approach: A Review

Since ancient times, herbal medicines (HMs) have been widely popular with consumers as a "natural" drug for health care and disease treatment. With the emergence of problems, such as increasing demand for HMs and shortage of resources, it often occurs the phenomenon of shoddy exceed and mixing the false with the genuine in the market. There is an urgent need to evaluate the quality of HMs to ensure their important role in health care and disease treatment, and to reduce the possibility of threat to human health. Modern analytical technology is can be analyzed for analyzing chemical components of HMs or their preparations. Reflecting complex chemical components' characteristic curves in the analysis sample, and the comprehensive effect of active ingredients of HMs. In this review, modern analytical technology (chromatography, spectroscopy, mass spectrometry), chemometrics methods (unsupervised, supervised) and their advantages, disadvantages, and applicability were introduced and summarized. In addition, the authentication application of modern analytical technology combined with chemometrics methods in four aspects, including origin, processing methods, cultivation methods, and adulteration of HMs have also been discussed and illustrated by a few typical studies. This article offers a general workflow of analytical methods that have been applied for HMs authentication and explains that the accuracy of authentication in favor of the quality assurance of HMs. It was provided reference value for the development and application of modern HMs.

Rapid parameter estimation of discrete decaying signals using autoencoder networks

In this work we demonstrate the use of neural networks for rapid extraction of signal parameters of discretely sampled signals. In particular, we use dense autoencoder networks to extract the parameters of interest from exponentially decaying signals and decaying oscillations. By using a three-stage training method and careful choice of the neural network size, we are able to retrieve the relevant signal parameters directly from the latent space of the autoencoder network at significantly improved rates compared to traditional algorithmic signal-analysis approaches. We show that the achievable precision and accuracy of this method of analysis is similar to conventional algorithm-based signal analysis methods, by demonstrating that the extracted signal parameters are approaching their fundamental parameter estimation limit as provided by the Cramér–Rao bound. Furthermore, we demonstrate that autoencoder networks are able to achieve signal analysis, and, hence, parameter extraction, at rates of 75 kHz, orders-of-magnitude faster than conventional techniques with similar precision. Finally, our exploration of the limitations of our approach in different computational systems suggests that analysis rates of > 200 kHz are feasible using neural networks in systems where the transfer time between the data-acquisition system and data-analysis modules can be kept below ∼3 µs.

Automated Distinction between Cement Paste and Aggregates of Concrete Using Laser-Induced Breakdown Spectroscopy

Laser-induced breakdown spectroscopy (LIBS) is a technique which enables the analysis of material components with precision and spatial resolution. Furthermore, the investigation method is comparatively fast which enables illustrating the distribution of elements within the examined material. This opens new possibilities for the investigation of very heterogeneous materials, such as concrete. Concrete consists of cement, water, and aggregates. As most of the transport processes take place exclusively in the hardened cement paste, relevant limit values linked to harmful element contents are specified in relation to the cement mass. When a concrete sample from an existing structure is examined, information on the concrete composition is usually not available. Therefore, assumptions have to be made to convert the element content analyzed in the sample based on the cement content in the sample. This inevitably leads to inaccuracies. Therefore, a method for distinction between cement paste and aggregates is required. Cement and aggregate components are chemically very close to each other and therefore, complex for classification. This is why the consideration of a single distinguishing feature is not sufficient. In this paper, a machine learning method is described and has been used to automate the distinction of the cement paste and aggregates of the LIBS data to receive reliable information of this technique. The presented approach could potentially be employed for many heterogeneous materials with the same complexity to quantify the arbitrary substances.

Lithium Isotope Measurement Using Laser-Induced Breakdown Spectroscopy and Chemometrics

Laser-induced breakdown spectroscopy (LIBS) is a technique capable of portable, quantitative elemental analysis; however, quantitative isotopic determination of samples in situ has not yet been demonstrated. This research demonstrates the ability of LIBS to quantitatively determine concentrations of ⁶Li in solid samples of lithium hydroxide monohydrate in a nominally 40 mTorr argon environment using chemometrics. Three chemometric analysis techniques (principal component regression, partial least squares regression, and neural networks analysis) are applied to spectra collected using a spectrometer with modest resolving power (λ/Δλ ≈ 27 000). This analysis suggests that bulk lithium isotopic assay can be determined using LIBS to within a 95% confidence interval in minutes to an hour for enrichment levels ranging from 3% to 85%. This has direct applications for the nuclear safeguards and geological exploration communities and others that desire a portable, stable isotope analytical technique. Additionally, isotope-specific self-absorption of atomic emission in a laser-produced plasma is observed for the first time.

