The integration of large-scale foundation models(e.g.,GPT series and AlphaFold)into oncology is fundamentally transforming both research methodologies and clinical practices,driven by unprecedented advancements in com...The integration of large-scale foundation models(e.g.,GPT series and AlphaFold)into oncology is fundamentally transforming both research methodologies and clinical practices,driven by unprecedented advancements in computational power.This review synthesizes recent progress in the application of large language models to core oncological tasks,including medical imaging analysis,genomic interpretation,and personalized treatment planning.Underpinned by advanced computational infrastructures,such as graphics processing unit/tensor processing unit clusters,heterogeneous computing,and cloud platforms,these models enable superior representation learning and generalization across multimodal data sources.This review examines how these infrastructures overcome key bottlenecks in intelligent oncology through scalable optimization strategies,including mixed-precision training,memory optimization,and heterogeneous computing.Alongside these technical advancements,the review explores pressing challenges,such as data heterogeneity,limited model interpretability,regulatory uncertainties,and the environmental impact of artificial intelligence(AI)systems.Special emphasis is placed on emerging solutions,encompassing green AI and edge computing,which offer promising approaches for low-resource deployment scenarios.Additionally,the review highlights the critical role of interdisciplinary collaboration among oncology,computer science,ethics,and policy to ensure that AI systems are not only powerful but also transparent,safe,and clinically relevant.Finally,the review outlines potential avenues for future research aimed at developing robust,scalable,and human-centered frameworks for intelligent oncology.展开更多
Dear Editor,In this letter,we focus on the algebraic relationship between the coefficient matrices and the solution of the stochastic algebraic Riccati equation.It is revealed that,if the coefficient matrices are in a...Dear Editor,In this letter,we focus on the algebraic relationship between the coefficient matrices and the solution of the stochastic algebraic Riccati equation.It is revealed that,if the coefficient matrices are in an algebra,then the solution(and also the control gain in many cases)is also in the same algebra.The main result is verified by a numerical simulation.展开更多
Carbonate reservoirs are vital energy storage spaces,including for oil,shale gas,geothermal,and hydrogen energy.Accurate prediction of reservoir characteristics such as permeability and saturated fluid types through n...Carbonate reservoirs are vital energy storage spaces,including for oil,shale gas,geothermal,and hydrogen energy.Accurate prediction of reservoir characteristics such as permeability and saturated fluid types through noninvasive approaches is crucial for optimal storage capability.In this paper,we combine a linear Boolean model and a discrete Fourier transform approach to generate pore‐and fracturepore‐type carbonate rocks.Elastic wave velocity information is necessary to predict permeability in different rock geometry models.Permeability is calculated using the lattice Boltzmann method,and the elastic wave velocity is calculated using a finite element method based on a minimal energy approach.Saturated fluids that contain oil and gas were both considered.Our simulated results reveal that,for pore‐type carbonate,empirical formulas were proposed to estimate permeability through elastic data.However,in fracture‐pore carbonate rocks,the precision of the empirical formula is compromised due to the presence of significant conductive channels within the rock matrix.We also find that using S‐wave velocity and permeability relationships to distinguish oil and gas is better than using P‐wave velocity and permeability relationships under low‐porosity conditions.展开更多
Next-GenerationNetworks(NGNs)demand high resilience,dynamic adaptability,and efficient resource utilization to enable ubiquitous connectivity.In this context,the Space-Air-Ground Integrated Network(SAGIN)architecture ...Next-GenerationNetworks(NGNs)demand high resilience,dynamic adaptability,and efficient resource utilization to enable ubiquitous connectivity.In this context,the Space-Air-Ground Integrated Network(SAGIN)architecture is uniquely positioned to meet these requirements.However,conventional NGN routing algorithms often fail to account for SAGIN’s intrinsic characteristics,such as its heterogeneous structure,dynamic topology,and constrained resources,leading to suboptimal performance under disruptions such as node failures or cyberattacks.To meet these demands for SAGIN,this study proposes a resilience-oriented routing optimization framework featuring dynamic weighting and multi-objective evaluation.Methodologically,we define three core routing performance metrics,quantified through a four-dimensionalmodel,encompassing robustness Rd,resilience Rr,adaptability Ra,and resource utilization efficiency Ru,and integrate them into a comprehensive evaluation metric.In simulated SAGIN environments,the proposed Multi-Indicator Weighted Resilience Evaluation Algorithm(MIW-REA)demonstrates significant improvements in resilience enhancement,recovery acceleration,and resource optimization.It maintains 82.3%service availability even with a 30%node failure rate,reduces Distributed Denial of Service(DDoS)attack recovery time by 43%,decreases bandwidth waste by 23.4%,and lowers energy consumption by 18.9%.By addressing challenges unique to the SAGIN network,this research provides a flexible real-time solution for NGN routing optimization that balances resilience,efficiency,and adaptability,advancing the field.展开更多
