Savitzky-Golay Smoothing Research Articles

Hierarchical extreme puzzle learning machine-based emotion recognition using multimodal physiological signals

Detection of exact emotions through multi-modal physiological signals provides relevant information for different processes. Numerous computational approaches have been presented for the precise analysis of emotion types. But due to some problems like ruined signal quality, increased time consumption, and the necessity of high storage space, classification accuracy’s efficiency worsens. Hence, this research classified multi-modal physiological signals based on machine and deep learning (DL) models. The proposed work implements the Hierarchical Extreme Puzzle Learning Machine (HEPLM) approach to classify the actual output of embedded emotions. The proposed work comprises four steps: pre-processing, signal-to-image conversion, feature extraction, and classification. Pre-processing is carried out using Savitzky-Golay smoothing filtering (SGF) for the removal of noise and to increase signal quality. Hybrid wavelet scattering with Synchro squeezing Wavelet Transform approach converts the signal into an image. In feature extraction process, the valuable features are extracted using ResNet-152 and the Inception v3 model, whereas the features are combined through an ensemble approach. HEPLM is used in the final classification process, combining Puzzle Optimization Algorithm (POA) and Hierarchical Extreme Learning Machine (HELM) to reduce feature dimensionality and improve classification accuracy. The dataset adopted in the proposed work is Wearable Stress and Affect Detection (WESAD) to collect multi-modal physiological signals. The presentation of the projected work is assessed with metrics like accuracy, recall, precision, F1 score, kappa, and so on. The proposed effort demonstrates better results of emotion classification when compared to the existing methods by holding 96.29% of accuracy.

Nondestructive Determination of Leaf Nitrogen Content in Corn by Hyperspectral Imaging Using Spectral and Texture Fusion

The nitrogen content is an important indicator affecting corn plants’ growth status. Most of the standard hyperspectral imaging-based techniques for nondestructive detection of crop nitrogen content use a single feature as the input variable of the model, which reduces the generalization ability of the prediction model. To this end, a prediction model for the nitrogen content of corn leaves based on the fusion of image and spectral features is proposed. In this study, corn leaves at the modulation stage were studied, samples with different nitrogen levels were numbered, and their hyperspectral data in the wavelength range of 400~1100 nm were collected. The average spectrum of the models was used as valid spectral information. First-order derivatives, standard normal variables transformation (SNV), Savitzky-Golay (S-G) smoothing, and normalization were selected to preprocess the spectral features. The CARS-SPA algorithm was used to screen sensitive spectral variables. The gray level co-currency matrix (GLCM) was chosen to extract the texture image features of the test samples. Corn leaf spectral and texture image features were fused and modeled as target features. Partial least squares regression (PLSR) and support vector machine regression (SVR) were used to predict corn leaves’ nitrogen content. The results showed that the image and spectral-based fusion models improved the prediction performance to some extent compared to the univariate models. The PLSR model based on feature fusion predicted the best results, in which the RP2 and RMSEP were 0.987 and 0.047. This method provides a reliable theoretical basis and technical support for developing nondestructive and accurate detection of nitrogen content in corn leaves.

Rapid Detection of Tea Polyphenols in Fresh Tea Leaves Based on Fusion of Visible/Short-Wave and Long-Wave near Infrared Spectroscopy and Its Device Development

