Fake news on social media is a widespread and serious problem in today's society. Existing fake detection methods focus finding clues from Long text content, such as original articles user comments. This paper solves the of more realistic scenarios. Only source shot-text tweet its retweet users are provided without We develop novel neural network based model, Multi-View Attention Networks (MVAN) to detect provide explanations media. The MVAN model includes semantic attention propagation...

Abstract Efficient calculation of the light diffraction in free space is great significance for tracing electromagnetic field propagation and predicting performance optical systems such as microscopy, photolithography, manipulation. However, existing methods suffer from low computational efficiency poor flexibility. Here, we present a fast flexible method computing scalar vector corresponding regimes using Bluestein method. The computation time can be substantially reduced to sub-second...

The avian influenza virus is infected through the mucosal route, thus barrier defense very important. While inactivated H9N2 vaccine cannot achieve sufficient immunity, adjuvants are needed to induce and systemic immunity prevent poultry from infection. Our previous study found that polysaccharide Atractylodes macrocephala Koidz binding with zinc oxide nanoparticles (AMP-ZnONPs) had immune-enhancing effects in vitro. This aimed evaluate immune responses of oral whole-inactivated...

Reinforcement learning has shown promise in enabling autonomous ship navigation, allowing vessels to adapt and make informed decisions complex marine environments. However, the integration of soft constraints their impact on performance RL-based vessel navigation research remain understudied. This addresses this gap by investigating implications context risk-averse problem. Four distinct constraint functions are proposed, which integrated with two widely used RL algorithms, resulting...

Intelligent ship monitoring technology, driven by its exceptional data fitting ability, has emerged as a crucial component within the field of intelligent maritime perception. However, existing deep learning-based studies primarily focus on minimizing discrepancy between predicted and true labels during model training. This approach, unfortunately, restricts to learning only from labeled samples training set, limiting capacity recognize new unseen categories. To address this challenge...

Introduction Identification of effective therapies for colorectal cancer (CRC) remains an urgent medical need, especially the microsatellite stable (MSS) phenotype. In our previous study, potassium oxonate (PO), a uricase inhibitor commonly used elevating uric acid in mice, unexpectedly showed remarkable inhibition tumor growth when combined with anti-programmed death-1 (PD-1). Further research demonstrated that combination and anti-PD-1 could reprogram immune microenvironment. This study...

A dual-module machine learning scheme is proposed to reconstruct inhomogeneous scatterers with high contrasts and large electrical dimensions. The first nonlinear mapping module (NMM) an extreme (ELM), which used convert the measured scattered fields at receiver arrays into preliminary images of scatterers. second image-enhancing (IEM) a convolutional neural network (CNN), refine further from NMM obtain high-accuracy pixel-based model parameter distribution in inversion domain. Compared...

Vessel monitoring technology involves the application of remote sensing technologies to detect and identify vessels in various environments, which is critical for vessel traffic, identifying potential threats, facilitating maritime safety security achieve real-time awareness military civilian domains. However, most existing models tend focus on a single information source, leading limited detection functionality underutilization available information. In light these limitations, this paper...

Abstract Many successful machine learning methods have been developed for electromagnetic (EM) inverse scattering problems. However, so far, their inversion has performed only at the specifically trained frequencies. To make based method more generalizable realistic engineering applications, this work proposes a residual fully convolutional network (Res-FCN) to perform EM of high contrast scatterers an arbitrary frequency within wide band. The proposed Res-FCN combines advantages Res-Net and...

Hexavalent chromium is a common pollutant in the environment. Long-term exposure to hexavalent can cause damage multiple organs. The kidney one of main organs that metabolizes heavy metal toxicity, and accumulation Cr (VI) body lead serious function. Studies have shown ginseng polysaccharides function preventing cisplatin-induced endoplasmic reticulum stress, inflammatory response, apoptosis renal cells, but their efficacy mechanisms against chromium-induced nephrotoxicity need be explored....