In this paper,a typical experiment is carried out based on a high-resolution air-sea coupled model,namely,the coupled ocean-atmosphere-wave-sediment transport(COAWST)model,on both heterogeneous many-core(SW)and homoge...In this paper,a typical experiment is carried out based on a high-resolution air-sea coupled model,namely,the coupled ocean-atmosphere-wave-sediment transport(COAWST)model,on both heterogeneous many-core(SW)and homogenous multicore(Intel)supercomputing platforms.We construct a hindcast of Typhoon Lekima on both the SW and Intel platforms,compare the simulation results between these two platforms and compare the key elements of the atmospheric and ocean modules to reanalysis data.The comparative experiment in this typhoon case indicates that the domestic many-core computing platform and general cluster yield almost no differences in the simulated typhoon path and intensity,and the differences in surface pressure(PSFC)in the WRF model and sea surface temperature(SST)in the short-range forecast are very small,whereas a major difference can be identified at high latitudes after the first 10 days.Further heat budget analysis verifies that the differences in SST after 10 days are mainly caused by shortwave radiation variations,as influenced by subsequently generated typhoons in the system.These typhoons generated in the hindcast after the first 10 days attain obviously different trajectories between the two platforms.展开更多
Defining an ERBB2(HER2/neu)gene amplification status is critical to guiding human epidermal growth factor receptor 2(HER2)-targeted therapy in breast cancer.Up to 40%of breast cancer patients are reported as having an...Defining an ERBB2(HER2/neu)gene amplification status is critical to guiding human epidermal growth factor receptor 2(HER2)-targeted therapy in breast cancer.Up to 40%of breast cancer patients are reported as having an immunohistochemistry(IHC)of HER22+and requiring additional testing using fluorescence in situ hybridization to confirm the results.This paper aims to establish an automatically weighted calibration deep learning(AWCDL)algorithm to predict ERBB2 amplification based on IHC images.In this study,we applied IHC HER22+images from 1,073 breast cancer patients at three cancer centers in China and extracted 376,099 tiles.Among these,269,664 tiles were used for internal and external validation.The designed AWCDL consists of two steps.In Step 1,the internal validation achieved an accuracy of 89%,with a specificity of 0.89 and a sensitivity of 0.89.The external validation in the two other centers showed an average accuracy of 85%,with a specificity of 0.86 and a sensitivity of 0.82.In Step 2,the model achieved higher accuracy for the slides predicted as negative in Step 1 by automatically calibrating the weight.Collectively,these results suggest that this AWCDL model has successfully proved useful as an alternative method to fluorescence in situ hybridization for assessing the ERBB2 amplification status in breast cancer.展开更多
Sodium-ion batteries have emerged as promising alternatives to lithium-ion batteries due to their abundant raw material reserves,low cost,enhanced safety,and environmental sustainability.Na_(2)Fe_(2)OS_(2),featuring a...Sodium-ion batteries have emerged as promising alternatives to lithium-ion batteries due to their abundant raw material reserves,low cost,enhanced safety,and environmental sustainability.Na_(2)Fe_(2)OS_(2),featuring a layered anti-perovskite structure,has attracted significant interest for its high capacity and facile synthesis.In this study,density functional theory calculations were performed to systematically investigate the phase stability,ionic conductivity,and voltage characteristics of Na_(2)Fe_(2)OS_(2)as a model system for anti-perovskite layered cathode materials.The compound exhibits excellent phase stability,and its equilibrium potential was calculated for the series Na_(x)Fe_(2)OCh_(2)(0<±<2)(where Ch represents chalcogenides).Naion transport analysis using the climbing image nudged elastic band method reveals a relatively low migration barrier(~0.47eV)along a dingonal pathway,indicating efficient Na^(+)mobility.To expand the materials design space,we systematically explored the effects of substituting Fe with various transition metals and replacing S with Se in NaaTM_(2)OCh_(2)structures.Among the variants studied,Na_(2)Mn_(2)OS_(2) demonstrates the most favorable combination of high voltage(~2.51V),robust phase stability,and superior energy density(~427 W-h/kg).This comprehensive comparison of transition metal substitutions provides vnluable insights for the rational design and experimental development of next-generation anti-perovskite layered cathode materials for sodium-ion batteries.展开更多