Tea polyphenols are considered as an important indicator of tea quality. Rapid detection of tea polyphenol content plays a valuable role for tea breeding and quality inspection during tea production. In this work, a portable rapid non-destructive detection device of tea polyphenols in fresh tea leaves was developed, which integrated the fusion technology of visible/short-wave (400–1050 nm) and long-wave (1000–1650 nm) near-infrared spectroscopy (Vis/NIR). Experimental results indicated that the spectra within the overlapping region (1000–1050 nm) were assembled by applying the spectral data fusing method. Followed by spectral data preprocessing with the Savitzky–Golay smoothing (SG) method, least squares support vector regression (LS–SVR) models were established for detecting the tea polyphenol content of fresh tea leaves. Based on the fused Vis/NIR spectra (dual-band), the correlation coefficient of calibration (RC), root mean square error of calibration (RMSEC), correlation coefficient of prediction (RP), root mean square error of prediction (RMSEP), and residual predictive deviation (RPD) reached 0.976, 0.679%, 0.893, 0.897%, and 2.230, respectively, which were better than the visible/short-wave or long-wave near infrared spectral data (single-band). The sensitive spectral wavebands of tea polyphenols extracted using the random frog (RF) algorithm were distributed in 402–448 nm, 555–600 nm, 810–1042 nm, 1056–1103 nm, 1219–1323 nm, 1406–1416 nm, and 1499–1511 nm. This demonstrated that the prediction of tea polyphenol content using fused spectral data combined with the LS–SVR model depended on various functional groups such as auxochromes, chromogenic groups, and hydrogen-containing groups. The proposed device is capable of non-destructive detection of tea polyphenol content in fresh tea leaves, which can provide effective technical support for tea breeding and tea leaf quality control.

Leaf-based species classification of hybrid cherry tomato plants by using hyperspectral imaging

Approaches based on near infrared hyperspectral imaging (NIR-HSI) technology combined with machine learning have been developed to classify the leaves of hybrid cherry tomatoes and then identify the species of hybrid cherry tomato plants. The near infrared (NIR) hyperspectral images of 400 cherry tomato leaves (100 per species) were collected in the wavelength range of 900–1700 nm. Machine learning algorithms such as linear discriminant analysis (LDA), random forest (RF), and support vector machine (SVM) were employed to construct leaf classification models with the hyperspectral data preprocessed by Savitzky-Golay (SG) smoothing filter, first derivative (first Der) and standard normal variate (SNV). Principle of Component Analysis (PCA) was also used to reduce the data dimension and extract spectral features. It is revealed that the LDA model reaches the highest classification accuracy among the three machine learning algorithms and SNV can lead to higher improvement in model accuracy than other preprocessing methods of SG smoothing and first Der. Analysis based on PCA spectral feature extraction demonstrates that differences occur in internal material content in the leaves of cherry tomato plants with different species, which renders the models being able to distinguish between the species. Another important work was performed to reveal the different effects of the mesophyll and vein regions (VR) on the accuracy of the leaf classification model. It is demonstrated that the classification accuracy is improved by a value of 0.033 or 0.042 when mesophyll substitutes vein or whole leaf as regions of interest (ROI) to extract reflectance spectra for modeling. As a result, the accuracy of the training and test set respectively reached a high value of 0.998 and 0.973 for the LDA classification model combined with the SNV preprocessing method. The results propose that the use of mesophyll region (MR) as ROI can improve the performance of the leaf classification model, which provides a new strategy for efficient and non-destructive classification of different hybrid cherry tomato plants.

Rapid detection of chemical oxygen demand, pH value, total nitrogen, total phosphorus, and ammonia nitrogen in biogas slurry by near infrared spectroscopy.

Effective treatment of sewage requires accurate measurement of important water quality parameters, such as chemical oxygen demand (COD), pH value, total nitrogen (TN), total phosphorus (TP), and ammonia nitrogen (NH3-N). Traditional detection techniques can result in secondary contamination and are time- and labor-intensive. Near infrared spectroscopy was used in this study to create a model of these parameters of pig manure anaerobic fermentation sewage. The models' viability for quickly estimating the aforementioned water quality characteristics was reviewed, and the models' performance in predicting the results of several samples (biogas slurry, supernatant, and biogas residue) was contrasted. By analyzing the near infrared spectrograms with a spectral range of 4000 cm-1 and 12 500 cm-1 and using second derivative (SD), Savitzky-Golay smoothing (SG) and standard normal variable (SNV) to preprocess the spectra, partial least squares (PLS) was selected to establish the prediction model. The results showed that the effect of the NIR model constructed from the supernatant was better than that of biogas slurry and biogas residue. The determination coefficients for COD, pH value, NH3-N and TN were 0.69, 0.87, 0.81, and 0.94, respectively. This study could provide reference for on-line monitoring of wastewater in the future.