Ultraviolet-visible diffuse reflectance spectroscopy combined with chemometrics for rapid discrimination of Angelicae Sinensis Radix from its four similar herbs

Ultraviolet-visible diffuse reflectance spectroscopy (UV-Vis DRS) combined with chemometrics was used for the first time to differentiate Angelicae Sinensis Radix (ASR) from four other similar herbs (either from the same genus or of similar appearance). A total of 191 samples, including 40 ASR, 39 Angelicae Pubescentis Radix (APR), 38 Chuanxiong Rhizoma (CR), 35 Atractylodis Macrocephalae Rhizoma (AMR) and 39 Angelicae Dahuricae Radix (ADR), were collected and divided into the training and prediction sets. Principal component analysis (PCA) was used for observing the sample cluster tendency of the calibration set. Different preprocessing methods were investigated and the optimal preprocessing combination was selected according to spectral signal characteristics and three-dimensional PCA (3D PCA) clustering results. The final discriminant model was built using extreme learning machine (ELM). The exploratory studies on the raw spectra and their 3D PCA scores indicate that the classification of the five herbs cannot be achieved by PCA of the raw spectra. Autoscaling, continuous wavelet transform (CWT) and Savitzky-Golay (SG) smoothing can improve the clustering results to different degrees. Furthermore, their combination in the order of CWT + autoscaling + SG smoothing can enhance the spectral resolution and obtain the best clustering result. These results are also validated using ELM models of raw and different preprocessing methods. By using CWT + autoscaling + SG smoothing + ELM, 100% classification accuracy can be achieved in both the calibration set and the prediction set. Therefore, the developed method could be used as a rapid, economic and effective method for discriminating the five herbs used in this study.

Recent advances of novel technologies for quality consistency assessment of natural herbal medicines and preparations

Quality consistency is one of the basic attributes of medicines, but it is also a difficult problem that natural medicines and their preparations must face. The complex chemical composition and comprehensive pharmacological action of natural medicines make it difficult to simply apply the commonly used evaluation methods in chemical drugs. It is thus urgent to explore the novel evaluation methods suitable for the characteristics of natural medicines. With the rapid development of analytical techniques and the deepening understanding of the quality of natural herbs, increasing numbers of researchers have proposed many new ideas and technologies. This review mainly focuses on the basic principles, technical characteristics and application examples of the chemical evaluation, biological evaluation methods and their combination in quality consistency evaluation of natural herbs. On the bases of chemical evaluation and clinical efficacy, new methods reflecting their pharmacodynamic mechanism and safety characteristics will be developed, and gradually towards accurate quality control, to achieve the goal of quality consistency. We hope that this manuscript can provide new ideas and technical references for the quality consistency of natural drugs and their preparations, thus better guarantee their clinical efficacy and safety, and better promote industrial development.

Elemental analysis of sage (herb) using calibration-free laser-induced breakdown spectroscopy

In this work, laser-induced breakdown spectroscopy (LIBS) has been used for the quantitative and qualitative analysis of the sage sample using the calibration-free LIBS (CF-LIBS) technique. The sage plasma is generated by focusing the second harmonics (532 nm) of a Q-switched Nd:YAG laser with a repetition rate of 10 Hz and pulse duration of 5 ns. The emission spectra are recorded using a LIBS 2000 detection system spectrometer consisting of five high-resolution spectrometers covering a wavelength range from 200 to 720 nm. The optical emission spectra of the sage sample reveal the spectral lines of Fe, Ca, Ti, Co, Mn, Ni, and Cr. The plasma temperature and electron number density of the neutral spectral lines of the pertinent elements have been deduced using the Boltzmann plot and Stark-broadening line profile method, with average values 8855±885K and 3.89×10¹⁶cm^-3, respectively. The average values of the plasma parameters were used for the quantification of the detected elements in the sample. Based on the calibration-free method, the measured results demonstrate that Fe is the major constituent in the sample, having a percentage concentration of 48.1%, while the remaining elements are Ca, Ti, Co, Mn, Ni, and Cr, with percentage concentrations 0.7%, 5.3%, 8%, 11%, 12.3%, and 14.6%, respectively. This study demonstrates the feasibility of LIBS for the compositional analysis of major and trace elements present in the plant samples and its further applications in medicine.