Combining the advantages of high efficiency,low-pressure drop,and large throughput,the pore arrayenhanced tube-in-tube microchannel(PA-TMC) is a promising microreactor for industrial applications.However,most of the m...Combining the advantages of high efficiency,low-pressure drop,and large throughput,the pore arrayenhanced tube-in-tube microchannel(PA-TMC) is a promising microreactor for industrial applications.However,most of the mass transfer takes place in the upstream pore region,while the contribution of the downstream annulus is limited.In this work,helical wires were introduced into the annulus by adhering to the outer surface of the inner tube.Mixing behavior and mass transfer of liquid-liquid twophase flow in PA-TMC with different helical wires have been systematically studied by a combination of experiments and volume of fluid(VOF) method.The introduction of helical wires improves the overall volumetric mass transfer coefficient KLa by up to 133% and the mass transfer efficiency E by up to 117%.The simulation results show that the helical wire brings extra phase mixing regions and increases the specific interface area,while accelerating the fluid flow and expanding the area of enhanced turbulent dissipation rate.Influences of helical wires in various configurations are compared by the comprehensive index I concerning the pressure drop and mass transfer performance simultaneously and a new correlation between KLa and specific energy consumption φ is proposed.This research deepens the understanding of the mixing behavior and mass transfer in the PA-TMCs and provides practical experience for the process intensification of microchannel reactors.展开更多
Accurate recognition of flight deck operations for carrier-based aircraft, based on operation trajectories, is critical for optimizing carrier-based aircraft performance. This recognition involves understanding short-...Accurate recognition of flight deck operations for carrier-based aircraft, based on operation trajectories, is critical for optimizing carrier-based aircraft performance. This recognition involves understanding short-term and long-term spatial collaborative relationships among support agents and positions from long spatial–temporal trajectories. While the existing methods excel at recognizing collaborative behaviors from short trajectories, they often struggle with long spatial–temporal trajectories. To address this challenge, this paper introduces a dynamic graph method to enhance flight deck operation recognition. First, spatial–temporal collaborative relationships are modeled as a dynamic graph. Second, a discretized and compressed method is proposed to assign values to the states of this dynamic graph. To extract features that represent diverse collaborative relationships among agents and account for the duration of these relationships, a biased random walk is then conducted. Subsequently, the Swin Transformer is employed to comprehend spatial–temporal collaborative relationships, and a fully connected layer is applied to deck operation recognition. Finally, to address the scarcity of real datasets, a simulation pipeline is introduced to generate deck operations in virtual flight deck scenarios. Experimental results on the simulation dataset demonstrate the superior performance of the proposed method.展开更多
The Heterogeneous Capacitated Vehicle Routing Problem(HCVRP),which involves efficiently routing vehicles with diverse capacities to fulfill various customer demands at minimal cost,poses an NP-hard challenge in combin...The Heterogeneous Capacitated Vehicle Routing Problem(HCVRP),which involves efficiently routing vehicles with diverse capacities to fulfill various customer demands at minimal cost,poses an NP-hard challenge in combinatorial optimization.Recently,reinforcement learning approaches such as 2D Array Pointer Networks(2D-Ptr)have demonstrated remarkable speed in decision-making by modeling multiple agents’concurrent choices as a sequence of consecutive actions.However,these learning-based models often struggle with generalization,meaning they cannot seamlessly adapt to new scenarios with varying numbers of vehicles or customers without retraining.Inspired by the potential of multi-teacher knowledge distillation to harness diverse knowledge from multiple sources and craft a comprehensive student model,we propose to enhance the generalization capability of 2D-Ptr through Multiple Teacher-forcing Knowledge Distillation(MTKD).We initially train 12 unique 2D-Ptr models under various settings to serve as teacher models.Subsequently,we randomly sample a teacher model and a batch of problem instances,focusing on those where the chosen teacher performed best.This teacher model then solves these instances,generating high-reward action sequences to guide knowledge transfer to the student model.We conduct rigorous evaluations across four distinct datasets,each comprising four HCVRP instances of varying scales.Our empirical findings underscore the proposed method superiority over existing learning-based methods in terms of both computational efficiency and solution quality.展开更多
