Search

ObjectiveThe widespread prevalence of sclerotinia disease poses a significant challenge to the cultivation and supply of oilseed rape, not only results in substantial yield losses and decreased oil content in infected plant seeds but also severely impacts crop productivity and quality, leading to significant economic losses. To solve the problems of complex operation, environmental pollution, sample destruction and low detection efficiency of traditional chemical detection methods, a Bi-directional Gate Recurrent Unit (Bi-GRU) model based on space-spectrum feature fusion was constructed to achieve hyperspectral images (HSIs) segmentation of oilseed rape sclerotinia infected area.MethodsThe spectral characteristics of sclerotinia disease from a spectral perspective was initially explored. Significantly varying spectral reflectance was notably observed around 550 nm and within the wavelength range of 750-1 000 nm at different locations on rapeseed leaves. As the severity of sclerotinia infection increased, the differences in reflectance at these wavelengths became more pronounced. Subsequently, a rapeseed leaf sclerotinia disease dataset comprising 400 HSIs was curated using an intelligent data annotation tool. This dataset was divided into three subsets: a training set with 280 HSIs, a validation set with 40 HSIs, and a test set with 80 HSIs. Expanding on this, a 7×7 pixel neighborhood was extracted as the spatial feature of the target pixel, incorporating both spatial and spectral features effectively. Leveraging the Bi-GRU model enabled simultaneous feature extraction at any point within the sequence data, eliminating the impact of the order of spatial-spectral data fusion on the model's performance. The model comprises four key components: an input layer, hidden layers, fully connected layers, and an output layer. The Bi-GRU model in this study consisted of two hidden layers, each housing 512 GRU neurons. The forward hidden layer computed sequence information at the current time step, while the backward hidden layer retrieves the sequence in reverse, incorporating reversed-order information. These two hidden layers were linked to a fully connected layer, providing both forward and reversed-order information to all neurons during training. The Bi-GRU model included two fully connected layers, each with 1 000 neurons, and an output layer with two neurons representing the healthy and diseased classes, respectively.Results and DiscussionsTo thoroughly validate the comprehensive performance of the proposed Bi-GRU model and assess the effectiveness of the spatial-spectral information fusion mechanism, relevant comparative analysis experiments were conducted. These experiments primarily focused on five key parameters—ClassAP(1), ClassAP(2), mean average precision (mAP), mean intersection over union (mIoU), and Kappa coefficient—to provide a comprehensive evaluation of the Bi-GRU model's performance. The comprehensive performance analysis revealed that the Bi-GRU model, when compared to mainstream convolutional neural network (CNN) and long short-term memory (LSTM) models, demonstrated superior overall performance in detecting rapeseed sclerotinia disease. Notably, the proposed Bi-GRU model achieved an mAP of 93.7%, showcasing a 7.1% precision improvement over the CNN model. The bidirectional architecture, coupled with spatial-spectral fusion data, effectively enhanced detection accuracy. Furthermore, the study visually presented the segmentation results of sclerotinia disease-infected areas using CNN, Bi-LSTM, and Bi-GRU models. A comparison with the Ground-Truth data revealed that the Bi-GRU model outperformed the CNN and Bi-LSTM models in detecting sclerotinia disease at various infection stages. Additionally, the Dice coefficient was employed to comprehensively assess the actual detection performance of different models at early, middle, and late infection stages. The dice coefficients for the Bi-GRU model at these stages were 83.8%, 89.4% and 89.2%, respectively. While early infection detection accuracy was relatively lower, the spatial-spectral data fusion mechanism significantly enhanced the effectiveness of detecting early sclerotinia infections in oilseed rape.ConclusionsThis study introduces a Bi-GRU model that integrates spatial and spectral information to accurately and efficiently identify the infected areas of oilseed rape sclerotinia disease. This approach not only addresses the challenge of detecting early stages of sclerotinia infection but also establishes a basis for high-throughput non-destructive detection of the disease.

The evolution of pore structure is very important to the frost resistance of concrete. In order to study the effect of nano-TiO2 on pore structure and frost resistance of concrete, the nano-TiO2 concrete with substitution rates of 0%, 1%, 3%, 5% (mass fraction, the same below) were selected as research object, and the quick freezing test, compressive strength test, nuclear magnetic resonance test and scanning electron microscope test were carried out. The changes of mass, dynamic elastic modulus, compressive strength, pore structure and micro-morphology of nano-TiO2 concrete before and after freeze-thaw cycle were analyzed to evaluate the freeze-thaw damage at - 18 ~ 5 °C and to analyze the improvement mechanism of nano-TiO2 on concrete properties. At the same time, the response models of compressive strength, relative dynamic modulus, free water saturation and crack ratio were established to determine the optimum content of nano-TiO2. The results show that an appropriate content of nano-TiO2 effectively improves the micro-morphology of concrete, increases the proportion of micropores and medium pores of concrete, and reduces the proportion of macropores and cracks, while excessive nano-TiO2 increases the proportion of macropores and cracks in concrete, which is not conducive to the improvement of frost resistance of concrete. When the content of nano-TiO2 is 1%, the frost resistance of concrete is the best. Based on the frost resistance performance index and pore test results, the response model is established, and the optimal content of nano-TiO2 is close to 1%, which is consistent with the test results. [ABSTRACT FROM AUTHOR]