Non-destructive Detection of Fatty Acid Content of Camellia Seed Based on Hyperspectral.

As a unique traditional vegetable oil in China, camellia seed oil has very high edible value. Camellia seed kernel is mainly composed of fatty acids, which not only determines the oil yield of camellia seed, but also exert an important impact on the storage performance of camellia seed. In order to quickly and accurately determine the fatty acid content of camellia seed, this paper took camellia seed as the research object, used hyperspectral technology to determine the fatty acid content of camellia seed, and establishes a spectral model. 8 pretreatment methods, such as Savitzky-Golay smoothing, normalization, baseline correction, multivariate scattering correction, standard normal variable transformation, detrending algorithm, first derivative and second derivative, were adopted in this paper. The spectral prediction model of fatty acid content in camellia seed was established by combining 4 modeling methods: principal components regression (PCR), partial least square regression (PLSR), back propagation neural network (BP), radial basis function neural network (RBF). The optimal prediction model was selected by comparing the coefficient of determination (R2) and root mean square error (RMSE) of various models. The results showed that the spectral sensitive bands with high correlation coefficients (r) were 410-420 nm, 450-460 nm, 490-510 nm, 545-580 nm, 845-870 nm and 905-925 nm, respectively. The r obtained by MSC pretreatment of spectral data was the largest. The data obtained by 8 different pretreatment methods combined with RBF neural network model was the best, in which the average value of coefficient of determination (RC2) in the calibration set was 0.8654, and the root mean square error of calibration (RMSEC) was 0.0777; the average value of coefficient of determination (R2P) and root mean square error of prediction (RMSEP) in the prediction set model were 0.8437 and 0.0827, respectively. It could be seen that the best accuracy could be achieved by MSC pretreatment combined with RBF neural network modeling. This paper can provide reference for rapid nondestructive detection of fatty acid content in camellia seed by hyperspectral technology.

Predicting soil carbon in granitic soils using Fourier-transform mid-infrared (FT-MIR) spectroscopy: the value of database disaggregation

Soil carbon (C) is an important component in quality assessments and efficient models are required to estimate C rapidly. Accurate C assessments are valuable in monitoring land-use changes. Fourier-transform mid-infrared (FT-MIR) spectroscopy has proved to be a powerful tool for assessing C. The potential of FT-MIR spectroscopy to estimate C was evaluated using the following techniques: (1) three algorithms [partial least squares (PLS)], principal component regression (PCR), and classical least squares (CLS); and (2) disaggregating the dataset into subgroups based on soil depth and texture. The C contents of samples collected in the Johannesburg Granite Dome were determined by dry combustion for comparison. The soils ranged considerably in C (0.123–2.650%), clay (2.80–41.20%), and silt content (8.56–23.75%). Using standard normal variant (SNV), Savitzky-Golay smoothing and PLS, the best-performing model was the horizons subgroup which provided values of root mean square error for prediction (RMSEP) between 0.079 and 0.095%, root mean square error for calibration (RMSEC) = 0.041 − 0.092, r 2 pre = 0.6174–0.8459, r 2 cal = 0.6599–0.9778, residual prediction variation (RPD) = 2.404–2.753, and ratio of performance to interquartile range (RPIQ) = 2.667–3.454. The pronounced accuracy of FT-MIR spectroscopy coupled with PLS, pre-processing techniques, and textural subgroups confirms the potential of infrared spectroscopy as an efficient tool for estimating C content. Future studies should investigate the combined effects of FT-MIR spectroscopy and subgroups grouped according to soil types and land-uses when predicting C.

