Discrimination of New and Aged Seeds Based on On-Line Near-Infrared Spectroscopy Technology Combined with Machine Learning.

The harvest year of maize seeds has a significant impact on seed vitality and maize yield. Therefore, it is vital to identify new seeds. In this study, an on-line near-infrared (NIR) spectra collection device (899-1715 nm) was designed and employed for distinguishing maize seeds harvested in different years. Compared with least squares support vector machine (LS-SVM), k-nearest neighbor (KNN), and extreme learning machine (ELM), the partial least squares discriminant analysis (PLS-DA) model has the optimal recognition performance for maize seed harvest years. Six different preprocessing methods, including Savitzky-Golay smoothing (SGS), standard normal variate transformation (SNV), multiplicative scatter correction (MSC), Savitzky-Golay 1 derivative (SG-D1), Savitzky-Golay 2 derivative (SG-D2), and normalization (Norm), were used to improve the quality of the spectra. The Monte Carlo cross-validation uninformative variable elimination (MC-UVE), competitive adaptive reweighted sampling (CARS), bootstrapping soft shrinkage (BOSS), successive projections algorithm (SPA), and their combinations were used to obtain effective wavelengths and decrease spectral dimensionality. The MC-UVE-BOSS-PLS-DA model achieved the classification with an accuracy of 88.75% using 93 features based on Norm preprocessed spectral data. This study showed that the self-designed NIR collection system could be used to identify the harvested years of maize seed.

Rapid Determination of Different Ripening Stages of Occidental Pears (Pyrus communis L.) by Volatile Organic Compounds Using Proton-Transfer-Reaction Mass Spectrometry (PTR-MS).

Determination of Occidental pear (Pyrus communis) ripening is difficult because the appearance of Occidental pears does not change significantly during the ripening process. Occidental pears at different ripening stages release different volatile organic compounds (VOCs), which can be used to determine fruit ripeness non-destructively and rapidly. In this study, VOCs were detected using proton-transfer-reaction mass spectrometry (PTR-MS). Notably, data were acquired within 1 min. Occidental pears harvested at five separate times were divided into three ripening stages: unripe, ripe, and overripe. The results showed that the composition of VOCs differed depending on the ripening stage. In particular, the concentrations of esters and terpenes significantly increased during the overripe stage. Three ripening stages were clearly discriminated by heatmap clustering and principal component analysis (PCA). This study provided a rapid and non-destructive method to evaluate the ripening stages of Occidental pears. The result can help fruit farmers to decide the optimum harvest time and hence reduce their economic losses.

Non-destructive and in-situ detection of shrimp freshness using mid-infrared fiber-optic evanescent wave spectroscopy.

There is strong interest in non-destructive and rapid determination of food freshness in food research. In this study, mid-infrared (MIR) fiber-optic evanescent wave (FOEW) spectroscopy was applied to monitor shrimp freshness through the evaluation of protein, chitin, and calcite contents in conjunction with a Partial Least Squares Discriminant Analysis (PLS-DA) model. Shrimp shells were wiped with a micro fiber-optic probe to obtain a FOEW spectrum which quickly and nondestructively allowed evaluation of the shrimp freshness. Peaks for proteins, chitin, and calcite, which are closely related to shrimp freshness, were detected and quantified. Compared with the standard indicator for evaluating shrimp freshness (total volatile basic nitrogen), the PLS-DA model gave recognition rates for shrimp freshness using calibration and validation sets of the FOEW data of 87.27%, 90.28%, respectively. Our results show that FOEW spectroscopy is a feasible method for non-destructive and in-site detection of shrimp freshness.

Hyperspectral remote sensing for tobacco quality estimation, yield prediction, and stress detection: A review of applications and methods.

Tobacco is an important economic crop and the main raw material of cigarette products. Nowadays, with the increasing consumer demand for high-quality cigarettes, the requirements for their main raw materials are also varying. In general, tobacco quality is primarily determined by the exterior quality, inherent quality, chemical compositions, and physical properties. All these aspects are formed during the growing season and are vulnerable to many environmental factors, such as climate, geography, irrigation, fertilization, diseases and pests, etc. Therefore, there is a great demand for tobacco growth monitoring and near real-time quality evaluation. Herein, hyperspectral remote sensing (HRS) is increasingly being considered as a cost-effective alternative to traditional destructive field sampling methods and laboratory trials to determine various agronomic parameters of tobacco with the assistance of diverse hyperspectral vegetation indices and machine learning algorithms. In light of this, we conduct a comprehensive review of the HRS applications in tobacco production management. In this review, we briefly sketch the principles of HRS and commonly used data acquisition system platforms. We detail the specific applications and methodologies for tobacco quality estimation, yield prediction, and stress detection. Finally, we discuss the major challenges and future opportunities for potential application prospects. We hope that this review could provide interested researchers, practitioners, or readers with a basic understanding of current HRS applications in tobacco production management, and give some guidelines for practical works.

