Classification of oolong tea varieties based on hyperspectral imaging technology and BOSS‐LightGBM model

Online small-object anti-fringe sorting of tobacco stem impurities based on hyperspectral superpixels

The use of tobacco stems as raw material for cigarettes reduces cost and improves the flammability of cigarettes. However, various impurities, such as plastic, reduce the purity of tobacco stems, degrade the quality of cigarettes, and endanger the health of smokers. Therefore, the correct classification of tobacco stems and impurities is crucial. This study proposes a method based on hyperspectral image superpixels and the use of light gradient boosting machine (LightGBM) classifier to categorize tobacco stems and impurities. First, the hyperspectral image is segmented using superpixels. Second, the gray-level co-occurrence matrix extracts the texture features of superpixels. Subsequently, an improved LightGBM is applied and trained with the spectral and textural features of superpixels as a classification model. Several experiments were implemented to evaluate the performance of the proposed method. The results show that the classification performance based on superpixels is better than that based on single-pixel points. The classification model based on superpixels (10 × 10 px) achieved the highest impurity recognition rate (93.8%). This algorithm has already been applied to industrial production in cigarette factories. It exhibits considerable potential in overcoming the influence of interference fringes to promote the intelligent industrial application of hyperspectral imaging.

Rapid detection of sunset yellow adulteration in tea powder with variable selection coupled to machine learning tools using spectral data

In the present study sunset yellow (SY), a synthetic colour, which is a common adulterant in tea powders has been analysed using FT-IR spectral data coupled to machine learning tools for efficient classification and quantification of the SY adulteration. Earlier established real coded genetic algorithm (RCGA) was used as variable selection method to predict the key fingerprints of SY in the FT-IR spectra. Here, RCGA was used to select 20, 30, 40, 50 and 60 characteristic wavenumbers for SY. Classification was carried using support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGB) classifiers. SVM classifier using 50 variables could give an accuracy of 0.90 amongst the three. Quantification of SY based on PLS (partial least squares), LS-SVM (least squares-SVM), RF and XGBoost were built on characteristic wavenumbers. Both RF and LS-SVM models were observed to be superior to PLS when coupled to RCGA obtained 20 fingerprint variables. Overall, RCGA-LS-SVM model resulted in lowest RMSECV (0.1956) with regression co-efficient values RC 2 = 0.9989 and RP 2 = 0.9979, when 50 fingerprint variables were used. These results demonstrated that FT-IR combined with RCGA-LS-SVM procedure could be a robust technique for rapid detection of SY in tea powder.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13197-023-05694-3.

Dissection of Hyperspectral Reflectance to Estimate Photosynthetic Characteristics in Upland Cotton (Gossypium hirsutum L.) under Different Nitrogen Fertilizer Application Based on Machine Learning Algorithms

Hyperspectral technology has enabled rapid and efficient nitrogen monitoring in crops. However, most approaches involve direct monitoring of nitrogen content or physiological and biochemical indicators directly related to nitrogen, which cannot reflect the overall plant nutritional status. Two important photosynthetic traits, the fraction of absorbed photosynthetically active radiation (FAPAR) and the net photosynthetic rate (Pn), were previously shown to respond positively to nitrogen changes. Here, Pn and FAPAR were used for correlation analysis with hyperspectral data to establish a relationship between nitrogen status and hyperspectral characteristics through photosynthetic traits. Using principal component and band autocorrelation analyses of the original spectral reflectance, two band positions (350-450 and 600-750 nm) sensitive to nitrogen changes were obtained. The performances of four machine learning algorithm models based on six forms of hyperspectral transformations showed that the light gradient boosting machine (LightGBM) model based on the hyperspectral first derivative could better invert the Pn of function-leaves in cotton, and the random forest (RF) model based on hyperspectral first derivative could better invert the FAPAR of the cotton canopy. These results provide advanced metrics for non-destructive tracking of cotton nitrogen status, which can be used to diagnose nitrogen nutrition and cotton growth status in large farms.

A machine learning approach for predicting suicidal ideation in post stroke patients

Currently, the identification of stroke patients with an increased suicide risk is mainly based on self‐report questionnaires, and this method suffers from a lack of objectivity. This study developed and validated a suicide ideation (SI) prediction model using clinical data and identified SI predictors. Significant variables were selected through traditional statistical analysis based on retrospective data of 385 stroke patients; the data were collected from October 2012 to March 2014. The data were then applied to three boosting models (Xgboost, CatBoost, and LGBM) to identify the comparative and best performing models. Demographic variables that showed significant differences between the two groups were age, onset, type, socioeconomic, and education level. Additionally, functional variables also showed a significant difference with regard to ADL and emotion (p < 0.05). The CatBoost model (0.900) showed higher performance than the other two models; and depression, anxiety, self-efficacy, and rehabilitation motivation were found to have high importance. Negative emotions such as depression and anxiety showed a positive relationship with SI and rehabilitation motivation and self-efficacy displayed an inverse relationship with SI. Machine learning-based SI models could augment SI prevention by helping rehabilitation and medical professionals identify high-risk stroke patients in need of SI prevention intervention.