Water Stress Early Detection of Eggplant Plants by Hyperspectral Fluorescence Spectroscopy

Water stress early detection is essential for precision farming to improve crop productivity and product quality. The methods usually used are destructive, long and expensive. In this work, we used hyperspectral chlorophyll fluorescence technology as a rapid, non-destructive approach to detect the water deficiency of eggplant plants using their spectral footprint. So, an experiment was made on 54 eggplant plants subjected to three water treatments: normal irrigation (T100), intermediate irrigation (T50) and no irrigation (T0). The fluorescence spectra were acquired in vivo and in situ using a USB4000 spectrometer from Ocean optics. For the classification of the plants subjected to three water treatments, we used three pretreatments of the raw hyperspectral data in order to suppress the non-informative variability present in these spectra and to obtain robust models. These are the Savitzky-Golay smoothing (SG), the standard normal variable (SNV) and the first derivative of Savitzky-Golay (SG-D1). The preprocessed data were then subjected to two partial least squares discriminant analyses (PLS-DA): Hard PLS-DA and Soft PLS-DA. These statistical approaches are suitable for large samples as it reduces the dimensionality of the data but improves the accuracy of the prediction. The SG-D1 combined with the Soft PLS-DA gave the best discrimination of plants with scores of sensitivity, specificity and total efficiency respectively of 97.33%, 94% and 95% for calibration, 6 days after hydric stress induction. For the plants used for the prediction, the scores are 86%, 91% and 90% respectively. This study shows that hyperspectral chlorophyll fluorescence spectroscopy is a fast and non-destructive technology allowing early detection of water stress in eggplant plants.

Systemic risk prediction based on Savitzky-Golay smoothing and temporal convolutional networks

<abstract><p>Based on the data from January 2007 to December 2021, this paper selects 14 representatives from four levels of the extreme risk of financial institutions, the contagion effect between financial systems, volatility and instability of financial markets, liquidity, and credit risk systemic risk. By constructing a Savitzky-Golay-TCN deep convolutional neural network, the systemic risk indicators of China's financial market are predicted, and their accuracy and reliability are analyzed. The research found that: 1) Savitzky-Golay-TCN deep convolutional neural network has a strong generalization ability, and the prediction effect on all indices is stable. 2) Compared with the three control models (time-series convolutional network (TCN), convolutional neural network (CNN), and long short-term memory (LSTM)), the Savitzky-Golay-TCN deep convolutional neural network has excellent prediction accuracy, and its average prediction accuracy for all indices has increased. 3) Savitzky-Golay-TCN deep convolutional neural network can better monitor financial market changes and effectively predict systemic risk.</p></abstract>

A Mid-Infrared Spectrophotometric Method for Simultaneous Quantification of Naltrexone and Bupropion with Multivariate Calibration

Naltrexone (NTX) and bupropion (BUP) are used in combination in clinical practice for obesity; however, the existing analytical methods for this drug combination are not sustainable. This work aims to develop an analytical method that is faster, easier and less expensive compared with high performance liquid chromatography (HPLC) and involves green technology without solvents to quantify BUP and NTX in combination. The objective was to validate a method using mid-infrared (MIR) spectroscopy associated with multivariate calibration and chemometrics to simultaneously measure NTX and BUP in a pharmaceutical capsule form. The models were developed using MIR spectroscopy with diffuse reflectance, with interval partial least squares (iPLS) variable selection. The working range selected to optimize the model was from 1885.8 to 1585.4 cm-1. The chosen model was obtained with partial least squares (PLS2) and with data pre-processed by first derivative Savitzky-Golay smoothing followed by mean centering, using four latent variables, providing a root mean square error of prediction of 1.8 mg g-1 for NTX and 6.42 mg g-1 for BUP. The method was validated according to current international standards. In conclusion, the methods developed in the MIR region provided statistically similar results to the validated chromatographic method for commercial pharmaceutical formulations.

