Search

With the rapid development of social media and the popularity of mobile devices,the interaction between users has become more convenient.But at the same time,rumors on social media are more and more rampant,which brings hidden dangers to the public and social safety.In the real world,users often express their own opinions after observing other microblogs that have been posted,especially the context of the microblog to be replied.Although some existing rumor detection methods learn the propagation patterns on propagation trees of rumors to extract clues of user interrogation or factual evidences based on the principle of crowd wisdom,which greatly improves the performance of rumor detection,they only focus on those microblogs that have direct response relationships,and Lack of ability to fully mine the indirect and implicit relationships among microblogs in the process of rumor propagation.Therefore,in this paper,a node and path dual-attention network on propagation tree structures(DAN-Tree) for debunking rumors is proposed.First,the model uses the Transformer structure to fully learn the implicit semantic relationship between posts in the propagation path,and then uses the attention mechanism to perform weighted fusion to obtain the feature vector of the propagation path.Secondly,the path representation is weighted and aggregated by using the attention mechanism to obtain the representation vector of the whole propagation tree.In addition,the structure embedding method is used to learn the spatial location information of the post on the propagation tree,which realizes the effective fusion of the deep structure and semantic information in the rumor propagation structure.The effect of the DAN-Tree model is verified on four classic datasets.Experimental results show that the DAN-Tree model surpasses the best results of the existing literature on the three datasets:the accuracy of the Twitter15 and Twitter16 datasets increases by 1.81% and 2.39%,respectively,and the F1 score of the PHEME dataset increases by 7.51%,which proves the effectiveness of DAN-Tree model.

This study proposes a deep learning method for pavement defect detection, focusing on identifying potholes and cracks. A dataset comprising 10,828 images is collected, with 8662 allocated for training, 1083 for validation, and 1083 for testing. Vehicle attitude data are categorized based on three-axis acceleration and attitude change, with 6656 (64%) for training, 1664 (16%) for validation, and 2080 (20%) for testing. The Nvidia Jetson Nano serves as the vehicle-embedded system, transmitting IMU-acquired vehicle data and GoPro-captured images over a 5G network to the server. The server recognizes two damage categories, low-risk and high-risk, storing results in MongoDB. Severe damage triggers immediate alerts to maintenance personnel, while less severe issues are recorded for scheduled maintenance. The method selects YOLOv7 among various object detection models for pavement defect detection, achieving a mAP of 93.3%, a recall rate of 87.8%, a precision of 93.2%, and a processing speed of 30–40 FPS. Bi-LSTM is then chosen for vehicle vibration data processing, yielding 77% mAP, 94.9% recall rate, and 89.8% precision. Integration of the visual and vibration results, along with vehicle speed and travel distance, results in a final recall rate of 90.2% and precision of 83.7% after field testing.

Melanoma remains a challenge due to the lack of effective and low-toxicity treatments. Litsea cubeba essential oil (LEO), known for its tyrosinase inhibitory activity, has shown promise as an anti-melanoma compound, although robust scientific evidence is lacking. We conducted GC-MS analysis to identify the major components of LEO and screened for effective components were further evaluated on A375 and HaCaT cells using the CCK-8 assay. Network pharmacology was employed to predict potential targets using PharmMapper and SwissTarget Prediction databases, with melanoma-related targets sourced from the GeneCards database. Protein–protein interaction (PPI) network was created using STRING and Cytoscape. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analyses were performed through the DAVI database. Additionally, we constructed a natural product-main components-core targets-pathways-disease (NMCPD) network in Cytoscape and conducted molecular docking using PyMOL and Autodock Vina. GC-MS analysis revealed neral (cis-citral) and geranial (trans-citral) as the primary active components of LEO. Cell assays demonstrated that a citral mixture, in combination with LEO, effectively inhibited A375 cell growth with IC50 values of 35.94 ± 1.23 μM and 12.00 ± 0.96 μg/mL, while exhibiting minimal toxicity to HaCaT cells with IC50 values of 67.72 ± 2.96 μM and 22.32 ± 2.53 μg/mL. Screening identified10 hub targets among 190 common targets between drug and disease-related targets. KEGG pathway enrichment analysis suggested therapeutic effects of citral on melanoma by modulating signaling pathways. Molecular docking revealed strong binding affinity of neral and geranial with RXRA and ESR1, suggesting that citral, the principal LEO component, regulates multiple pathways for potential melanoma therapy. These findings support the potential utility of LEO as a treatment for melanoma and highlight the importance of exploring tyrosinase inhibitors for the development of novel anti-melanoma drugs. [ABSTRACT FROM AUTHOR]

Abstract Background Seed germination and seedling establishment are two of the most critical phases in plant development. However, the molecular mechanisms underlying the effect of phosphorus on seed germination and post-germinated growth of oilseed rape are unclear so far. Here, we report the role of BnPHT1;4 in seed germination and early seedling development of Brassica napus. Results Our results show that BnPHT1;4 is preferentially expressed in cotyledons of early developing seedlings. Overexpression of BnPHT1;4 in oilseed rape promoted seed germination and seedling growth. Expression levels of the genes related to ABA and GA biosynthesis and signaling were significantly altered in BnPHT1;4 transgenic seedlings. Consequently, active GA level was up-regulated, whereas ABA content was down-regulated in BnPHT1;4 transgenic seedlings. Furthermore, exogenous GA could promote seed germination of wild type, while exogenous ABA could partially recover the advanced-germination phenotype of BnPHT1;4 transgenic seeds. Total phosphorus content in cotyledons of the transgenic seedlings was decreased more rapidly than that in wild type when Pi was supplied or deficient, and Pi contents in shoots and roots of the BnPHT1;4 transgenic plants were higher than those in wild type under high and low Pi conditions. Conclusions Our data suggest that the high-affinity transporter BnPHT1;4 is involved in phosphorus acquisition and mobilization for facilitating seed germination and seedling growth of Brassica napus by modulating ABA and GA biosynthesis.

Manually designing a convolutional neural network (CNN) is an important deep learning method for solving the problem of image classification. However, most of the existing CNN structure designs consume a significant amount of time and computing resources. Over the years, the demand for neural architecture search (NAS) methods has been on the rise. Therefore, we propose a novel deep architecture generation model based on Aquila optimization (AO) and a genetic algorithm (GA). The main contributions of this paper are as follows: Firstly, a new encoding strategy representing the CNN coding structure is proposed, so that the evolutionary computing algorithm can be combined with CNN. Secondly, a new mechanism for updating location is proposed, which incorporates three typical operators from GA cleverly into the model we have designed so that the model can find the optimal solution in the limited search space. Thirdly, the proposed method can deal with the variable-length CNN structure by adding skip connections. Fourthly, combining traditional CNN layers and residual blocks and introducing a grouping strategy provides greater possibilities for searching for the optimal CNN structure. Additionally, we use two notable datasets, consisting of the MNIST and CIFAR-10 datasets for model evaluation. The experimental results show that our proposed model has good results in terms of search accuracy and time.