An application to analyzing and correcting for the effects of irregular topographies on NIR hyperspectral images to improve identification of moldy peanuts

Optical absorption enhancement in inhomogeneous InGaN nanowire arrays photocathode

In the development of surface structures, nanowire arrays (NWAS) have been widely studied because of their trapping effect. In this paper, the finite difference time domain (FDTD) method is used to simulate homogeneous and inhomogeneous NWAS. We studied the influence of the structural parameters of InGaN NWAS and inhomogeneous arrays on optical response properties. The optical response includes light absorptivity and cutoff wavelength sensitivity. The simulation results show that the inhomogeneous NWAS can increase the effective transmission distance of light on the surface, thus greatly improving the optical absorption capacity of InGaN NWAS. We can obtain high sensitivity of cut-off wavelength by adjusting the structural parameters of the side nanowires. We find that by reducing the diameters and heights of the side nanowires, a higher light absorption rate can be obtained, which is a 5% improvement compared to uniform NWAS. Therefore, the research in this paper can provide some theoretical reference for the experiment and preparation of InGaN photocathodes.

Nonlinearity parameter in the pathlength dimension to improve the scattering in the transmission spectra

In spectrochemical quantitative analysis of solutions containing scattering components, the spectral nonlinearity caused by scattering seriously affects the prediction accuracy, robustness, and even feasibility of the models. Unlike the traditional methods (modeling with the spectra data of single pathlength) of approximating the nonlinear spectral line to linear to reduce the nonlinear features of scattering, a new method is proposed to reduce the effect of scattering by taking advantage of the nonlinear characteristics of spectral lines. First, the logarithmic function is used to fit the attenuation of multiple pathlengths, then the regression coefficient of the function is taken as the characteristic parameter of scattering, and the wavelengths with smaller characteristic parameter are selected as the modeling wavelengths. The model is robust and insensitive to the effect of scattering. The experiment involving a variety of scattering cases containing intralipids and ink was taken to verify the method. An F-test of the experimental results was significant at the 0.05 level. The root mean square error of prediction of the new method was 1.94%, and the prediction accuracy was 75.5% higher than that of the traditional model. The new method provides a novel approach toward describing the spectral nonlinearity with a function.

Identification of Moldy Peanuts under Different Varieties and Moisture Content Using Hyperspectral Imaging and Data Augmentation Technologies

Aflatoxins in moldy peanuts are seriously toxic to humans. These kernels need to be screened in the production process. Hyperspectral imaging techniques can be used to identify moldy peanuts. However, the changes in spectral information and texture information caused by the difference in moisture content in peanuts will affect the identification accuracy. To reduce and eliminate the influence of this factor, a data augmentation method based on interpolation was proposed to improve the generalization ability and robustness of the model. Firstly, the near-infrared hyperspectral images of 5 varieties, 4 classes, and 3 moisture content gradients with 39,119 kernels were collected. Then, the data augmentation method called the difference of spectral mean (DSM) was constructed. K-nearest neighbors (KNN), support vector machines (SVM), and MobileViT-xs models were used to verify the effectiveness of the data augmentation method on data with two gradients and three gradients. The experimental results show that the data augmentation can effectively reduce the influence of the difference in moisture content on the model identification accuracy. The DSM method has the highest accuracy improvement in 5 varieties of peanut datasets. In particular, the accuracy of KNN, SVM, and MobileViT-xs using the data of two gradients was improved by 3.55%, 4.42%, and 5.9%, respectively. Furthermore, this study provides a new method for improving the identification accuracy of moldy peanuts and also provides a reference basis for the screening of related foods such as corn, orange, and mango.

Research advancements in optical imaging and spectroscopic techniques for nondestructive detection of mold infection and mycotoxins in cereal grains and nuts

Cereal grains and nuts are represented as the economic backbone of many developed and developing countries. Kernels of cereal grains and nuts are prone to mold infection under high relative humidity and suitable temperature conditions in the field as well as storage conditions. Health risks caused by molds and their molecular metabolite mycotoxins are, therefore, important topics to investigate. Strict regulations have been developed by international trade regulatory bodies for the detection of mold growth and mycotoxin contamination across the food chain starting from the harvest to storage and consumption. Molds and aflatoxins are not evenly distributed over the bulk of grains, thus appropriate sampling for detection and quantification is crucial. Existing reference methods for mold and mycotoxin detection are destructive in nature as well as involve skilled labor and hazardous chemicals. Also, these methods cannot be used for inline sorting of the infected kernels. Thus, analytical methods have been extensively researched to develop the one that is more practical to be used in commercial detection and sorting processes. Among various analytical techniques, optical imaging and spectroscopic techniques are attracting growers' attention for their potential of nondestructive and rapid inline identification and quantification of molds and mycotoxins in various food products. This review summarizes the recent application of rapid and nondestructive optical imaging and spectroscopic techniques, including digital color imaging, X-ray imaging, near-infrared spectroscopy, fluorescent, multispectral, and hyperspectral imaging. Advance chemometric techniques to identify very low-level mold growth and mycotoxin contamination are also discussed. Benefits, limitations, and challenges of deploying these techniques in practice are also presented in this paper.

Review on the photonic techniques suitable for automatic monitoring of the composition of multi-materials wastes in view of their posterior recycling

In the increasingly pressing context of improving recycling, optical technologies present a broad potential to support the adequate sorting of plastics. Nevertheless, the commercially available solutions (for example, employing near-infrared spectroscopy) generally focus on identifying mono-materials of a few selected types which currently have a market-interest as secondary materials. Current progress in photonic sciences together with advanced data analysis, such as artificial intelligence, enable bridging practical challenges previously not feasible, for example in terms of classifying more complex materials. In the present paper, the different techniques are initially reviewed based on their main characteristics. Then, based on academic literature, their suitability for monitoring the composition of multi-materials, such as different types of multi-layered packaging and fibre-reinforced polymer composites as well as black plastics used in the motor vehicle industry, is discussed. Finally, some commercial systems with applications in those sectors are also presented. This review mainly focuses on the materials identification step (taking place after waste collection and before sorting and reprocessing) but in outlook, further insights on sorting are given as well as future prospects which can contribute to increasing the circularity of the plastic composites' value chains.

Identification of Bacterial Blight Resistant Rice Seeds Using Terahertz Imaging and Hyperspectral Imaging Combined With Convolutional Neural Network

Because bacterial blight (BB) disease seriously affects the yield and quality of rice, breeding BB resistant rice is an important priority for plant breeders but the process is time-consuming. The feasibility of using terahertz imaging technology and near-infrared hyperspectral imaging technology to identify BB resistant seeds has therefore been studied. The two-dimensional (2D) spectral images and one-dimensional (1D) spectra provided by both imaging methods were used to build discriminant models based on a deep learning method, the convolutional neural network (CNN), and traditional machine learning methods, support vector machine (SVM), random forest (RF), and partial least squares discriminant analysis (PLS-DA). The highest classification accuracy was achieved by the discriminate model based on CNN using the terahertz absorption spectra. Confusion matrixes were pictured to show the identification details. The t-distributed stochastic neighbor embedding (t-SNE) method was used to visualize the process of CNN data processing. Terahertz imaging technology combined with CNN has great potential to quickly identify BB resistant rice seeds and is more accurate than using near-infrared hyperspectral imaging.