Identifying Ancient Ceramics Using Laser-Induced Breakdown Spectroscopy Combined with a Back Propagation Neural Network

This study investigated the rapid identification of ceramics via laser-induced breakdown spectroscopy (LIBS) to realize the identification of ancient ceramics from different regions. Ceramics from different regions may have large differences in their elemental composition. Thus, using LIBS technology for ceramic identification is feasible. The spectral intensities of 11 common elements, namely, Si, Al, Fe, Ca, Mg, Ti, Mn, Na, K, Sr, and Ba, in ceramics were selected as classification indices. Principal component analysis (PCA) and kernel principal component analysis (KPCA) combined with the back propagation (BP) neural network were used to identify ceramics. Furthermore, the effects of the PCA and KPCA data processing methods were compared. Finally, this work aimed to select a suitable method for obtaining spectral data on ceramics identified by LIBS through experiments. Results revealed that LIBS technology could aid the routine, rapid, and on-site analysis of archeological objects to rapidly identify or screen various types of objects.

Traceability the provenience of cultivated Paris polyphylla Smith var. yunnanensis using ATR-FTIR spectroscopy combined with chemometrics

The conventional procedures, based on attenuated total reflectance-Fourier transform infrared spectrometry (ATR-FTIR), have been developed for the origins traceability of cultivated Paris polyphylla Smith var. yunnanensis (PPY) samples with the help of partial least square discriminant analysis (PLS-DA) and random forest. In this study, a set of 219 batch cultivated PPY samples, containing the cultivation years of 5, 6 and 7, and covering the municipal districts of Chuxiong, Dali, Honghe, Lijiang and Yuxi in Yunnan Province, China, were used to build the discrimination models. Firstly, a visualized analysis was carried out by t-distributed stochastic neighbor embedding (t-SNE) to reduce each data point in a two-dimensional map and make a knowledge of the sample distribution tendency. Secondly, the single spectra data sets of Paridis rhizome and leaf tissues, and the combination of these two data sets with variable selection (mid-level data fusion strategy), were used to establish PLS-DA and random forest models, and parallelly compared the model performance. Results demonstrated that the discrimination ability of PLS-DA preceded the random forest model, and the classification performance was remarkably improved after mid-level data fusion. These results verified each other by 5-, 6- and 7-year old Paridis samples and indicated that the model performance established in the present study was reliable. Besides, five agronomic characters, including the plant height, dry weight of rhizome and leaf tissues, and the allocation of rhizome and leaf were determined and analyzed, results of which indicated that the dry weight and their allocation was significantly different among various origins and fluctuated with the cultivation years. This study was using a comprehensive and green analytical method to discriminate the cultivated Paridis according to their provenances, which was simultaneously benefited for the appropriate cultivation areas selection based on the dry weight of rhizome tissues.

Rapid Identification of Kudzu Powder of Different Origins Using Laser-Induced Breakdown Spectroscopy

The rapid identification of kudzu powder of different origins is of great significance for studying the authenticity identification of Chinese medicine. The feasibility of rapidly identifying kudzu powder origin was investigated based on laser-induced breakdown spectroscopy (LIBS) technology combined with chemometrics methods. The discriminant models based on the full spectrum include extreme learning machine (ELM), soft independent modeling of class analogy (SIMCA), K-nearest neighbor (KNN) and random forest (RF), and the accuracy of models was more than 99.00%. The prediction results of KNN and RF models were best: the accuracy of calibration and prediction sets of kudzu powder from different producing areas both reached 100%. The characteristic wavelengths were selected using principal component analysis (PCA) loadings. The accuracy of calibration set and the prediction set of discrimination models, based on characteristic wavelengths, is all higher than 98.00%. Random forest and KNN have the same excellent identification results, and the accuracy of calibration and prediction sets of kudzu powder from different producing areas reached 100%. Compared with the full spectrum discriminant analysis model, the discriminant analysis model based on the characteristic wavelength had almost the same discriminant effects, and the input variables were reduced by 99.92%. The results of this research show that the characteristic wavelength can be used instead of the LIBS full spectrum to quickly identify kudzu powder from different producing areas, which had the advantages of reducing input, simplifying the model, increasing the speed and improving the model effect. Therefore, LIBS technology is an effective method for rapid identification of kudzu powder from different habitats. This study provides a basis for LIBS to be applied in the genuineness and authenticity identification of Chinese medicine.

