Beijing Academy of Artificial Intelligence

Neutrophil to Lymphocyte Ratio and Neurological Outcome in Ischemic Stroke at 4.5 to 24 Hours: A Post Hoc Analysis of TRACE-III Trial

Whether neutrophil to lymphocyte ratio (NLR), as a marker of increased inflammatory response, modifies the efficacy and safety of tenecteplase is uncertain in patients 4.5–24 h after stroke onset. We investigated this in the Tenecteplase Reperfusion Therapy in Acute Ischemic Cere...

Data-driven safe adaptive dynamic programming with hybrid lifelong learning in wastewater treatment processes

The wastewater treatment process (WWTP) is a critical component driving sustainable industrial development. The monitoring and control of the dissolved oxygen (DO) concentration play a vital role in the WWTP. An adaptive utility function, a control barrier function, and an adapti...

Anti-parity-time-symmetric gyroscope via high-order exceptional points

Exceptional points (EPs), which arise from non-Hermitian systems, have been extensively investigated for the development of high-performance sensors. However, operating a non-Hermitian sensor at a high-order EP (HOEP) to achieve extreme performance requires strict and precise con...

Computational mapping of full interfacial segregation spectrum for designing core-shell θ' precipitates in Al-Cu-based alloys

With rising demand for lightweight high-temperature structural materials in aerospace and automotive industries, developing heat-resistant aluminum alloys has become a critical challenge. This work employs high-throughput density functional theory and machine learning to systemat...

Adaptive graph structure learning for skeleton-based gait recognition

Gait recognition, which identifies individuals based on their walking patterns, offers a contactless and robust biometric approach. Skeleton-based gait recognition using graph convolutional networks (GCNs) is favored for its robustness against external variations, such as clothin...

Resilient Fully Distributed Event‐Triggered Consensus Against DSS Attacks in Nonlinear MAS via Fractional‐Order Super‐Twisting Sliding Mode Control

ABSTRACT This paper proposes a fully distributed event‐triggered control strategy for nonlinear multi‐agent systems (MASs) that is resilient to distributed sequential scaling (DSS) attacks. A key innovation is the integration of fractional‐order super‐twisting sliding mode contro...

Beyond statistical thresholds: Mapping sequential ATN cascade transitions via brain structural topography in Alzheimer’s disease

Alzheimer’s disease is widely conceptualized as a biological continuum initiated by amyloid-β (Aβ) accumulation, followed by tau aggregation and neurodegeneration. Although the ATN framework is commonly used to define disease stages, its static biomarker categories may not fully...

Design and analysis of an underwater vectored thruster employing spherical actuator

Underwater vectored thruster is an important development direction for the propulsion system of autonomous underwater vehicles. However, conventional vectored thruster systems generally consist of multiple actuators and complex transmission structures, which results in large syst...

Mechanical Programming of Hollow DNA Nanocapsules Rewires In Vivo Trafficking

ABSTRACT DNA nanostructures are programmable, biocompatible platforms for biomedicine; however, their mechanical properties are coupled to sequence and structural dimensions, limiting control over stiffness. Here, we report a paradigm shift from static design to mechanical engine...

Mechanical Programming of Hollow DNA Nanocapsules Rewires In Vivo Trafficking

ABSTRACT DNA nanostructures are programmable, biocompatible platforms for biomedicine; however, their mechanical properties are coupled to sequence and structural dimensions, limiting control over stiffness. Here, we report a paradigm shift from static design to mechanical engine...

TPHH: a long-term (1901–2023) high-resolution (1∕30°) near-surface humidity dataset for the Tibetan Plateau generated via spatial downscaling based on hybrid-structure deep learning

The Tibetan Plateau acts as the “Asian Water Tower” and faces regional amplified warming compared to the global climate change baseline. Given the Tibetan Plateau's pronounced alpine terrain, i.e., significant elevation gradients within short horizontal distances, studies on clim...

Transdiagnostic latent factors dissociating depression and anxiety through reinforcement learning

The comorbidity of depression and anxiety has long been recognized. While mainly characterized as mood dysregulation, depression and anxiety symptoms are also manifested in learning and decision-making deficits. However, the specific cognitive mechanisms that are common to both d...

Accurate and explainable ICD-10-CM diagnosis coding through multi-stage model adaptation and evidence-guided verification

The International Classification of Diseases (ICD) coding system is central to reimbursement, registry construction, and secondary analysis, yet automated inpatient International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) diagnosis coding from d...

A multimodal deep learning method based on multiple medical images for Fuchs endothelial corneal dystrophy diagnosis

To establish a multimodal deep learning network for the automated diagnosis of Fuchs endothelial corneal dystrophy (FECD). The ResNet-50 neural network was trained and validated using patients with FECD, patients with other corneal endothelial disorders, and healthy controls. At...

Anomaly Detection in Long-term Time Series with Transformer and Variational Autoencoder

Abstract Anomaly detection is crucial for ensuring system reliability and providing early warnings of potential failures. However, long-term time-series anomaly detection remains challenging because anomalous events are rare, anomaly patterns are diverse, and temporal dependencie...

Computation-bandwidth-memory trade-offs: a unified paradigm for AI infrastructure

Abstract Large-scale artificial intelligence (AI) models are fundamentally transforming industries and redefining the paradigm of human–machine collaboration. While the technological revolution signals a new era of machine intelligence, the continued scaling of these models has e...

Odometry and Mapping for Complex Environment Perception Under Partial-View Sensing

Dense partial-view LiDAR observations are attractive for outdoor perception, but limited overlap and viewpoint sensitivity make odometry and mapping less reliable than with spinning LiDARs. Many recent algorithms for this sensing regime are built as LiDAR-inertial odometry framew...

The probability of state transition of five diabetic complications and their influencing factors based on multi-state markov models: evidence from a Chinese cohort study

Diabetes-related complications remain a leading cause of disability and mortality among individuals with diabetes and substantially impair patients’ health-related quality of life. In this study, we employed a multi-state Markov model (MSM) to characterize transition probabilitie...

CDSB: accelerating connectomics workflow via Content-Decoupled Schrödinger Bridge

Abstract Background Large-scale connectomics requires the nanometer-scale resolution of electron microscopy to resolve ultrastructural details, but its acquisition is time- and labor-intensive. In contrast, high-throughput light microscopy offers high throughput but lacks the spa...

Interpretable multi-modal hierarchical framework to support cytomorphological analysis of hematologic cancers

Cytomorphological analysis of bone marrow aspirate (BMA) and peripheral blood smears (PBS) remains a diagnostic cornerstone in hematology. Machine-assisted analysis could support diagnostic workflows, but remains challenging due to the imbalanced prevalence of hematologic maligna...