The efficiency of carrier-based aircraft support operation scheduling critically impacts aircraft carrier operational effectiveness by determining sortie generation rates,yet faces significant challenges in complex de...The efficiency of carrier-based aircraft support operation scheduling critically impacts aircraft carrier operational effectiveness by determining sortie generation rates,yet faces significant challenges in complex deck environments characterized by resource coupling,dynamic constraints,and highdimensional state-action spaces.Traditional optimization algorithms and vanilla reinforcement learning(RL)struggle with computational inefficiency,sparse rewards,and adaptability to dynamic scenarios,while human expert systems are constrained by the quality of expert knowledge,and poor expert guidance may even have a negative impact.To address these limitations,this paper proposes a human experience-guided actor-critic reinforcement learning framework that synergizes domain expertise with adaptive learning.First,a dynamic Markov decision process(MDP)model is developed to rigorously simulate carrier deck operations,explicitly encoding constraints on positions,resources,and collision avoidance.Building upon this foundation,a human experience database is constructed to enable real-time pattern-matching-based intervention during agent-environment interactions,dynamically correcting wrong actions to avoid catastrophic states while refining exploration efficiency.Finally,the policy and value network objectives are reshaped to incorporate human intent through hybrid reward functions and adaptive guidance weighting,ensuring balanced integration of expert knowledge with RL's exploration capabilities.Extensive simulations across three scenarios demonstrate superior performance compared to state-of-the-art methods and maintain robustness under suboptimal human guidance.These results validate the framework's ability to harmonize human expertise with adaptive learning,offering a practical solution for real-world carriers.展开更多
Non-line-of-sight imaging recovers hidden objects around the corner by analyzing the diffuse reflection light on the relay surface that carries hidden scene information.Due to its huge application potential in the fie...Non-line-of-sight imaging recovers hidden objects around the corner by analyzing the diffuse reflection light on the relay surface that carries hidden scene information.Due to its huge application potential in the fields of autonomous driving,defense,medical imaging,and post-disaster rescue,non-line-of-sight imaging has attracted considerable attention from researchers at home and abroad,especially in recent years.The research on non-line-of-sight imaging primarily focuses on imaging systems,forward models,and reconstruction algorithms.This paper systematically summarizes the existing non-line-of-sight imaging technology in both active and passive scenes,and analyzes the challenges and future directions of non-line-of-sight imaging technology.展开更多
Accurate wind speed measurements on maritime vessels are crucial for weather forecasting,sea state prediction,and safe navigation.However,vessel motion and challenging environmental conditions often affect measurement...Accurate wind speed measurements on maritime vessels are crucial for weather forecasting,sea state prediction,and safe navigation.However,vessel motion and challenging environmental conditions often affect measurement precision.To address this issue,this study proposes an innovative framework for correcting and predicting shipborne wind speed.By integrating a main network with a momentum updating network,the proposed framework effectively extracts features from the time and frequency domains,thereby allowing for precise adjustments and predictions of shipborne wind speed data.Validation using real sensor data collected at the Qingdao Oceanographic Institute demonstrates that the proposed method outperforms existing approaches in single-and multi-step predictions compared to existing methods,achieving higher accuracy in wind speed forecasting.The proposed innovative approach offers a promising direction for future validation in more realistic maritime onboard scenarios.展开更多