Rapid identification of rice species by laser-induced breakdown spectroscopy combined with pattern recognition

Laser-induced breakdown spectroscopy (LIBS) combined with pattern recognition was proposed to discriminate rice species. LIBS spectra in the range of 210-480 nm wavelength from 11 different rice species were collected and preprocessed. Principal component analysis was applied to extract the characteristic variables from LIBS spectral data. Three pattern recognition methods, discriminant analysis, radial basis function neural network, and multi-layer perceptron neural network (MLP) were performed to compare the precision in identifying rice species. The results showed that the performance of the MLP model was better. The average identification rate of rice species reached 100% and 97.9% in the training and test sets, respectively, with MLP. The highest and lowest percentages for correct identification were 100% for early indica rice, Huai rice 5, Yan japonica 6, Lian japonica 8, Xuhan 1, Lvhan 1, Sheng rice 16, Yang japonica 687, and Fenghan 30, and 77.8% for Wuyu japonica rice in test sets. The overall results demonstrate that LIBS combined with MLP could be utilized to rapidly discriminate rice species.

Modeling of laser-induced breakdown spectroscopic data analysis by an automatic classifier

Laser-induced breakdown spectroscopy (LIBS) is a multi-elemental and real-time analytical technique with simultaneous detection of all the elements in any type of sample matrix including solid, liquid, gas, and aerosol. LIBS produces vast amount of data which contains information on elemental composition of the material among others. Classification and discrimination of spectra produced during the LIBS process are crucial to analyze the elements for both qualitative and quantitative analysis. This work reports the design and modeling of optimal classifier for LIBS data classification and discrimination using the apparatus of statistical theory of detection. We analyzed the noise sources associated during the LIBS process and created a linear model of an echelle spectrograph system. We validated our model based on assumptions through statistical analysis of "dark signal" and laser-induced breakdown spectra from the database of National Institute of Science and Technology. The results obtained from our model suggested that the quadratic classifier provides optimal performance if the spectroscopy signal and noise can be considered Gaussian.

Rapid identification and quantification of Panax notoginseng with its adulterants by near infrared spectroscopy combined with chemometrics

Traditional methods for identification of Panax notoginseng (PN) such as high performance liquid chromatography (HPLC) and gas chromatography (GC) are time-consuming, laborious and difficult to realize rapid and online analysis. In this research, the feasibility of identification and quantification of PN with rhizoma curcumae (RC), Curcuma longa (CL) and rhizoma alpiniae offcinarum (RAO) are investigated by using near infrared (NIR) spectroscopy combined with chemometrics. Five chemical pattern recognition methods including hierarchical cluster analysis (HCA), partial least squares-discriminant analysis (PLS-DA), artificial neural networks (ANN), support vector machine (SVM) and extreme learning machine (ELM) are used to build identification model of the dataset with 109 samples of PN and its three adulterants. Then seven datasets of binary, ternary and quaternary adulterations of PN are designed, respectively. Five multivariate calibration methods, i.e., principal component regression (PCR), support vector regression (SVR), partial least squares regression (PLSR), ANN and ELM are used to build quantitative model and compared for each dataset, separately. Finally, in order to further improve the prediction accuracy, SG smoothing, 1st derivative, 2nd derivative, continuous wavelet transform (CWT), standard normal variate (SNV), multiple scatter correction (MSC) and their combinations are investigated. Results show that PLS-DA and SVM can achieve 100% classification accuracy for identification of 109 PN with its three adulterants. PLSR is an optimal calibration method by comprehensive consideration of prediction accuracy, over-fitting and efficiency for the quantitative analysis of seven adulterated datasets. Furthermore, the predictive ability of the PLSR model for PN contents can be improved obvious by pretreating the spectra by the optimal preprocessing method, with correlation coefficients of which all higher than 0.99.