Att-BrainNet: Attention-based BrainNet for lung cancer segmentation network.

Most current medical image segmentation models employ a unified feature modeling strategy for all target regions. However, they overlook the significant heterogeneity in lesion structure, boundary characteristics, and semantic texture, which frequently restricts their ability to accurately segment morphologically diverse lesions in complex imaging contexts, thereby reducing segmentation accuracy and robustness. To address this issue, we propose a brain-inspired segmentation framework named BrainNet, which adopts a tri-level backbone encoder-Brain Network-decoder architecture.

Spin-orbit-controlled correlation physics and orbital-selective electronic transitions in uranium monoxide revealed by many-body calculations.

We present a comprehensive study of the temperature-dependent electronic structure in uranium monoxide (UO) using the local density approximation (LDA) combined with dynamical mean-field theory (LDA + DMFT). Our calculations reveal orbital-selective electronic transitions driven by relativistic spin-orbit coupling, leading to metallic 5f states and insulating 5f states. These transitions are robust against thermal perturbations, suggesting a many-body protection mechanism.

A New Perspective for Solid-to-Liquid Transition of an Inorganic Particle Structure in a Gel System Filled with Fumed Silica and Aluminum Microparticles during Stress-Controlled Oscillation.

Silica-based gels are often mentioned because of their viscoelasticity, but very little work has really reflected this competing relationship between restorative and destructive properties dominated by the inorganic particle structure. Understanding the mechanical behavior of the solid-to-liquid transition is a key to be addressed in the design of gelation, while it is an attractive task to excavate the respective morphology and separate effects on the viscoelasticity of the gel structure and the viscous elasticity of the interface. In this work, gel fuels were prepared by dispersing fumed silica (FS) and aluminum microparticles (Al MPs) in a hydrocarbon fuel.

Study on the macro and micro characteristics of the influence of deviator stress on true triaxial unloading failure.

This paper uses a specific underground tunnel project in the eastern coastal region of China as its research background. It analyzes the impact of deviatoric stress on the evolution of rock unloading failure, providing data to support the understanding of dynamic failure during the excavation and construction of underground chambers. The macroscopic characteristics observed in true triaxial compression tests with confining pressure unloading revealed that during unloading, the ε curve initially dropped before rising back along the original loading path.

In-Motion Initial Alignment Method Based on Multi-Source Information Fusion for Special Vehicles.

To address the urgent demand for autonomous rapid initial alignment of vehicular inertial navigation systems in complex battlefield environments, this study overcomes the technical limitations of traditional stationary base alignment methods by proposing a robust moving-base autonomous alignment approach based on multi-source information fusion. First, a federal Kalman filter-based multi-sensor fusion architecture is established to effectively integrate odometer, laser Doppler velocimeter, and SINS data, resolving the challenge of autonomous navigation parameter calculation under GNSS-denied conditions. Second, a dual-mode fault diagnosis and isolation mechanism is developed to enable rapid identification of sensor failures and system reconfiguration.

Achieving Efficient Fast Neutron and Gamma Discrimination in Hydrogen-Rich 2D Halide Perovskite Scintillators.

Neutron radiation fields frequently coexist with γ-rays, posing a significant challenge to ensure the accuracy of neutron detection. 2D perovskites have been proved to be the potential fast neutron scintillators due to their structural properties and excellent luminescent performance. Herein, the study reports on the scintillation properties of 2D perovskite phenethylammonium lead bromide ((PEA)PbBr) single crystal (SC) induced by different types of radiation and first demonstrate its pulse shape discrimination (PSD) capability in neutron/gamma (n/γ) mixed radiation fields.

Virtual Node-Driven Cloud-Edge Collaborative Resource Scheduling for Surveillance with Visual Sensors.

For public security purposes, distributed surveillance systems are widely deployed in key areas. These systems comprise visual sensors, edge computing boxes, and cloud servers. Resource scheduling algorithms are critical to ensure such systems' robustness and efficiency.

Two-dimensional Nanosheets by Liquid Metal Exfoliation.

Liquid exfoliation is a scalable and effective method for synthesizing 2D nanosheets (NSs) but often induces contamination and defects. Here, liquid metal gallium (Ga) is used to exfoliate bulk layered materials into 2D NSs at near room temperature, utilizing the liquid surface tension and Ga intercalation to disrupt Van der Waals (vdW) forces. In addition, the process can transform the 2H-phase of transition metal dichalcogenides into the 1T'-phase under ambient conditions.