Rumors in social media represent a severe problem prevailing today's society. Previous studies on automated rumor detection have shown that the topological information specific to is vital clue for debunking rumors. However, existing automatic approaches either oversimplify graph structure or ignore this crucial clue. To address issue, we propose model explores homogeneity and conversation identify Our learns more comprehensive precise representations by modeling follower-following...

The ionospheric delay effect is inevitable when a radio signal propagates through the ionosphere. It has been extensively studied in L-band. Typically, influence of ionosphere on code phase and carrier regarded as same. In this study, numerical ratio between group time advance with reference to study L-band investigated short-wave band. variation frequency, critical elevation angle discussed detail. There appears an interesting phenomenon wherein greater than frequency frequency. increases...

Studying the physicochemical properties and biological activities of Lycium barbarum polysaccharides(LBPs) is great significance. The previous study had extracted LBPs(LBP-1, LBP-2, LBP-3, LBP-4, LBP-5) by five different methods(cold water extraction, boiling reflux extraction residue after cold ultrasonic with 50% ethanol, 25% ethanol hot extraction). In this study, structures obtained LBPs were characterized UV spectroscopy, thermogravimetric analysis, scanning electron microscopy....

Previous studies have introduced a resonant caisson designed to enhance wave energy extraction in regions with low density; however, its operational mechanism remains poorly understood. This paper seeks elucidate the of by leveraging Star-CCM+ for Computational Fluid Dynamics (CFD) simulations, focusing on influence guides and their dimensions water levels, flow velocities, vortex dynamics. The findings demonstrate remarkable wave-amplification capabilities caisson, maximum amplification...

With the increase in port throughput and development of trend large-scale ships, selecting applicable anchor positions for ships ensuring rational comprehensive utilization anchorage areas have become a key issue utilizing rate resources, safety anchoring operations promoting shipping industry. Existing position selection detection algorithm studies are limited to two-dimensional plane ship selection, with few considering intelligent algorithms safe water depths based on three-dimensional...

A mechanical vibration fault diagnosis is a key means of ensuring the safe and stable operation transformers. To achieve an accurate transformer faults, this paper proposes novel method based on time-shift multiscale increment entropy (TSMIE) combined with CatBoost. Firstly, inspired by concept time shift, TSMIE was proposed. effectively solves problem information loss caused coarse-graining process traditional entropy. Secondly, signals under different operating conditions extracted as...

As intelligent ship technology advances, the importance of anchor position detection, as one key technologies, can ensure safe anchoring ships and enhance efficiency port operation. At present, most selection detection algorithms are mainly based on two-dimensional planes, there is a lack research water depth for in three-dimensional space. It not only restricts full utilization anchorage resources but also affects safety environmental adaptability operations. To address these issues, this...

The prediction of crowd flow in key urban areas is an important basis for city informatization development and management. Timely understanding trends can provide cities with data support epidemic prevention, public security management, other aspects. In this paper, the model uses Node2Vec graph embedding algorithm combined LSTM (NDV-LSTM) to predict flow. first analyzes correspondence between grid centers, was used extract spatial features. At same time, considering region type, weather,...

Ship detection in the maritime domain awareness field has seen a significant shift towards deep-learning-based techniques as mainstream approach. However, most existing ship models adopt random sampling strategy for training data, neglecting complexity differences among samples and learning progress of model, which hinders efficiency, robustness, generalization ability. To address this issue, we propose model called Leap-Forward-Learning-Decay Curriculum Learning-based Network (LFLD-CLbased...

The hybrid spectral-element spectral-integral (SESI) method is developed for the electromagnetic (EM) scattering in 1-D Bloch (Floquet) periodic problems with scatterers embedded multiple regions of 2-D layered media. medium Green's function (PLMGF) derived SESI so that it can simulate EM by horizontally placed an arbitrary number layers. a combination (SEM) and (SIM). SEM applied only has merits exponential convergence at low spatial sampling density, while SIM serves as exact radiation...