Determination and Visualization of pH Values in Anaerobic Digestion of Water Hyacinth and Rice Straw Mixtures Using Hyperspectral Imaging with Wavelet Transform Denoising and Variable Selection

Prediction of chemical indicators for quality of Zanthoxylum spices from multi-regions using hyperspectral imaging combined with chemometrics

Fruits of Zanthoxylum bungeanum Maxim (Red “Huajiao,” RHJ) and Z. schinifolium Sieb. et Zucc. (Green “Huajiao,” GHJ) are famous spices around the world. Antioxidant capability (AOC), total alkylamides content (TALC) and volatile oil content (VOC) in HJ are three important quality indicators and lack rapid and effective methods for detection. Non-destructive, time-saving, and effective technology of hyperspectral imaging (HSI) combined with chemometrics was adopted to improve the indicators prediction in this study. Results showed that the three chemical indexes exhibited significant differences between different regions and varieties (P < 0.05). Specifically, the mass percentages of TALC were 11–22% in RHJ group and 21–36% in GHJ group. The mass percentages of VOC content were 23–31% and 16–24% in RHJ and GHJ groups, respectively. More importantly, these indicators could be well predicted based on the full or effective HSI wavelengths via model adaptive space shrinkage (MASS) and iteratively variable subset optimization (IVSO) selections combined with wavelet transform (WT) method for noise reduction. The best prediction results of AOC, TALC, and VOC indicators were achieved with the highest residual predictive deviation (RPD) values of 7.43, 7.82, and 3.73 for RHJ, respectively, and 6.82, 2.66, and 4.64 for GHJ, respectively. The above results highlight the great potential of HSI assisted with chemometrics in the rapid and effective prediction of chemical indicators of Zanthoxylum spices.

Technical workflows for hyperspectral plant image assessment and processing on the greenhouse and laboratory scale

Background

The use of hyperspectral cameras is well established in the field of plant phenotyping, especially as a part of high-throughput routines in greenhouses. Nevertheless, the workflows used differ depending on the applied camera, the plants being imaged, the experience of the users, and the measurement set-up.

Results

This review describes a general workflow for the assessment and processing of hyperspectral plant data at greenhouse and laboratory scale. Aiming at a detailed description of possible error sources, a comprehensive literature review of possibilities to overcome these errors and influences is provided. The processing of hyperspectral data of plants starting from the hardware sensor calibration, the software processing steps to overcome sensor inaccuracies, and the preparation for machine learning is shown and described in detail. Furthermore, plant traits extracted from spectral hypercubes are categorized to standardize the terms used when describing hyperspectral traits in plant phenotyping. A scientific data perspective is introduced covering information for canopy, single organs, plant development, and also combined traits coming from spectral and 3D measuring devices.

Conclusions

This publication provides a structured overview on implementing hyperspectral imaging into biological studies at greenhouse and laboratory scale. Workflows have been categorized to define a trait-level scale according to their metrological level and the processing complexity. A general workflow is shown to outline procedures and requirements to provide fully calibrated data of the highest quality. This is essential for differentiation of the smallest changes from hyperspectral reflectance of plants, to track and trace hyperspectral development as an answer to biotic or abiotic stresses.

Quantitative Analysis of Soil Total Nitrogen Using Hyperspectral Imaging Technology with Extreme Learning Machine

Soil nutrient detection is important for precise fertilization. A total of 150 soil samples were picked from Lishui City. In this work, the total nitrogen (TN) content in soil samples was detected in the spectral range of 900-1700 nm using a hyperspectral imaging (HSI) system. Characteristic wavelengths were extracted using uninformative variable elimination (UVE) and the successive projections algorithm (SPA), separately. Partial least squares (PLS) and extreme learning machine (ELM) were used to establish the calibration models with full spectra and characteristic wavelengths, respectively. The results indicated that the prediction effect of the nonlinear ELM model was superior to the linear PLS model. In addition, the models using the characteristic wavelengths could also achieve good results, and the UVE-ELM model performed better, having a correlation coefficient of prediction (r_p), root-mean-square error of prediction (RMSEP), and residual prediction deviation (RPD) of 0.9408, 0.0075, and 2.97, respectively. The UVE-ELM model was then used to estimate the TN content in the soil sample and obtain a distribution map. The research results indicate that HSI can be used for the detection and visualization of the distribution of TN content in soil, providing a basis for future large-scale monitoring of soil nutrient distribution and rational fertilization.

Variety Identification of Orchids Using Fourier Transform Infrared Spectroscopy Combined with Stacked Sparse Auto-Encoder

The feasibility of using the fourier transform infrared (FTIR) spectroscopic technique with a stacked sparse auto-encoder (SSAE) to identify orchid varieties was studied. Spectral data of 13 orchids varieties covering the spectral range of 4000-550 cm^-1 were acquired to establish discriminant models and to select optimal spectral variables. K nearest neighbors (KNN), support vector machine (SVM), and SSAE models were built using full spectra. The SSAE model performed better than the KNN and SVM models and obtained a classification accuracy 99.4% in the calibration set and 97.9% in the prediction set. Then, three algorithms, principal component analysis loading (PCA-loading), competitive adaptive reweighted sampling (CARS), and stacked sparse auto-encoder guided backward (SSAE-GB), were used to select 39, 300, and 38 optimal wavenumbers, respectively. The KNN and SVM models were built based on optimal wavenumbers. Most of the optimal wavenumbers-based models performed slightly better than the all wavenumbers-based models. The performance of the SSAE-GB was better than the other two from the perspective of the accuracy of the discriminant models and the number of optimal wavenumbers. The results of this study showed that the FTIR spectroscopic technique combined with the SSAE algorithm could be adopted in the identification of the orchid varieties.