Rapid discrimination of Brassica napus varieties using visible and Near-infrared (Vis-NIR) spectroscopy

Brassica napus is an oilseed plant that is mostly used to produce edible oils, industrial oils, modified lipids and biofuels. The number of varieties/cultivars is high for the species, owing to their higher level of economic use. The aim of this study is to assess the use of visible-near infrared (Vis-NIR) spectroscopy in combination with multiple chemometric methods that have been explored for the discrimination of eight Brassica napus varieties in Korea. In this study, the spectra from leaves of the eight B. napus varieties were measured in the Vis-NIR spectra in the range of 325–1075 nm with a stepping of 1.5 nm in reflectance mode. The spectral data were preprocessed with three different preprocessing methods and eight different chemometric analyses were used for effective discrimination. After the outlier detection, the samples were split into two sets, one serving as a calibration set and the remaining one as a validation set. When using multiple preprocessing and chemometric methods for the discrimination, the maximum classification accuracy was witnessed in the combination of standard normal variate and support vector machine up to 98.2 %. The use of Savitzky-Golay filter smoothing as a preprocessing method had the best and most satisfactory discrimination of all other chemometric methods. The results suggest that the use of handheld Vis-NIR spectroscopy in combination with chemometric approaches can be used as an effective tool for the discrimination of B. napus varieties in the field.

Non-destructive measurement of malic acid content of sapodilla fruit using visible near infrared (VisNIR) spectroscopy with variations in storage temperature

Sapodilla fruit (Manilkara zapota) is a climacteric fruit having a short shelf life. To extend shelf life, cold temperature storage is often used. During storage, one of the parameters that could change is malic acid. Malic acid can be measured non-destructively using visible-near infrared (Vis-NIR) spectroscopy. However, measurement using VisNIR spectroscopy has limitations, one of which is the sensitivity of the instrument towards temperature. The temperature of the fruit influences VisNIR spectral data, therefore prediction of malic acid using VisNIR is challenging. This study was conducted to study fruit temperature effect on the malic acid measurement of sapodilla fruit using VisNIR spectroscopy. Partial least square regression (PLSR) combined with spectral preprocess (Savitzky-Golay smoothing, normalization, Savitzky-Golay 1st & 2nd derivatives, standard normal variate (SNV), detrending, and multiple scattering correction (MSC) was used to build calibration model. Fruits were stored in three storage temperature i.e. 8°C, 13°C, and 29°C. Spectra of fruit were taken directly after stored in cold condition and after immersed in a water bath at 30°C to obtain normal temperature. Calibration models were built using cold temperature spectra at 8°C and 13°C and normal temperature spectra at 8°C, 13°C, and 29°C.Determination of calibration coefficient (R²c) of fruits measured in cold condition after stored at 8°C and 13°C were 0.89 and 0.87 obtained using MSC spectra. R²c of fruits measured after submersed in a water-bath after stored at 8°C and 13°C were 0.88 and 0.87 obtained using detrending and MSC spectra. Moreover, R²c of fruit stored in room temperature of 29°C was 0.92 obtained using mean normalization spectra. In general, PLSR models for determination malic acid of sapodilla were not significantly different between spectra of fruits which were cold and were heated to normal temperature. However, the PLSR model was the highest for fruits stored in room temperature (29°C). The results showed the potency of VisNIR spectroscopy for malic acid determination of sapodilla. Moreover, the result also showed that storage temperature and fruit temperature affected PLSR models developed using VisNIR spectroscopy.

Rapid Determination of Phosphogypsum in Soil Based by Infrared (IR) and Near-Infrared (NIR) Spectroscopy with Multivariate Calibration