Stealthy Vehicle Adversarial Camouflage Texture Generation Based on Neural Style Transfer.

Adversarial attacks that mislead deep neural networks (DNNs) into making incorrect predictions can also be implemented in the physical world. However, most of the existing adversarial camouflage textures that attack object detection models only consider the effectiveness of the attack, ignoring the stealthiness of adversarial attacks, resulting in the generated adversarial camouflage textures appearing abrupt to human observers. To address this issue, we propose a style transfer module added to an adversarial texture generation framework.

AerialIRGAN: unpaired aerial visible-to-infrared image translation with dual-encoder structure.

Due to the high cost of equipment and the constraints of shooting conditions, obtaining aerial infrared images of specific targets is very challenging. Most methods using Generative Adversarial Networks for translating visible images to infrared greatly depend on registered data and struggle to handle the diversity and complexity of scenes in aerial infrared targets. This paper proposes a one side end-to-end unpaired aerial visible-to-infrared image translation algorithm, termed AerialIRGAN.

Micronuclear battery based on a coalescent energy transducer.

Micronuclear batteries harness energy from the radioactive decay of radioisotopes to generate electricity on a small scale, typically in the nanowatt or microwatt range. Contrary to chemical batteries, the longevity of a micronuclear battery is tied to the half-life of the used radioisotope, enabling operational lifetimes that can span several decades. Furthermore, the radioactive decay remains unaffected by environmental factors such as temperature, pressure and magnetic fields, making the micronuclear battery an enduring and reliable power source in scenarios in which conventional batteries prove impractical or challenging to replace.

Electronic structure of the strongly correlated electron system plutonium hexaboride: A study from single-particle approximations and many-body calculations.

The electronic structure of the strongly correlated electron system plutonium hexaboride is studied by using single-particle approximations and a many-body approach. Imaginary components of impurity Green's functions show that 5f and 5f manifolds are in conducting and insulating regimes, respectively. Quasi-particle weights and their ratio suggest that the intermediate coupling mechanism is applicable for Pu 5f electrons, and PuB might be in the orbital-selective localized state.

Experimental study on seismic characteristics of slope supported by long-short composite anti-slide piles.

In this study, a shaking table test was conducted on long-short composite anti-slide piles, the development process and dynamic response of cracks in a pile-supported slope were observed, and the failure mechanism of the slope was explored. The experiment showed that the failure of the pile-supported slope under an earthquake was a gradual process; cracks first occur at the top of the slope, where the support action of the piles was weak. As the input seismic action increased, cracks developed downwards along the slope.

Tunable and Non-Invasive Printing of Transmissive Interference Colors with 2D Material Inks.

Interference colors hold significant importance in optics and arts. Current methods for printing interference colors entail complex procedures and large-scale printing systems for the scarcity of inks that exhibit both sensitivity and tunability to external fields. The production of highly transparent inks capable of rendering transmissive colors has presented ongoing challenges.

Effects of Contact Surface Shape on Dynamic Lifetime and Strength of Molecular Bond Clusters under Displacement- and Force-Controlled Loading Conditions.

Many experimental and theoretical studies have shown that the mechanical properties of cells and the extracellular matrix can significantly affect the lifetime and strength of the adhesion clusters of molecular bonds. However, there are few studies on how the shape of the contact surface affects the lifetime and strength of the adhesion clusters of molecular bonds, especially theoretical studies in this area. An idealized model of focal adhesion is adopted, in which two rigid media are bonded together by an array of receptor-ligand bonds modeled as Hookean springs on a complex surface topography, which is described by three parameters: the surface shape factor β, the length of a single identical surface shape , and the amplitude of surface shapes .

An inorganic liquid crystalline dispersion with 2D ferroelectric moieties.

Electro-optical effect-based liquid crystal devices have been extensively used in optical modulation techniques, in which the Kerr coefficient reflects the sensitivity of the liquid crystals and determines the strength of the device's operational electric field. The Peterlin-Stuart theory and the O'Konski model jointly indicate that a giant Kerr coefficient could be obtained in a material with both a large geometrical anisotropy and an intrinsic polarization, but such a material is not yet reported. Here we reveal a ferroelectric effect in a monolayer two-dimensional mineral vermiculite.

