Changchun University

Interpretable machine learning for identifying mild cognitive impairment among Chinese patients with obstructive sleep apnea: a multicenter cross-sectional study

Mild cognitive impairment (MCI) is clinically relevant in obstructive sleep apnea (OSA). We developed and externally validated an interpretable machine-learning model for concurrent clinically defined MCI to support prioritization for formal cognitive assessment rather than diagn...

Seismic Signal Denoising via RRTO-Optimized VMD Combined with Spectral Kurtosis and Enhanced Wavelet Packet Thresholding

Abstract Seismic signal denoising is a key link to improve the interpretation accuracy of seismic data, especially in the complex noise background, where random noise and coherent noise will seriously interfere with the identification and extraction of effective signals. To this...

Multi-Scene Continuous Sign Language Recognition Based on Temporal–Frequency Enhancement and Discrete Cosine Transform Linear Attention

To address the adverse effects of complex acquisition conditions on continuous sign language recognition (CSLR) performance and the increasing computational cost of standard self-attention with increasing video sequence length, this paper proposes a continuous sign language recog...

Uncertainty-Aware structured decoding for Chinese Braille document transcription

Automatic transcription of braille documents remains challenging in document digitization settings, particularly under real imaging degradations such as uneven embossing, illumination variation, paper texture, skew, blur, and ghosting, which make braille dot presence uncertain an...

Tailoring the Optical Properties of MOCVD Grown InGaAs/InAlGaAs MQWs with GaAs Insertion‑Layer

Abstract InGaAs/InAlGaAs multiple quantum wells (MQWs) are widely adoped as the active region of near‑infrared semiconductor lasers due to their excellent optical performance and broad application prospects. In this work, we systematically investigate the effects of the thickness...

AI investment (In)congruence and innovation resilience in knowledge-intensive firms: unpacking the boundary role of knowledge structure

Purpose Drawing on the knowledge-based view (KBV), this study aims to deconstruct firm-level artificial intelligence (AI) investment into a supply-demand structure to examine how the (in)congruence between supply-side AI investment (SAI) and demand-side AI investment (DAI) affect...

An oncolytic virus armed with fowl adenovirus fiber-modified recombinant TRAIL enhances tumor targeting and immunotherapy activity

Oncolytic viruses have emerged as a promising strategy in cancer immunotherapy and have been applied to the treatment of various tumors. We previously demonstrated that oncolytic adenoviruses engineered expressing tumor necrosis factor-related apoptosis-inducing ligand (TRAIL) co...

An atlas of colonization factors in the mouse gut microbiome reveals phylogenetically structured repertoires and infection-stage-associated variation during Toxoplasma gondii infection in mice

ABSTRACT Colonization factors (CFs) comprise CF-associated gene families related to microbial establishment, persistence, host interaction, and gut ecological fitness, but their organization and variation in the mouse gut microbiome remain poorly defined. We integrated the Mouse...

Dielectrophoretic Assembly of BaTiO 3 Radiative Cooling Textiles for Proactive Urban Cooling

ABSTRACT The urban heat island (UHI) effect threatens sustainable urban development. Passive daytime radiative cooling textiles are promising but face a trade‐off between optical performance and mechanical–chemical stability. Here, we report the first use of dielectrophoretic ass...

Benzoxazine-Modified Phenolic Triazine Resin with Improved Curing, Toughness, and Balanced Thermomechanical Properties, Enabling Hot-Melt Processing

Abstract Phenolic triazine (PT) resins suffer from high curing temperatures, inherent brittleness, and poor adaptability with hot-melt prepreg processing. To address these restrictions, benzoxazine (BZ) was introduced as a modifier for low-temperature curing, toughening, good hot...

Development of a Dual-Mode Measurement and Control System with Energy Feedback Optimization for a Retrofitted NEV Powertrain Dynamometer

Retrofitting an internal combustion engine (ICE) dynamometer test bench for electric motor testing introduces significant measurement and control challenges. The two modes differ fundamentally in torque dynamics, communication protocols, and energy flow characteristics. This stud...

Genome-resolved analysis reveals disruption of gut microbial vitamin B and K 2 biosynthesis during Toxoplasma gondii infection in mice

ABSTRACT Toxoplasma gondii infection remodels the gut microbiome, yet its impact on microbial vitamin biosynthetic potential and host redox metabolism remains unclear. Here, we integrated mouse gut metagenomes with publicly available metagenome-assembled genomes (MAGs) to constru...

Breaking of π‐Continuity by σ‐Linkers in Covalent Organic Frameworks for Efficient Photoreduction and Recovery of Gold From Electronic Waste

Photoreduction of metal ions plays a central role in the recovery of precious metals from electronic waste, yet its design is still largely governed by a semiconductor paradigm that links extended π-conjugation and long-range charge transport to superior performance. Herein, we c...

Dynamic load analysis of gearbox suspenders for metro vehicles based on field tests and numerical simulation

The gearbox suspender is a critical suspension component that ensures the operational stability of the traction transmission system in metro vehicles. However, after 1.3 million km of service operation, cracks were detected at the same position on the gearbox bracket of multiple...

KneeFusionNet Enables Accurate and Efficient Comprehensive Detection of Knee Ligament Injuries on Magnetic Resonance Imaging: A Multicenter Validation Study

Purpose To develop and externally validate KneeFusionNet, a multimodal deep learning model for detecting anterior cruciate ligament (ACL), posterior cruciate ligament (PCL), medial collateral ligament (MCL), and lateral collateral ligament (LCL) injuries on knee magnetic resonanc...

Gas Identification Driven by Dynamic Response Fragments and Multi-Task Learning

Abstract The electronic nose system has attracted much attention due to its wide application in industrial detection, atmospheric monitoring and noninvasive disease diagnosis. However, the traditional methods are limited in accuracy and generalization due to the lack of selectivi...

Waveform-preserving source-independent wave-equation-based local-scale traveltime inversion: Application to the SEG Chevron 2014 blind test dataset

Summary Full Waveform Inversion (FWI) leverages the amplitude and phase of full wavefield seismic data to obtain high-resolution subsurface structures by minimizing an objective function. However, FWI encounters severe cycle-skipping issues when the seismic data lack low-frequenc...

Rice Cultivation Duration Is Associated with Changes in Potential CO2 Production, Q10, Enzyme Activity, and Microbial Diversity in Saline–Alkali Soils

Saline–alkali soils are important reserve resources for agricultural production. In western Jilin Province, China, large areas of saline–alkali land have been reclaimed as paddy fields; however, their carbon cycling responses to long-term rice cultivation and warming remain uncle...

From graph Laplacian to ring polymer dynamics: part I

Abstract A graph-theoretic formulation of overdamped Langevin dynamics and constitutive equations for ring polymers is developed. The polymer molecule is represented as a bead–spring network whose connectivity is described by a graph Laplacian. Starting from overdamped stochastic...

Exponential convergence can happen in weighted Birkhoff averages via quasi‐periodicity with arbitrary nonresonance and low regularity

Abstract Since Krengel's work [Monatsh. Math. 86 (1978/79), 3–6] in 1978, it has been widely known that no effective rate of convergence exists in the ergodic theorem. For toral translations, however, by choosing appropriate weights one can accelerate the convergence of ergodic a...