The application and accumulation of phosphogypsum (PG) may cause soil pollution, so it is of significance to establish a rapid method for its determination in soil. In this study, the feasibility of quantifying PG in soil by multivariate calibration combined with portable near-infrared spectroscopy (NIR) and infrared spectroscopy (IR) was investigated. In order to obtain better accuracy, standard normal variable (SNV) and Savitzky-Golay smoothing were employed as the pretreatment methods for IR and NIR, respectively. The competitive adaptive reweighted sampling (CARS) algorithm was used for variable optimization of these models. The results show that the predictive determination coefficient and root mean square error of prediction (RMSEP) of IR and NIR partial least squares (PLS) models were 0.9933 and 1.88% and 0.8830 and 6.55%. The limits of detection (LOD) for the models were 4.0006% and 14.225%. The reproducibility of the models is satisfactory with good accuracy and precision. In addition, extreme learning machine (ELM) and support vector machine (SVM) algorithms were also used to analyze the data, resulting in similar outcomes to those obtained by PLS. The results of a dual t test demonstrated that there is no significant difference between these methods and the standard procedure (GB/T 23456-2018) at the 95% confidence level. However, the reported protocols have the advantages of on-site analysis, speed, and convenience for the determination of phosphogypsum in soil.

Rapid determination of chemical compositions in chicken flesh by mining hyperspectral data

Hyperspectral data in 900–1700 nm range was mined for rapid and non-destructive determination of chicken chemical compositions. Hyperspectral images of chicken flesh samples were acquired and spectral data within the hyperspectral images were extracted, preprocessed to relate to moisture, protein and ash contents by partial least squares (PLS). The results showed that PLS model built with Savitzky-Golay convolution smoothing (SGCS) spectra (SGCS-PLS model), RAW spectra (RAW-PLS model), normalization (NOR) spectra (NOR-PLS model) had the best performance in predicting moisture (RP = 0.925, RMSEP = 0.391%), protein (RP = 0.926, RMSEP = 0.589%) and ash (RP = 0.938, RMSEP = 0.114%) contents, respectively. Four different methods including regression coefficients (RC), stepwise regression (SR), successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) were then applied to select optimal wavelengths for simplifying the original PLS models. As a result, 23 and 15 optimal wavelengths were respectively selected by CARS method from SGCS spectra (for moisture) and NOR spectra (for ash) and the original PLS models were optimized (CARS-SGCS-PLS model, CARS-NOR-PLS model) with RP of 0.932, 0.932 and RMSEP of 0.376%, 0.120%, respectively. Thirteen optimal wavelengths were selected by RC method from RAW spectra (for protein) and RC-RAW-PLS model was constructed with RP of 0.923 and RMSEP of 0.588%. F test and t test results further verified the statistical soundness of the three best optimized models. The chemical maps of moisture, protein and ash were finally generated by transferring the models into each pixel of images of chicken samples to visualize the chemical distribution. The overall study indicated that hyperspectral data combined with PLS algorithm could be potentially used for predicting the chemical compositions of chicken flesh.

Selection of characteristic wavelengths using SMA for laser induced fluorescence spectroscopy of power transformer oil

As the core component of the power system, the accurate analysis of its state and fault type is very important for the maintenance and repair of the transformer. The detection method represented by the transformer oil dissolved gas has the disadvantages of complicated processing steps and high operation requirements. Here, laser induced fluorescence (LIF) spectroscopy was applied for the analysis of transformer oil. Specifically, the slime mould algorithm (SMA) was used to select the characteristic wavelengths of the transformer oil fluorescence spectrum, and on this basis, a transformer fault diagnosis model was constructed. First, samples of transformer oil in different states were collected, and the fluorescence spectrum of the transformer oil was obtained with the help of the LIF acquisition system. Then, different spectral pretreatments were performed on the original fluorescence spectra, and it was found that the pretreatment effect of Savitzky-Golay smoothing (SG) was the best. Then, SMA was used to screen the characteristic wavelengths of the fluorescence spectrum, and 137 characteristic wavelengths were screened out to realize the accurate identification of the fluorescence spectrum of the transformer oil. In addition, the advantages of SMA for feature wavelength screening of transformer oil fluorescence spectra were demonstrated by comparing with traditional feature extraction strategies using principal components analysis (PCA). The research results show that it is effective to use SMA to screen the characteristic wavelengths of the LIF spectroscopy of transformer oil and use it for transformer fault diagnosis, which is of great significance for promoting the development of transformer fault diagnosis technology.

