RESUMEN
Potatoes are popular among consumers due to their high yield and delicious taste. However, due to the numerous varieties of potatoes, different varieties are suitable for different processing methods. Therefore, it is necessary to distinguish varieties after harvest to meet the needs of processing enterprises and consumers. In this study, a new visible-near-infrared spectroscopic analysis method was proposed, which can achieve detection of five potato varieties. The method measures the transmission and reflection spectra of potatoes using a spectral acquisition system, encodes one-dimensional spectra into two-dimensional images using Gramian Angular Summation Field (GASF), Gramian Angular Difference Field (GADF), Markov Transition Field (MTF) and Recurrence Plot (RP), and improves the coordinated attention mechanism module and embeds the improved module into the ConvNeXt V2 model to build the ConvNeXt V2-CAP model for potato variety classification. The results show that compared with directly using one-dimensional classification models, image encoding of spectral data for classification greatly improves the accuracy. Among them, the best accuracy of 99.54% is achieved by using GADF image encoding of transmission spectra combined with the ConvNeXt V2-CAP model for classification, which is 16.28% higher than the highest accuracy of the one-dimensional classification model. The CAP attention mechanism module improves the performance of the model, especially when the dataset is small. When the training set is reduced to 150 images, the accuracy of the model is improved by 2.33% compared to the original model. Therefore, it is feasible to classify potato varieties using visible-near infrared spectroscopy and image encoding technology.
RESUMEN
Functional connectivity (FC) derived from resting-state functional magnetic resonance imaging (rs-fMRI) exhibits non-Euclidean topological structures, which have pathological foundations and serve as ideal objective data for intelligent diagnosis of major depressive disorder (MDD) patients. Additionally, the fully connected FC demonstrates uniform spatial structures. To learn and integrate information from these two structural forms for a more comprehensive identification of MDD patients, we propose a novel hierarchical learning structure called Multi-View Graph Neural Network (MV-GNN). In MV-GNN, the collaborative FC of subjects is filtered and reconstructed from topological view to obtain the reconstructed FC, incorporating various threshold values to calculate the topological attributes of brain regions. ROC analysis is performed on the average scores of these attributes for MDD and healthy control (HC) groups to determine an efficient threshold. Group differences analysis is conducted on the efficient topological attributes of brain regions, followed by their selection. These efficient attributes, along with the reconstructed FC, are combined to construct a graph view using self-attention graph pooling and graph convolutional neural networks, enabling efficient embedding. To extract efficient FC pattern difference information from spatial view, a dual leave-one-out cross-feature selection method is proposed. It selects and extracts relevant information from uniformly sized FC structures' high-dimensional spatial features, constructing a relationship view between brain regions. This approach incorporates both the whole graph topological view and spatial relationship view in a multi-layered structure, fusing them using gating mechanisms. By incorporating multiple views, it enhances the inference of whether subjects suffer from MDD and reveals differential information between MDD and HC groups across different perspectives. The proposed model structure is evaluated through leave-one-site cross-validation and achieves an average accuracy of 65.61% in identifying MDD patients at a single-center site, surpassing state-of-the-art methods in MDD recognition. The model provides valuable discriminatory information for objective diagnosis of MDD and serves as a reference for pathological foundations.
RESUMEN
Galloping of ice-coated transmission lines is occasionally observed under oblique wind directions. However, most current investigations on the galloping mechanisms are for flow perpendicular to the span of the transmission lines. In order to address this gap, this research studies the galloping characteristics of ice-coated transmission lines under oblique flows based on wind tunnel tests. The wind-induced displacement of an aero-elastic iced-coated transmission line model was measured with a noncontact displacement measurement equipment in a wind tunnel at different wind speeds and directions. The results show that galloping is characterized by elliptical trajectories and negative damping, which is more likely to occur under oblique flows than the direct flow (0°). At 15° wind direction, a galloping in vertical direction was observed at wind speeds above 5 m/s. At 30° wind direction, galloping was observed over the entire range of the tested wind speeds. Moreover, the galloping amplitudes under oblique flows are observed to be larger than that at the direct flows. Consequently, when the wind direction between the major winter monsoon azimuth and the lateral direction of transmission line route is between 15° and 30°, appropriate anti-galloping devices are highly recommended in practice.
RESUMEN
OBJECTIVE: To observe the effects of curcumin on the epithelial mesenchymal transition (EMT) and TGF-beta/Smads signal pathway in unilateral ureteral obstruction (UUO) rats. METHODS: UUO rat model was established. Rats were divided into the sham-operation group, the model group, the 1st curcumin group, and the 2nd curcumin group, respectively. From the 2nd day after surgery, rats of the 1st curcumin group were administrated with curcumin by gastrogavage at the daily dose of 100 mg/kg. From the 10th day after surgery, rats of the 2nd curcumin group were administrated with curcumin by gastrogavage at the daily dose of 100 mg/kg. Equal volume of normal saline was given to rats by gastrogavage in the sham-operation group and the model group. On the 28th day after surgery rats were killed. The renal tissues of the obstructed side were taken out. The distribution of mice alpha-smooth muscle actin (alpha-SMA) and E-cadherin expressions were observed using immunohistochemical method. Transforming growth factor-beta 1 (TGF-beta 1), P-Smad2, P-Smad3, and Smad7 expressions were detected by Western blot. TGF-beta 1, transforming growth factor-beta receptor I (TbetaRI), collagen-I (Col-I), and collagen-III (Col-III) mRNA expressions were detected by Real-time fluorescent quantitative PCR. RESULTS: alpha-SMA expressions were obviously enhanced, E-cadherin expressions obviously weakened, the protein expression levels of P-Smad2 and P-Smad3, protein and mRNA expression levels of TGF-beta 1, TbetaRI mRNA, Col-I mRNA, and Col-III mRNA obviously up-regulated, Smad7 protein expressions obviously decreased (all P<0.01) in the renal tissues of rats in the UUO group. In the 1st curcumin group and the 2nd curcumin group, the protein expressions of alpha-SMA, P-Smad2, P-Smad3, and TGF-beta 1; mRNA expression levels of TGF-beta 1, TbetaRI mRNA, Col-I, and Col-III obviously decreased (P<0.05, P< 0.01), while the protein expressions of E-cadherin and Smad7 obviously increased (P<0.05, P<0.01). CONCLUSIONS: Curcumin could intervene several sites of the TGF-beta/Smads signal transduction pathway of UUO rats, inhibit the occurrence of EMT of renal tubular epithelial cells, thus attenuating the tubulo-interstitial fibrosis.