Insights into ThB: Stability, Electronic Structure, and Interaction.

The interaction between nonmetal and metal atoms has attracted great interest in the development of organometallic compounds and their promising applications. In this study, we explored the interaction between boron and thorium atoms, based on the stable BTh coordination compound, by employing density functional theory calculations. We elucidated the stability and geometries of the BTh coordination compound and revealed the electron transfer from the metal atom Th to B, which is evidenced by the natural bond orbital calculations.

Research on collaborative edge network service migration strategy based on crowd clustering.

The innovative application of Crowd Intelligent Devices (CIDS) in edge networks has garnered attention due to the rapid development of artificial intelligence and computer technology. This application offers users more reliable and low-latency computing services through computation offloading technology. However, the dynamic nature of network terminals and the limited coverage of edge servers pose challenges, such as data loss and service interruption.

Burnout and depression in college students.

Research on burnout has garnered considerable attention since its inception. However, the ongoing debate persists regarding the conceptual model of burnout and its relationship with depression. Thus, we conducted a network analysis to determine the dimensional structure of burnout and the burnout-depression overlap.

An Electro-Optical Kerr Device Based on 2D Boron Nitride Liquid Crystals for Solar-Blind Communications.

Achieving light modulation in the spectral range of 200-280 nm is a prerequisite for solar-blind ultraviolet communication, where current technologies are mainly based on the electro-luminescent self-modulation of the ultraviolet source. External light modulation through the electro-birefringence control of liquid crystal (LC) devices has shown success in the visible-to-infrared regions. However, the poor stability of conventional LCs against ultraviolet irradiation and their weak electro-optical response make it challenging to modulate ultraviolet light.

Multi-domain feature joint optimization based on multi-view learning for improving the EEG decoding.

Background: Brain-computer interface (BCI) systems based on motor imagery (MI) have been widely used in neurorehabilitation. Feature extraction applied by the common spatial pattern (CSP) is very popular in MI classification. The effectiveness of CSP is highly affected by the frequency band and time window of electroencephalogram (EEG) segments and channels selected.

Electron correlation and relativistic effects on the electronic properties of a plutonium and americium mixed oxide (PuAmO): from single-particle approximation to dynamical mean-field theory.

First-principles calculations were performed on a plutonium and americium mixed oxide (PuAmO), aiming at revealing the effects of electron correlation, Pu/Am 5f-conduction electrons' hybridization, and relativity on its electronic properties. The many-body calculation suggests that the spin-orbit-coupling (SOC)-splitting of = 5/2 and = 7/2 manifolds are both in the weakly and moderately correlated states, respectively, implying that the coupling scheme is more appropriate for Pu/Am 5f electrons. The density of states, 5f occupation numbers, and Green's functions all suggest that both Pu and Am 5f electrons exhibit the coexistence of the localized and delocalized states.

Fault-Tolerant SINS/Doppler Radar/Odometer Integrated Navigation Method Based on Two-Stage Fault Detection Structure.

To improve the reliability of strapdown inertial navigation system (SINS)/Doppler radar/odometer integrated navigation system, the federated Kalman filter with two-stage fault detection structure is designed, and a fault-tolerant SINS/Doppler radar/odometer integrated navigation method is proposed. Firstly, the pre-fault detection module sets before the local filter, and the residual chi-square test in the carrier coordinate system is selected to detect the abrupt faults of Doppler radar and odometer. Then, the secondary-fault detection module emplaces between the local filter and the main filter, and the sequential probability ratio test (SPRT) is selected to further detect the ramp faults that are difficult to detect by the residual chi-square test.

MIMU Optimal Redundant Structure and Signal Fusion Algorithm Based on a Non-Orthogonal MEMS Inertial Sensor Array.

A micro-inertial measurement unit (MIMU) is usually used to sense the angular rate and acceleration of the flight carrier. In this study, multiple MEMS gyroscopes were used to form a spatial non-orthogonal array to construct a redundant MIMU system, and an optimal Kalman filter (KF) algorithm was established by a steady-state KF gain to combine array signals to improve the MIMU's accuracy. The noise correlation was used to optimize the geometric layout of the non-orthogonal array and reveal the mechanisms of influence of correlation and geometric layout on MIMU's performance improvement.