Rapid determination of acidity index of peanut during storage by a portable near-infrared spectroscopy system

In the process of peanut storage, the acidity index can be used as one of the important evaluation criteria of peanut storage characteristics. This study proposed a rapid detection method of acidity index of peanuts during storage based on a portable near-infrared (NIR) spectroscopy system. The portable spectroscopy system was built to collect the NIR spectra of peanuts during storage. The Savitzky-Golay (SG) smoothing combined with multiple scattering correction (MSC) was used to preprocess the raw spectra and normalize it. Three model population analysis-based (MPA-based) wavelength variable selection methods (namely: variable combination population analysis (VCPA), iterative retained information variable (IRIV) and (VCPA-IRIV) were employed comparatively to optimize the characteristics of the pre-treated spectra. And support vector machine (SVM) models were established based on optimized features to achieve rapid detection of acidity index of peanuts during storage. The results obtained showed that compared with the full-spectrum SVM model, the prediction performance of the SVM model based on optimized features has been improved. In addition, the VCPA-SVM model obtained the best prediction performance. The root mean square error (RMSEP) of the model was 0.61 g·kg−1, the coefficient of determination of the prediction set (RP2) was 0.95, and the residual predictive deviation (RPD) was 4.31. The overall results demonstrate that the portable NIR spectroscopy system can realize the rapid detection of the acidity index during peanut storage, and the VCPA algorithm can efficiently obtain the characteristic wavelengths of the NIR spectra of peanuts during storage.

A Method of Invasive Alien Plant Identification Based on Hyperspectral Images

Invasive alien plants (IAPs) are considered to be one of the greatest threats to global biodiversity and ecosystems. Timely and accurate detection technology is needed to identify these invasive plants, helping to mitigate the damage to farmland, fruit trees and woodland. Hyperspectral technology has the potential to identify similar species. However, the challenge remains to simultaneously identify multiple invasive alien plants with similar colors based on image data. The spectral images were collected by a hyperspectral camera with a spectral range of 450–998 nm, and the raw spectra were extracted by Cubert software. First derivative (FD), Savitzky-Golay (SG) smoothing and standard normal variate (SNV) were used to preprocess the raw spectral data, respectively. Then, on the basis of preprocessing, principal component analysis (PCA) and ant colony optimization (ACO) were used for feature dimensionality reduction, and the reduced features were used as input variables for later modeling. Finally, a combination of both dimensionality reduction and non-dimensionality reduction is used for identification using support vector machines (SVM) and random forests (RF). In order to determine the optimal recognition model, a total of 18 combinations of different preprocessing methods, dimensionality reduction methods and classifiers were tested. The results showed that a combination of SG smoothing and SVM achieved a total accuracy (A) of 89.36%, an average accuracy (AA) of 89.39% and an average precision (AP) of 89.54% with a test time of 0.2639 s. In contrast, the combination of SG smoothing, the ACO, and SVM resulted in weaker performance in terms of A (86.76%), AA (86.99%) and AP (87.22%), but with less test time (0.0567 s). The SG-SVM and SG-ACO-SVM models should be selected considering accuracy and time cost, respectively, for recognition of the seven IAPs and background in the wild.

Identification of foodborne pathogenic bacteria using confocal Raman microspectroscopy and chemometrics.