The Dynamical Density Functional Theory(DDFT)algorithm,derived by associating classical Density Functional Theory(DFT)with the fundamental Smoluchowski dynamical equation,describes the evolution of inhomo-geneous flui...The Dynamical Density Functional Theory(DDFT)algorithm,derived by associating classical Density Functional Theory(DFT)with the fundamental Smoluchowski dynamical equation,describes the evolution of inhomo-geneous fluid density distributions over time.It plays a significant role in studying the evolution of density distributions over time in inhomogeneous systems.The Sunway Bluelight II supercomputer,as a new generation of China’s developed supercomputer,possesses powerful computational capabilities.Porting and optimizing industrial software on this platform holds significant importance.For the optimization of the DDFT algorithm,based on the Sunway Bluelight II supercomputer and the unique hardware architecture of the SW39000 processor,this work proposes three acceleration strategies to enhance computational efficiency and performance,including direct parallel optimization,local-memory constrained optimization for CPEs,and multi-core groups collaboration and communication optimization.This method combines the characteristics of the program’s algorithm with the unique hardware architecture of the Sunway Bluelight II supercomputer,optimizing the storage and transmission structures to achieve a closer integration of software and hardware.For the first time,this paper presents Sunway-Dynamical Density Functional Theory(SW-DDFT).Experimental results show that SW-DDFT achieves a speedup of 6.67 times within a single-core group compared to the original DDFT implementation,with six core groups(a total of 384 CPEs),the maximum speedup can reach 28.64 times,and parallel efficiency can reach 71%,demonstrating excellent acceleration performance.展开更多
The purpose of infrared and visible image fusion is to create a single image containing the texture details and significant object information of the source images,particularly in challenging environments.However,exis...The purpose of infrared and visible image fusion is to create a single image containing the texture details and significant object information of the source images,particularly in challenging environments.However,existing image fusion algorithms are generally suitable for normal scenes.In the hazy scene,a lot of texture information in the visible image is hidden,the results of existing methods are filled with infrared information,resulting in the lack of texture details and poor visual effect.To address the aforementioned difficulties,we propose a haze-free infrared and visible fusion method,termed HaIVFusion,which can eliminate the influence of haze and obtain richer texture information in the fused image.Specifically,we first design a scene information restoration network(SIRNet)to mine the masked texture information in visible images.Then,a denoising fusion network(DFNet)is designed to integrate the features extracted from infrared and visible images and remove the influence of residual noise as much as possible.In addition,we use color consistency loss to reduce the color distortion resulting from haze.Furthermore,we publish a dataset of hazy scenes for infrared and visible image fusion to promote research in extreme scenes.Extensive experiments show that HaIVFusion produces fused images with increased texture details and higher contrast in hazy scenes,and achieves better quantitative results,when compared to state-ofthe-art image fusion methods,even combined with state-of-the-art dehazing methods.展开更多
Structure and composition of Earth are fundamental importance in exploring the dynamic evolution of the crust and mantle.The Qinling Orogenic Belt(QOB)is located between the North China plate and the South China Plate...Structure and composition of Earth are fundamental importance in exploring the dynamic evolution of the crust and mantle.The Qinling Orogenic Belt(QOB)is located between the North China plate and the South China Plate,and is one of the main orogenic belts in China.To explore the composition and origin of anisotropy and the low wave velocity zone of the QOB,ten rock samples(gneiss and schist)were collected from the five sites of the QOB and the P-and S-wave velocities of these samples were measured under 0.6 to 2.0 GPa and 100 to 550℃.The wave velocities increase with increasing pressure and decreasing temperature.The V_(P)and V_(S)of the schist and gneiss match the velocity of the middle and lower crust of the QOB,indicating that schist and gneiss are important component of the QOB.All the schist and gneiss samples exhibit obvious seismic anisotropy with 1.64%-17.42%for V_(S)and 2.93%-14.78%for V_(P)under conditions of crust and upper mantle.The CPO/LPO and layering distribution of mica in rock samples are the main reasons for this anisotropy.The V_(S)structures below the five sampled sites from seismic ambient noise tomography were built to explore the effect of schist and gneiss on the composition and structure of the QOB.The results indicate that orientation-arranged gneiss and schist driven by the tectonic stresses might be a new origin of the character of V_(P)/V_(S),seismic anisotropy,and the low velocity zone in the QOB.展开更多