Distinguishing Different Varieties of Oolong Tea by Fluorescence Hyperspectral Technology Combined with Chemometrics

Oolong tea is a semi-fermented tea that is popular among people. This study aims to establish a classification method for oolong tea based on fluorescence hyperspectral technology(FHSI) combined with chemometrics. First, the spectral data of Tieguanyin, Benshan, Maoxie and Huangjingui were obtained. Then, standard normal variation (SNV) and multiple scatter correction (MSC) were used for preprocessing. Principal component analysis (PCA) was used for data visualization, and with tolerance ellipses that were drawn according to Hotelling, outliers in the spectra were removed. Variable importance for the projection (VIP) > 1 in partial least squares discriminant analysis (PLS−DA) was used for feature selection. Finally, the processed spectral data was entered into the support vector machine (SVM) and PLS−DA. MSC_VIP_PLS−DA was the best model for the classification of oolong tea. The results showed that the use of FHSI could accurately distinguish these four types of oolong tea and was able to identify the key wavelengths affecting the tea classification, which were 650.11, 660.29, 665.39, 675.6, 701.17, 706.31, 742.34 and 747.5 nm. In these wavelengths, different kinds of tea have significant differences (p < 0.05). This study could provide a non-destructive and rapid method for future tea identification.

The Rapid Non-Destructive Detection of Adulteration and Its Degree of Tieguanyin by Fluorescence Hyperspectral Technology

Tieguanyin is one of the top ten most popular teas and the representative of oolong tea in China. In this study, a rapid and non-destructive method is developed to detect adulterated tea and its degree. Benshan is used as the adulterated tea, which is about 0%, 10%, 20%, 30%, 40%, and 50% of the total weight of tea samples, mixed with Tieguanyin. Taking the fluorescence spectra from 475 to 1000 nm, we then established the 2-and 6-class discriminant models. The 2-class discriminant models had the best evaluation index when using SG-CARS-SVM, which can reach a 100.00% overall accuracy, 100.00% specificity, 100% sensitivity, and the least time was 1.2088 s, which can accurately identify pure and adulterated tea; among the 6-class discriminant models (0% (pure Tieguanyin), 10, 20, 30, 40, and 50%), with the increasing difficulty of adulteration, SNV-RF-SVM had the best evaluation index, the highest overall accuracy reached 94.27%, and the least time was 0.00698 s. In general, the results indicated that the two classification methods explored in this study can obtain the best effects. The fluorescence hyperspectral technology has a broad scope and feasibility in the non-destructive detection of adulterated tea and other fields.

Rapid Identification of Different Grades of Huangshan Maofeng Tea Using Ultraviolet Spectrum and Color Difference

Tea is an important beverage in humans’ daily lives. For a long time, tea grade identification relied on sensory evaluation, which requires professional knowledge, so is difficult and troublesome for laypersons. Tea chemical component detection usually involves a series of procedures and multiple steps to obtain the final results. As such, a simple, rapid, and reliable method to judge the quality of tea is needed. Here, we propose a quick method that combines ultraviolet (UV) spectra and color difference to classify tea. The operations are simple and do not involve complex pretreatment. Each method requires only a few seconds for sample detection. In this study, famous Chinese green tea, Huangshan Maofeng, was selected. The traditional detection results of tea chemical components could not be used to directly determine tea grade. Then, digital instrument methods, UV spectrometry and colorimetry, were applied. The principal component analysis (PCA) plots of the single and combined signals of these two instruments showed that samples could be arranged according to grade. The combined signal PCA plot performed better with the sample grade descending in clockwise order. For grade prediction, the random forest (RF) model produced a better effect than the support vector machine (SVM) and the SVM + RF model. In the RF model, the training and testing accuracies of the combined signal were all 1. The grades of all samples were correctly predicted. From the above, the UV spectrum combined with color difference can be used to quickly and accurately classify the grade of Huangshan Maofeng tea. This method considerably increases the convenience of tea grade identification.

Rapid and Nondestructive Discrimination of Geographical Origins of Longjing Tea using Hyperspectral Imaging at Two Spectral Ranges Coupled with Machine Learning Methods

Longjing tea is one of China’s protected geographical indication products with high commercial and nutritional value. The geographical origin of Longjing tea is an important factor influencing its commercial and nutritional value. Hyperspectral imaging systems covering the two spectral ranges of 380–1030 nm and 874–1734 nm were used to identify a single tea leaf of Longjing tea from six geographical origins. Principal component analysis (PCA) was conducted on hyperspectral images to form PCA score images. Differences among samples from different geographical origins were visually observed from the PCA score images. Support vector machine (SVM) and partial least squares discriminant analysis (PLS-DA) models were built using the full spectra at the two spectral ranges. Decent classification performances were obtained at the two spectral ranges, with the overall classification accuracy of the calibration and prediction sets over 84%. Furthermore, prediction maps for geographical origins identification of Longjing tea were obtained by applying the SVM models on the hyperspectral images. The overall results illustrate that hyperspectral imaging at both spectral ranges can be applied to identify the geographical origin of single tea leaves of Longjing tea. This study provides a new, rapid, and non-destructive alternative for Longjing tea geographical origins identification.