In situ detection of fruit spoilage based on volatile compounds using the mid-infrared fiber-optic evanescent wave spectroscopy.

Volatile compounds such as ethanol released from fruit can be rapidly detected using Fourier Transform Infrared spectroscopy based on a long-path gas cell. However, this method relies on a long optical path length and requires pumping fruit volatiles into the gas cell. This can lead to the volatile compounds being contaminated and not detectable in situ. Fiber optic evanescent wave spectroscopy (FOEW) is not influenced by the path length so can detect materials (solid, liquid and gas phase) rapidly in situ, using only a few millimeters of optical fiber. In the present study, a spiral silver halide FOEW sensor with a length of approximately 21 mm was used to replace a long-path gas cell to explore the feasibility of identifying volatile compounds released from grapes in situ. The absorption peaks of ethanol in the volatile compounds were clearly found in the FOEW spectra and their intensity gradually increased as the storage time of the grapes increased. PCA analysis of these spectra showed clear clustering at different storage times (1-3, 4-5 and 6-7 d), revealing that the concentration of the ethanol released from the grapes changed significantly with time. The qualitative model established by PLS-DA algorithm could accurately classify grape samples as "Fresh," "Slight spoilage," or "Severe spoilage". The accuracy of the calibration and validation sets both were 100.00%. These changes can therefore be used for rapidly identifying fruit deterioration. Compared with the method used in a previous study by the authors, this method avoids using a pumping process and can thus identify volatile compounds and hence monitor deterioration in situ and on-line by placing a very short optical fiber near the fruit.

Influencing factors of environmental efficiency of strategic emerging industries and their power cooperation mechanism design.

We investigate the influencing factors of environmental efficiency of strategic emerging industries (SEIs) and cooperative game mechanism design amongst diversified actors by using China's provincial panel data from 2004 to 2019. Firstly, we find that the following factors improve the environmental efficiency of SEIs: rationalisation of the industrial structure, proportion of the tertiary industry, government's ability to intervene in the economy and fairness and integrity of environmental law enforcement. Conversely, factors, such as intensity of ecological construction and environmental regulation, hamper the environmental efficiency of SEIs. Secondly, evolutionary game analysis indicates that the behavioural strategies of game decision-making subjects depend on the behavioural decisions of the relative actors, social supervision and government regulation, which work together in influencing the environmental efficiency of SEIs. {innovation, supervision} is the optimal equilibrium state of the game. Thirdly, simulation results show that in the absence of government regulation, foreign direct investment (FDI) slows down the speed of firms tending to the equilibrium state of green innovation. The potential gain and loss of social supervision on corporate behaviour is an important factor affecting government behaviour decision making. Governments prefer punishment tools in environmental regulation, therefore influencing noninnovative firms in SEIs. We contribute to prior works by unifying various policy tools into the same econometric model framework based on an evolutionary game model.

A Graph-Related High-Order Neural Network Architecture via Feature Aggregation Enhancement for Identification Application of Diseases and Pests.

Diseases and pests are essential threat factors that affect agricultural production, food security supply, and ecological plant diversity. However, the accurate recognition of various diseases and pests is still challenging for existing advanced information and intelligence technologies. Disease and pest recognition is typically a fine-grained visual classification problem, which is easy to confuse the traditional coarse-grained methods due to the external similarity between different categories and the significant differences among each subsample of the same category. Toward this end, this paper proposes an effective graph-related high-order network with feature aggregation enhancement (GHA-Net) to handle the fine-grained image recognition of plant pests and diseases. In our approach, an improved CSP-stage backbone network is first formed to offer massive channel-shuffled features in multiple granularities. Secondly, relying on the multilevel attention mechanism, the feature aggregation enhancement module is designed to exploit distinguishable fine-grained features representing different discriminating parts. Meanwhile, the graphic convolution module is constructed to analyse the graph-correlated representation of part-specific interrelationships by regularizing semantic features into the high-order tensor space. With the collaborative learning of three modules, our approach can grasp the robust contextual details of diseases and pests for better fine-grained identification. Extensive experiments on several public fine-grained disease and pest datasets demonstrate that the proposed GHA-Net achieves better performances in accuracy and efficiency surpassing several other existing models and is more suitable for fine-grained identification applications in complex scenes.

Bioresorbable hydrogels prepared by photo-initiated crosslinking of diacrylated PTMC-PEG-PTMC triblock copolymers as potential carrier of antitumor drugs.