Investigating highly effective electrocatalysts for high-temperature proton exchange membrane fuel cells(HT-PEMFC)requires the resistance to phosphate acid(PA)poisoning at cathodic oxygen reduction reaction(ORR).Recen...Investigating highly effective electrocatalysts for high-temperature proton exchange membrane fuel cells(HT-PEMFC)requires the resistance to phosphate acid(PA)poisoning at cathodic oxygen reduction reaction(ORR).Recent advancements in catalysts have focused on alleviating phosphoric anion adsorption on Pt-based catalysts with modified electronic structure or catalytic interface and developing Fe-N-C based catalysts with immunity of PA poisoning.Fe-N-C-based catalysts have emerged as promising alternatives to Pt-based catalysts,offering significant potential to overcome the characteristic adsorption of phosphate anion on Pt.An overview of these developments provides insights into catalytic mechanisms and facilitates the design of more efficient catalysts.This review begins with an exploration of basic poisoning principles,followed by a critical summary of characterization techniques employed to identified the underlying mechanism of poisoning effect.Attention is then directed to endeavors aimed at enhancing the HT-PEMFC performance by well-designed catalysts.Finally,the opportunities and challenges in developing the anti-PA poisoning strategy and practical HT-PEMFC is discussed.Through these discussions,a comprehensive understanding of PA-poisoning bottlenecks and inspire future research directions is aim to provided.展开更多
Through three millennia of practice,Traditional Chinese Medicine(TCM)has evolved by integrating knowledge from diverse disciplines,forging a distinct developmental path that respects its ancient foundations while inco...Through three millennia of practice,Traditional Chinese Medicine(TCM)has evolved by integrating knowledge from diverse disciplines,forging a distinct developmental path that respects its ancient foundations while incorporating innovation.TCM has achieved significant breakthroughs in elucidating its theoretical foundations using contemporary scientific methodologies,through the implementation of modernization initiatives over the past three decades.The TCM modernization program has yielded continuous innovations,propelling TCM into a high-quality development stage across both clinical practice and industrial applications.Notably,these advances have enhanced global recognition and adoption of TCM.展开更多
Ambient noise tomography is an established technique in seismology,where calculating single-or ninecomponent noise cross-correlation functions(NCFs)is a fundamental first step.In this study,we introduced a novel CPU-G...Ambient noise tomography is an established technique in seismology,where calculating single-or ninecomponent noise cross-correlation functions(NCFs)is a fundamental first step.In this study,we introduced a novel CPU-GPU heterogeneous computing framework designed to significantly enhance the efficiency of computing 9-component NCFs from seismic ambient noise data.This framework not only accelerated the computational process by leveraging the Compute Unified Device Architecture(CUDA)but also improved the signal-to-noise ratio(SNR)through innovative stacking techniques,such as time-frequency domain phaseweighted stacking(tf-PWS).We validated the program using multiple datasets,confirming its superior computation speed,improved reliability,and higher signal-to-noise ratios for NCFs.Our comprehensive study provides detailed insights into optimizing the computational processes for noise cross-correlation functions,thereby enhancing the precision and efficiency of ambient noise imaging.展开更多
To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities...To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.展开更多
文摘The integration of large-scale foundation models(e.g.,GPT series and AlphaFold)into oncology is fundamentally transforming both research methodologies and clinical practices,driven by unprecedented advancements in computational power.This review synthesizes recent progress in the application of large language models to core oncological tasks,including medical imaging analysis,genomic interpretation,and personalized treatment planning.Underpinned by advanced computational infrastructures,such as graphics processing unit/tensor processing unit clusters,heterogeneous computing,and cloud platforms,these models enable superior representation learning and generalization across multimodal data sources.This review examines how these infrastructures overcome key bottlenecks in intelligent oncology through scalable optimization strategies,including mixed-precision training,memory optimization,and heterogeneous computing.Alongside these technical advancements,the review explores pressing challenges,such as data heterogeneity,limited model interpretability,regulatory uncertainties,and the environmental impact of artificial intelligence(AI)systems.Special emphasis is placed on emerging solutions,encompassing green AI and edge computing,which offer promising approaches for low-resource deployment scenarios.Additionally,the review highlights the critical role of interdisciplinary collaboration among oncology,computer science,ethics,and policy to ensure that AI systems are not only powerful but also transparent,safe,and clinically relevant.Finally,the review outlines potential avenues for future research aimed at developing robust,scalable,and human-centered frameworks for intelligent oncology.
