Northwestern Polytechnical University

Multi-Granularity Graph Neural Network for Satellite-Assisted Marine Environmental Field Reconstruction over Sparse Observation Grids

Marine remote sensing combines broad-coverage satellite observations of the ocean surface with sparse in-situ and underwater observations. However, reconstructing continuous three-dimensional environmental fields remains challenging because of irregular sampling, vertical non-sta...

HSSynergy: scale-aware hierarchical attention for interpretable drug synergy prediction

Abstract Combination therapy offers a promising strategy for cancer treatment by reducing toxicity and overcoming drug resistance. However, existing substructure-based prediction methods may struggle to effectively capture the scale-specific features of substructure interactions...

Templated growth of phase-pure two-dimensional perovskite for durable solar cells

Abstract The impure phase in typical solution-processed two-dimensional/three-dimensional (2D/3D) perovskite heterostructures limit the performance and stability of perovskite solar cells. We overcome this limitation through a templated growth strategy utilizing excess lead iodid...

Oxygen Serves as an Electron Acceptor for Efficient Photocatalytic Acetylene Hydrochlorination in Seawater

ABSTRACT The photocatalytic acetylene hydrochlorination with H 2 O as hydrogen source and Cl – as chlorine source in seawater is a highly promising alternative to traditional thermocatalytic acetylene hydrochlorination, but seriously suffers from poor performance due to the rapid...

MAC1toK: relax feature matching with maximal cliques for 3D registration

Abstract The majority of existing point cloud registration (PCR) methods exhibit performance degradation under extremely low inlier ratios. To address this limitation, this paper presents a robust learning-free estimator called MAC1to K , which relaxes the feature matching with m...

Ship-radiated noise separation via auditory scene analysis-guided deep learning

Ship-radiated noise is an important acoustic source in passive underwater monitoring, but marine recordings often contain overlapping components from multiple sources, which can hinder target-related analysis. To address this problem, this paper develops a ship-radiated noise sep...

A Defect Detection Method for Rail Ultrasonic B-Scan Images Based on a Multi-Scale Dense Attention Network

Rail internal defects pose significant threats to railway operational safety, and ultrasonic B-scan imaging provides an effective nondestructive testing approach for visualizing subsurface rail conditions. However, manual interpretation of B-scan images is time-consuming and depe...

Dendrite-Network-Assisted Multi-Source Domain Generalization for Fault Diagnosis in Rotating Machinery

Intelligent fault diagnosis is crucial for the safe, efficient operation of rotating machinery. Domain adaptation models can mitigate distribution shifts from diverse operating conditions, but their over-reliance on annotated target domain data limits their use under unknown and...

Flutter characteristics of a two-dimensional prepositive elliptical wing–main wing combined configuration

Flutter is a complex dynamic aeroelastic problem that poses a significant threat to flight safety, making its mitigation a critical focus of aeronautical research. This study proposes a two-dimensional prepositive elliptical wing–main wing combined configuration (abbreviated as p...

The spectrum of a compact internal space. I. Gauge structure and fermion content

We present a spectral framework for gauge structure and fermion content. The basic datum is a discrete spectrum with finite multiplicities, generating a mass tower. Physical quantities are defined by convergent spectral sums and closed analytic expressions. The construction start...

The spectrum of a compact internal space. II. Effective couplings and mass scales

This paper studies the numerical consequences of a fixed compact spectral datum, taken here to be the Laplace and Dirac spectra of RP^3, together with a specified scale-flow prescription. The structural content supported by this datum, namely the gauge algebra, the fermion repres...

Vaporization-Guided Morphology Evolution Enables Precision Control in Blade-Coated Organic Solar Cells

Abstract Controlling the morphology evolution of blade-coated bulk-heterojunction active layers is crucial for achieving high-efficiency organic solar cells (OSCs), yet remains challenging because rapid solvent evaporation and unbalanced donor–acceptor aggregation often lead to p...

Research on music audio chord feature extraction and similarity calculation based on transformer and deep metric learning

Aiming at the problem that existing methods have difficulty balancing chord recognition accuracy and feature discrimination, this paper proposes the Transformer Chord Metric Extractor (TCME). The model effectively captures the long-range harmony dependence of music by designing a...

Arc-DED additive manufacturing of high-Zn-content Al-Zn-Mg-Cu alloy assisted by interlayer remelting and mechanical hammering

Arc-directed energy deposition (Arc-DED) is a promising additive manufacturing technology for fabricating medium-to-large-scale and lightweight structural components. The development of high-strength aluminum alloys is crucial for optimising the performance of these Arc-DED-manuf...

The spectrum of a compact internal space. I. Gauge structure and fermion content

We present a spectral framework for gauge structure and fermion content. The basic datum is a discrete spectrum with finite multiplicities, generating a mass tower. Physical quantities are defined by convergent spectral sums and closed analytic expressions. The construction start...

Physics-informed neural predictor-corrector guidance for time-coordinated reentry of hypersonic glide vehicles

Abstract This paper addresses the time-coordinated reentry guidance problem for multiple hypersonic glide vehicles and proposes a physics-informed neural predictor-corrector guidance method. In the proposed framework, the path and terminal constraints are mapped to the bank-angle...

Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead

Code generation represents a critical intersection of Software Engineering (SE) and Artificial Intelligence (AI). Within this broader landscape, Verilog, as a representative hardware description language (HDL), is fundamental to Electronic Design Automation (EDA), recent research...

EngageCue: Enabling Balanced Engagement in Face-to-Face Group Collaboration via AI Cues Through Smart Glasses

In face-to-face group collaboration, uneven engagement often undermines efficiency and interaction quality. Although AI and wearable devices are increasingly applied to support collaboration, existing approaches largely remain confined to online or screen-based environments, leav...

Hard Carbon Networks for Mitigating Graphite Lattice Strain Under Extreme‑Low‑Temperature Fast Charging

ABSTRACT Low‐temperature fast charging of lithium‐ion batteries is primarily constrained by sluggish reaction kinetics and mechanical degradation of graphite anodes. Here, a kinetic–structural coordination strategy based on a 15 wt.% hard carbon (HC) percolating network embedded...

A Dragonfly Wing-InspiredMXene-Reinforced Soy ProteinAdhesive with Balanced Strength, Toughness, and Multifunctionality

Abstract Replacing petroleum-derived wood adhesives with soy protein isolate (SPI) offers a sustainable alternative, yet the practical application of SPI is severely hindered by its intrinsic poor water resistance and mechanical fragility. To overcome these drawbacks, we develope...