A Compact Ultrawideband Antenna Based on Hexagonal Split-Ring Resonator for pH Sensor Application

A compact ultrawideband (UWB) antenna based on a hexagonal split-ring resonator (HSRR) is presented in this paper for sensing the pH factor. The modified HSRR is a new concept regarding the conventional square split-ring resonator (SSRR). Two HSRRs are interconnected with a strip line and a split in one HSRR is introduced to increase the electrical length and coupling effect. The presented UWB antenna consists of three unit cells on top of the radiating patch element. This combination of UWB antenna and HSRR gives double-negative characteristics which increase the sensitivity of the UWB antenna for the pH sensor. The proposed ultrawideband antenna metamaterial sensor was designed and fabricated on FR-4 substrate. The electrical length of the proposed metamaterial antenna sensor is 0.238 × 0.194 × 0.016 λ, where λ is the lowest frequency of 3 GHz. The fractional bandwidth and bandwidth dimension ratio were achieved with the metamaterial-inspired antenna as 146.91% and 3183.05, respectively. The operating frequency of this antenna sensor covers the bandwidth of 17 GHz, starting from 3 to 20 GHz with a realized gain of 3.88 dB. The proposed HSRR-based ultrawideband antenna sensor is found to reach high gain and bandwidth while maintaining the smallest electrical size, a highly desired property for pH-sensing applications.

Application of Hyperspectral Imaging to Detect Sclerotinia sclerotiorum on Oilseed Rape Stems

Hyperspectral imaging covering the spectral range of 384-1034 nm combined with chemometric methods was used to detect Sclerotinia sclerotiorum (SS) on oilseed rape stems by two sample sets (60 healthy and 60 infected stems for each set). Second derivative spectra and PCA loadings were used to select the optimal wavelengths. Discriminant models were built and compared to detect SS on oilseed rape stems, including partial least squares-discriminant analysis, radial basis function neural network, support vector machine and extreme learning machine. The discriminant models using full spectra and optimal wavelengths showed good performance with classification accuracies of over 80% for the calibration and prediction set. Comparing all developed models, the optimal classification accuracies of the calibration and prediction set were over 90%. The similarity of selected optimal wavelengths also indicated the feasibility of using hyperspectral imaging to detect SS on oilseed rape stems. The results indicated that hyperspectral imaging could be used as a fast, non-destructive and reliable technique to detect plant diseases on stems.

Key Variables Screening of Near-Infrared Models for Simultaneous Determination of Quality Parameters in Traditional Chinese Food “Fuzhu”

The traditional Chinese food Fuzhu is a dried soy protein-lipid film formed during the heating of soymilk. This study investigates whether a simple and accurate model can nondestructively determine the quality parameters of intact Fuzhu. The diffused reflectance spectra (1000–2499 nm) of intact Fuzhu were collected by a commercial near-infrared (NIR) spectrometer. Among various preprocessing methods, the derivative by wavelet transform method optimally enhanced the characteristic signals of Fuzhu spectra. Uninformative variable elimination based on Monte Carlo (MC-UVE), random frog (RF), and competitive adaptive reweighted sampling (CARS) were proposed to select key variables for partial least squares (PLS) calculation. The strong performance of the developed models is attributed to the high ratios of prediction to deviation values (3.32–3.51 for protein, 3.62–3.89 for lipid, and 4.27–4.55 for moisture). The prediction set was used to assess the performances of the best models of protein (CARS-PLS), lipid (RF-PLS), and moisture (CARS-PLS), which resulted in greater coefficients of determination of 0.958, 0.966, and 0.976, respectively, and lower root mean square errors of prediction of 0.656%, 0.442%, and 0.123%, respectively. Combined with chemometrics methods, the NIR technique is promising for simultaneous testing of quality parameters of intact Fuzhu.

Fast Detection of Striped Stem-Borer (Chilo suppressalis Walker) Infested Rice Seedling Based on Visible/Near-Infrared Hyperspectral Imaging System

Striped stem-borer (SSB) infestation is one of the most serious sources of damage to rice growth. A rapid and non-destructive method of early SSB detection is essential for rice-growth protection. In this study, hyperspectral imaging combined with chemometrics was used to detect early SSB infestation in rice and identify the degree of infestation (DI). Visible/near-infrared hyperspectral images (in the spectral range of 380 nm to 1030 nm) were taken of the healthy rice plants and infested rice plants by SSB for 2, 4, 6, 8 and 10 days. A total of 17 characteristic wavelengths were selected from the spectral data extracted from the hyperspectral images by the successive projection algorithm (SPA). Principal component analysis (PCA) was applied to the hyperspectral images, and 16 textural features based on the gray-level co-occurrence matrix (GLCM) were extracted from the first two principal component (PC) images. A back-propagation neural network (BPNN) was used to establish infestation degree evaluation models based on full spectra, characteristic wavelengths, textural features and features fusion, respectively. BPNN models based on a fusion of characteristic wavelengths and textural features achieved the best performance, with classification accuracy of calibration and prediction sets over 95%. The accuracy of each infestation degree was satisfactory, and the accuracy of rice samples infested for 2 days was slightly low. In all, this study indicated the feasibility of hyperspectral imaging techniques to detect early SSB infestation and identify degrees of infestation.