文摘Dear Editor,In this letter,we focus on the algebraic relationship between the coefficient matrices and the solution of the stochastic algebraic Riccati equation.It is revealed that,if the coefficient matrices are in an algebra,then the solution(and also the control gain in many cases)is also in the same algebra.The main result is verified by a numerical simulation.
基金Chengdu University of Technology Youth Teaching Backbone Project,Grant/Award Number:10912-JXGG2023-09458Sichuan Province Overseas Returnees Science and Technology Excellence Project,Grant/Award Number:10900-23BZ28-02+1 种基金Physics-informed machine learning for coupled modelling of carbon storage,Grant/Award Number:SKLGME021002Chengdu University of Technology Research Start-up Fund,Grant/Award Number:10912-KYQD2022-09458。
文摘Carbonate reservoirs are vital energy storage spaces,including for oil,shale gas,geothermal,and hydrogen energy.Accurate prediction of reservoir characteristics such as permeability and saturated fluid types through noninvasive approaches is crucial for optimal storage capability.In this paper,we combine a linear Boolean model and a discrete Fourier transform approach to generate pore‐and fracturepore‐type carbonate rocks.Elastic wave velocity information is necessary to predict permeability in different rock geometry models.Permeability is calculated using the lattice Boltzmann method,and the elastic wave velocity is calculated using a finite element method based on a minimal energy approach.Saturated fluids that contain oil and gas were both considered.Our simulated results reveal that,for pore‐type carbonate,empirical formulas were proposed to estimate permeability through elastic data.However,in fracture‐pore carbonate rocks,the precision of the empirical formula is compromised due to the presence of significant conductive channels within the rock matrix.We also find that using S‐wave velocity and permeability relationships to distinguish oil and gas is better than using P‐wave velocity and permeability relationships under low‐porosity conditions.
基金supported by the Beijing Natural Science Foundation under Grant 9242003partially supported by the Natural Science Foundation of Chongqing,China under Grant CSTB2023NSCQ-MSX0391+3 种基金partially supported by the National Natural Science Foundation of China under Grant 62471493partially supported by the Natural Science Foundation of Shandong Province under Grants ZR2023LZH017,ZR2024MF066supported by the Key Laboratory of Public Opinion Governance and Computational Communication under Grant YQKFYB202501The Research Project on the Development of Social Sciences in Hebei Province in 2024(No.202403150).