A dragonfly can hover, flap its wings for flight and fly vertically for a short distance. The membranous wings of a dragonfly have a high load-bearing capacity for static and dynamic load during flight. The mass of the wings of a dragonfly is only 1%-2% of its whole body but the wings can stabilize its body. The statics properties of biomimetic models were researched. The finite element software ANSYS was used to simulate the dragonfly wing. The veins were simulated by pipe20 with two nodes and the membranes by shell43 with four nodes. The influence of geometrical nonlinearity was taken into account but material nonlinearity. The models were assumed in the elastic range. The three-dimensional model of the dragonfly wing was reconstructed using reverse engineering software Imageware. The veins of dragonfly wing were drawn with AutoCAD and the membranes were added with ANSYS. The finite element models imitating the dragonfly wing were established by using free meshing. The finite element models of the dragonfly wing were simulated with structural statics. The deformation, the stress and the strain of the models under loads were analyzed respectively. The loads include the uniform load, the bending moment and the torque. Under the uniform load, the deformation of the finite element model imitating a dragonfly wing is very small, and increases gradually from the base to the wing tip. The base of the model bears heavy stress, the middle parts smaller, and the wing tip the least. The strain shows a radial pattern along the longitudinal veins, and reduces gradually from the base to the wing tip of the model. Under the bending moment, the deformation and the rotation angle around y axis increase gradually from the base to the wing tip of the model. The heavy stress and strain are mainly concentrated on the base of the model. The small stress and strain are acted on the middle parts and the wing tip. The distribution trend of the stress and strain is in substantial agreement. Under the torque, the finite element model imitating a dragonfly wing deforms only a little as a whole. The heavy deformation is mainly concentrated on the leading edges and the rear edges of the model. The smaller deformation is acted on the middle parts and the least deformation on the base. The maximum stress and strain occur at the middle parts of the model. The minimum stress and strain occur at the base of the model. The dragonfly wing is a two-dimensional truss structure with excellent rigidity. The dragonfly wing deforms only a little under loads. It is shown that the grid structures of the dragonfly wing deforming together at the boundaries of veins and membranes have excellent integrity. The understanding of dragonfly wings' characteristics provides some reference for improving the properties of two-dimensional composite materials through biomimetic designs. [ABSTRACT FROM AUTHOR]

Biodiesel (fatty acid methyl or ethyl esters) is made from vegetable oil or animal fat (triglycerides) reacting with methanol or ethanol using a catalyst (lye). It is safe, biodegradable, and produces less air pollutants than petroleum-based diesel or recycled restaurant greases. With the increasing demand of green energy source and the decreasing of fossil fuel, biodiesel has gained increasing attention as one of the alternative fuels. 100% biodiesel (B100) was used in this study. Experimental samples with water content of 0, 2.50%, 5.00%, 7.50% and 10.0% were set. There were 35 samples for every treatment with different water contents, and total 175 samples. 116 samples were selected for calibration set, and 58 samples for prediction set based with Kennard-Stone (K-S) method. Visible and near infrared spectra (Vis-NIR) technique which was a nondestructive and rapid method, was used to measure the water content in biodiesel. Samples were scanned using the ADS Handheld FieldSpec spectrometer and spectra of samples were acquired. Principal component analysis (PCA) was used to compress spectral data and observe the cluster's situation of biodiesel with different water contents. The scores plot showed a good cluster distribution and the total accumulated variance of PC-1 and PC-2 was up to 99.3%. Random Frog algorithm was applied to extract spectral feature. Then, 8 sensitive wavelengths (563, 560, 642, 565, 562, 493, 559 and 779 nm) were selected respectively. Spectral feature and different water contents were set as input values of partial least squares regression (PLSR) and least squares-support vector machine (LS-SVM) models. It was showed that LS-SVM and PLSR with full spectra had good results, while the variables were too much (116×591) compared with the regression models (116×8). Results of the Random Frog-LS-SVM were better than the Random Frog-PLSR. R of the non-linear LS-SVM models with spectral feature extracted by Random Frog was higher than 0.965, RMSEC of 0.722, RMSEP of 0.520. Sensitive wavelengths extracted were good for eliminating the interfering spectral and improving the accuracy of the model. Results indicated that the Random Frog-LS-SVM as a satisfactory model can measure the water content in biodiesel accurately, which could provide a reference for practical application. [ABSTRACT FROM AUTHOR]