PTMC-PEG-PTMC triblock copolymers were prepared by ring-opening polymerization of trimethylene carbonate (TMC) in the presence of dihydroxylated poly(ethylene glycol) (PEG) with Mn of 6000 and 10,000 as macro-initiator. The copolymers with different PTMC block Lengths and the two PEGs were end functionalized with acryloyl chloride. The resulting diacrylated PEG-PTMC-DA and PEG-DA were characterized by using NMR, GPC and DSC. The degree of substitution of end groups varied from 50.0 to 65.1%. Hydrogels were prepared by photo-crosslinking PEG-PTMC-DA and PEG-DA in aqueous solution using a water soluble photo-initiator under visible light irradiation. The effects of PTMC and PEG block lengths and degree of substitution on the swelling and weight loss of hydrogels were determined. Higher degree of substitution leads to higher crosslinking density, and thus to lower degree of swelling and weight loss. Similarly, higher PTMC block length also leads to lower degree of swelling and weight loss. Freeze dried hydrogels exhibit a highly porous structure with pore sizes from 20 to 100 µm. The biocompatibility of hydrogels was evaluated by MTT assay, hemolysis test, and dynamic clotting time measurements. Results show that the various hydrogels present outstanding cyto- and hemo-compatibility. Doxorubicin was taken as a model drug to evaluate the potential of PEG-PTMC-DA and PEG-DA hydrogels as drug carrier. An initial burst release was observed in all cases, followed by slower release up to more than 90%. The release rate is strongly dependent on the degree of swelling. The higher the degree of swelling, the faster the release rate. Finally, the effect of drug loaded hydrogels on SKBR-3 tumor cells was evaluated in comparison with free drug. Similar cyto-toxicity was obtained for drug loaded hydrogels and free drug at comparable drug concentrations. Therefore, injectable PEG-PTMC-DA hydrogels with outstanding biocompatibility and drug release properties could be most promising as bioresorbable carrier of hydrophilic drugs.

Sparse CT reconstruction based on multi-direction anisotropic total variation (MDATV).

BACKGROUND: The sparse CT (Computed Tomography), inspired by compressed sensing, means to introduce a prior information of image sparsity into CT reconstruction to reduce the input projections so as to reduce the potential threat of incremental X-ray dose to patients' health. Recently, many remarkable works were concentrated on the sparse CT reconstruction from sparse (limited-angle or few-view style) projections. In this paper we would like to incorporate more prior information into the sparse CT reconstruction for improvement of performance. It is known decades ago that the given projection directions can provide information about the directions of edges in the restored CT image. ATV (Anisotropic Total Variation), a TV (Total Variation) norm based regularization, could use the prior information of image sparsity and edge direction simultaneously. But ATV can only represent the edge information in few directions and lose much prior information of image edges in other directions. METHODS: To sufficiently use the prior information of edge directions, a novel MDATV (Multi-Direction Anisotropic Total Variation) is proposed. In this paper we introduce the 2D-IGS (Two Dimensional Image Gradient Space), and combined the coordinate rotation transform with 2D-IGS to represent edge information in multiple directions. Then by incorporating this multi-direction representation into ATV norm we get the MDATV regularization. To solve the optimization problem based on the MDATV regularization, a novel ART (algebraic reconstruction technique) + MDATV scheme is outlined. And NESTA (NESTerov's Algorithm) is proposed to replace GD (Gradient Descent) for minimizing the TV-based regularization. RESULTS: The numerical and real data experiments demonstrate that MDATV based iterative reconstruction improved the quality of restored image. NESTA is more suitable than GD for minimization of TV-based regularization. CONCLUSIONS: MDATV regularization can sufficiently use the prior information of image sparsity and edge information simultaneously. By incorporating more prior information, MDATV based approach could reconstruct the image more exactly.

Techniques to improve the accuracy of presampling MTF measurement in digital X-ray imaging based on constrained spline regression.

To develop an effective curve-fitting algorithm with a regularization term for measuring the modulation transfer function (MTF) of digital radiographic imaging systems, in comparison with representative prior methods, a C-spline regression technique based upon the monotonicity and convex/concave shape restrictions of the edge spread function (ESF) was proposed for ESF estimation in this study. Two types of oversampling techniques and following four curve-fitting algorithms including the C-spline regression technique were considered for ESF estimation. A simulated edge image with a known MTF was used for accuracy determination of algorithms. Experimental edge images from two digital radiography systems were used for statistical evaluation of each curve-fitting algorithm on MTF measurements uncertainties. The simulation results show that the C-spline regression algorithm obtained a minimum MTF measurement error (an average error of 0.12% ± 0.11% and 0.18% ± 0.17% corresponding to two types of oversampling techniques, respectively, up to the cutoff frequency) among all curve-fitting algorithms. In the case of experimental edge images, the C-spline regression algorithm obtained the best uncertainty performance of MTF measurement among four curve-fitting algorithms for both the Pixarray-100 digital specimen radiography system and Hologic full-field digital mammography system. Comparisons among MTF estimates using four curve-fitting algorithms revealed that the proposed C-spline regression technique outperformed other algorithms on MTF measurements accuracy and uncertainty performance.