Rapid and accurate identification of foodborne pathogenic bacteria is of great importance because they are often responsible for the majority of serious foodborne illnesses. The confocal Raman microspectroscopy (CRM) is a fast and easy-to-use method known for its effectiveness in detecting and identifying microorganisms. This study demonstrates that CRM combined with chemometrics can serve as a rapid, reliable, and efficient method for the detection and identification of foodborne pathogenic bacteria without any laborious pre-treatments. Six important foodborne pathogenic bacteria including S. flexneri, L. monocytogenes, V. cholerae, S. aureus, S. typhimurium, and C. botulinum were investigated with CRM. These pathogenic bacteria can be differentiated based on several characteristic peaks and peak intensity ratio. Principal component analysis (PCA) was used for investigating the difference of various samples and reducing the dimensionality of the dataset. Performances of some classical classifiers were compared for bacterial detection and identification including decision tree (DT), artificial neural network (ANN), and Fisher's discriminant analysis (FDA). Correct recognition ratio (CRR), area under the receiver operating characteristic curve (ROC), cumulative gains, and lift charts were used to evaluate the performance of models. The impact of different pretreatment methods on the models was explored, and pretreatment methods include Savitzky-Golay algorithm smoothing (SG), standard normal variate (SNV), multivariate scatter correction (MSC), and Savitzky-Golay algorithm 1st Derivative (SG 1st Der). In the DT, ANN, and FDA model, FDA is more robust for overfitting problem and offers the highest accuracy. Most pretreatment methods raised the performance of the models except SNV. The results revealed that CRM coupled with chemometrics offers a powerful tool for the discrimination of foodborne pathogenic bacteria.

Origin identification of Gardeniae Fructus based on hyperspectral imaging technology

In order to realize rapid and non-destructive identification of the origin of Gardeniae Fructus, a technical method based on hyperspectral imaging technology was established in this study. Spectral information of Gardeniae Fructus samples from eight production origins was acquired from visible NIR(410-990 nm, VNIR) and short wavelength NIR(950-2 500 nm, SWIR) bands based on hyperspectral imaging techniques. The average spectral reflectance within the region of interest was extracted and calculated using the ENVI 5.3 software, resulting in 1 600 sample data. The visible short wavelength infrared band(fused bands) spectral data covering the range 410-2 500 nm were obtained after combining the spectral data of VNIR and SWIR. Data were de-noised by five common preprocessing methods, including multivariate scatter correction, Savitzky-Golay smoothing, standard normal variate, first derivative(FD), and second derivative from VNIR, SWIR, and fused bands(VNIR+SWIR). Partial least squares discriminant analysis, linear support vector classification(LinearSVC), and random forest were used to establish the model for origin identification of Gardeniae Fructus. The results indicated that the identification model of Gardeniae Fructus origin established after FD pretreatment of the spectral data in the fused bands could yield good results. According to the confusion matrix evaluation results, the model prediction set using LinearSVC reached 100% accuracy, so the optimum identification model of Gardeniae Fructus origin was determined as fusion bands-FD-LinearSVC. Therefore, the hyperspectral imaging technology can achieve rapid, nondestructive, and accurate identification of Gardeniae Fructus samples of different origins, which provides a technical reference for the differential detection of Gardeniae Fructus and other Chinese medicines.

Rapid detection of yeast growth status based on molecular spectroscopy fusion (MSF) technique

This work innovatively proposes a novel method for quantitative detection of yeast growth status based on molecular spectroscopy fusion (MSF) technique. First, the Raman spectra and near-infrared (NIR) spectra of the samples during the yeast culture process were collected by spectrometers, and the raw spectra were respectively preprocessed using Savitzky-Golay (SG) smoothing + standard normal variate (SNV). Then, the two kinds of molecular spectra after preprocessing were respectively optimized for characteristic wavelength using variable combination population analysis (VCPA), and feature fusion was performed on the feature layer. Finally, support vector machine (SVM) models based on the fusion features were established to achieve quantitative detection of yeast growth status. The experimental results showed that, compared with the best VCPA-SVM model based on single-molecule spectral features, the best VCPA-SVM model based on the fusion features could obtain better prediction performance. The root mean square error of prediction (RMSEP), coefficient of determination (RP2) and relative percent deviation (RPD) of the best model were 0.47, 0.98, and 6.69, respectively. The results obtained reveal that the MSF technique can effectively improve the detection accuracy of yeast growth status; in addition, the VCPA method has a certain potential in feature wavelength mining, which can effectively reduce the dimensionality of fusion features.