Hyperspectral imaging covering the spectral range of 874–1734 nm was used to determine caffeine content of coffee beans. Spectral data of 958.24–1628.89 nm were extracted and preprocessed. Partial least squares regression (PLSR) model on the preprocessed full spectra obtained good performance with coefficient of determination of prediction (R2p) of 0.843 and root mean square error of prediction (RMSEP) of 131.904 μg/g. In addition, 10 variable selection methods were applied to select the best optimal wavelengths. The PLSR models on the different optimal wavelengths obtained satisfactory results. The PLSR model on the wavelengths selected by random frog (RF) performed the best, with R2p of 0.878 and RMSEP of 116.327 μg/g. The RF wavelength selection combined with the PLSR model also achieved satisfactory visualization of caffeine content between different coffee beans. The overall results indicated that optimal wavelength selection was an efficient method for spectral data preprocessing, and hyperspectral imaging was illustrated as a potential technique for real-time online determination for caffeine content of coffee beans.

•Hyperspectral imaging was successfully used to measure spinach pigments content.•Optimal wavelengths selected by a new random frog algorithm were proved efficient.•Visualization of pigments distribution of spinach leaf were analyzed.•The method had the potential to track changes of quality of vegetables for real-world application.Hyperspectral imaging covering spectral range of 874–1734 nm was used to measure spinach leaf pigments content (chlorophyll-a (Chla), chlorophyll-b (Chlb), total chlorophyll (tChl), carotenoids (Car)) under storage of 20 °C (Sample set 1) and 4 °C (Sample set 2). A sample set combining the two sample sets was formed, partial least squares (PLS) models on full spectra obtained acceptable results for all sample sets with correlation coefficient of prediction (rp) near or over 0.8. Random frog was used to select 20, 20, 20, 22 optimal wavelengths for Chla, Chlb, tChl and Car from the combined sample set, respectively. PLS models on optimal wavelengths obtained better results than corresponding full spectra PLS models. The visualization of the distribution map of pigments content were acquired by applying the PLS models on pixels within the hyperspectral image. The overall results indicated that hyperspectral imaging could be used for spinach leaf pigments content measurement, providing an alternative for real-world on-line vegetables quality monitor.

•We reviewed the commonly used LIBS instruments in agriculture.•Some signal enhancement methods were introduced to improve LIBS performance.•Calibration methods were introduced for quantitative analysis.•Recent applications of LIBS were reviewed in soil, plants, agricultural products and food.Toxic metal contamination and nutritious elements detection are two main issues in agriculture, as these relate to the development of agriculture and human health. Among the investigated techniques, laser-induced breakdown spectroscopy (LIBS) has the potential to become a fast and effective analytical tool for the application in agriculture. Herein is a review of the recent developments and applications of LIBS in the field of agriculture. We discussed the LIBS instruments and quantitative analytical methods, and introduced signal enhancement methods for expanding the elements detection capability. For detailed aspects of applications, we reviewed the recent progress in soil, plants, agricultural products and food. To solve the severe “matrix effect” problem and to meet high demands in agriculture, we recommended the development of robust and practical LIBS instruments, exploiting the chemometric methods and signal enhancement methods for quantitative analysis.

Visible and near-infrared (VIS/NIR) spectroscopy combined with least squares support vector machine (LS-SVM) was employed to determine soluble solid contents (SSC) and pH of white vinegars. Three hundred twenty vinegar samples were distributed into a calibration set (240 samples) and a validation set (80 samples). Partial least squares (PLS) analysis was implemented for the regression model and extraction of latent variables (LVs). The selected LVs were used as LS-SVM input variables. Finally, LS-SVM models with radial basis function kernel were achieved with the comparison of PLS models. The results indicated that LS-SVM outperformed PLS models. The correlation coefficient (r), root mean square error of prediction, bias, and residual prediction deviation for the validation set were 0.988, 0.207°Brix, 0.183, and 6.4 for SSC whereas these were 0.988, 0.041, −0.002, and 6.5 for pH, respectively. The overall results indicated that VIS/NIR spectroscopy and LS-SVM could be used as a rapid alternative method for the prediction of SSC and pH of white vinegars, and the results could be helpful for the fermentation process and quality control monitoring of white vinegar production.

•Hyperspectral imaging was used for fast detection of POD activity in tomato leaves.•21 optimal wavelengths were selected by GA-PLS.•Five different calibration models were developed for a better prediction performance.Tomatoes are cultivated around the world and gray mold is one of its most prominent and destructive diseases. An early disease detection method can decrease losses caused by plant diseases and prevent the spread of diseases. The activity of peroxidase (POD) is very important indicator of disease stress for plants. The objective of this study is to examine the possibility of fast detection of POD activity in tomato leaves which infected with Botrytis cinerea using hyperspectral imaging data. Five pre-treatment methods were investigated. Genetic algorithm-partial least squares (GA-PLS) was applied to select optimal wavelengths. A new fast learning neural algorithm named extreme learning machine (ELM) was employed as multivariate analytical tool in this study. 21 optimal wavelengths were selected by GA-PLS and used as inputs of three calibration models. The optimal prediction result was achieved by ELM model with selected wavelengths, and the r and RMSEP in validation were 0.8647 and 465.9880 respectively. The results indicated that hyperspectral imaging could be considered as a valuable tool for POD activity prediction. The selected wavelengths could be potential resources for instrument development.Graphical abstract

Oilseed rape is used as both food and a renewable energy resource. Physiological parameters, such as the amino acid aspartic acid, can indicate the growth status of oilseed rape. Traditional detection methods are laborious, time consuming, costly, and not usable in the field. Here, we investigate near infrared spectroscopy (NIRS) as a fast and non-destructive detection method of aspartic acid in oilseed rape leaves under herbicide stress. Different spectral pre-processing methods were compared for optimal prediction performance. The variable selection methods were applied for relevant variable selection, including successive projections algorithm (SPA), Monte Carlo-uninformative variable elimination (MC-UVE) and random frog (RF). The selected effective wavelengths (EWs) were used as input by multiple linear regression (MLR), partial least squares (PLS) and least-square support vector machine (LS-SVM). The best predictive performance was achieved by SPA-LS-SVM (Raw) model using 22 EWs, and the prediction results were Rp = 0.9962 and RMSEP = 0.0339 for the prediction set. The result indicated that NIR combined with LS-SVM is a powerful new method to detect aspartic acid in oilseed rape leaves under herbicide stress.