文摘Next-GenerationNetworks(NGNs)demand high resilience,dynamic adaptability,and efficient resource utilization to enable ubiquitous connectivity.In this context,the Space-Air-Ground Integrated Network(SAGIN)architecture is uniquely positioned to meet these requirements.However,conventional NGN routing algorithms often fail to account for SAGIN’s intrinsic characteristics,such as its heterogeneous structure,dynamic topology,and constrained resources,leading to suboptimal performance under disruptions such as node failures or cyberattacks.To meet these demands for SAGIN,this study proposes a resilience-oriented routing optimization framework featuring dynamic weighting and multi-objective evaluation.Methodologically,we define three core routing performance metrics,quantified through a four-dimensionalmodel,encompassing robustness Rd,resilience Rr,adaptability Ra,and resource utilization efficiency Ru,and integrate them into a comprehensive evaluation metric.In simulated SAGIN environments,the proposed Multi-Indicator Weighted Resilience Evaluation Algorithm(MIW-REA)demonstrates significant improvements in resilience enhancement,recovery acceleration,and resource optimization.It maintains 82.3%service availability even with a 30%node failure rate,reduces Distributed Denial of Service(DDoS)attack recovery time by 43%,decreases bandwidth waste by 23.4%,and lowers energy consumption by 18.9%.By addressing challenges unique to the SAGIN network,this research provides a flexible real-time solution for NGN routing optimization that balances resilience,efficiency,and adaptability,advancing the field.
基金This work is supported by the National Key Research and Development Plan program of the Ministry of Science and Technology of China(No.2016YFB0201100)Additionally,this work is supported by the National Laboratory for Marine Science and Technology(Qingdao)Major Project of the Aoshan Science and Technology Innovation Program(No.2018ASKJ01-04)the Open Fundation of Key Laboratory of Marine Science and Numerical Simulation,Ministry of Natural Resources(No.2021-YB-02).
文摘In this paper,a typical experiment is carried out based on a high-resolution air-sea coupled model,namely,the coupled ocean-atmosphere-wave-sediment transport(COAWST)model,on both heterogeneous many-core(SW)and homogenous multicore(Intel)supercomputing platforms.We construct a hindcast of Typhoon Lekima on both the SW and Intel platforms,compare the simulation results between these two platforms and compare the key elements of the atmospheric and ocean modules to reanalysis data.The comparative experiment in this typhoon case indicates that the domestic many-core computing platform and general cluster yield almost no differences in the simulated typhoon path and intensity,and the differences in surface pressure(PSFC)in the WRF model and sea surface temperature(SST)in the short-range forecast are very small,whereas a major difference can be identified at high latitudes after the first 10 days.Further heat budget analysis verifies that the differences in SST after 10 days are mainly caused by shortwave radiation variations,as influenced by subsequently generated typhoons in the system.These typhoons generated in the hindcast after the first 10 days attain obviously different trajectories between the two platforms.
基金supported by the National Natural Science Foundation of China(Grant No.:81672743 and 81974464).
文摘Defining an ERBB2(HER2/neu)gene amplification status is critical to guiding human epidermal growth factor receptor 2(HER2)-targeted therapy in breast cancer.Up to 40%of breast cancer patients are reported as having an immunohistochemistry(IHC)of HER22+and requiring additional testing using fluorescence in situ hybridization to confirm the results.This paper aims to establish an automatically weighted calibration deep learning(AWCDL)algorithm to predict ERBB2 amplification based on IHC images.In this study,we applied IHC HER22+images from 1,073 breast cancer patients at three cancer centers in China and extracted 376,099 tiles.Among these,269,664 tiles were used for internal and external validation.The designed AWCDL consists of two steps.In Step 1,the internal validation achieved an accuracy of 89%,with a specificity of 0.89 and a sensitivity of 0.89.The external validation in the two other centers showed an average accuracy of 85%,with a specificity of 0.86 and a sensitivity of 0.82.In Step 2,the model achieved higher accuracy for the slides predicted as negative in Step 1 by automatically calibrating the weight.Collectively,these results suggest that this AWCDL model has successfully proved useful as an alternative method to fluorescence in situ hybridization for assessing the ERBB2 amplification status in breast cancer.
基金supported by the National Natural Science Foundation of China(Grant Nos.12404264 and 22209067)Shenzhen Basic Research Program(Natural Science Foundation)Key Project of Basic Research(Grant No.JCYJ20241202123916023)Shenzhen Science and Technology Program(Grant No.KQTD20200820113047086)。
文摘Sodium-ion batteries have emerged as promising alternatives to lithium-ion batteries due to their abundant raw material reserves,low cost,enhanced safety,and environmental sustainability.Na_(2)Fe_(2)OS_(2),featuring a layered anti-perovskite structure,has attracted significant interest for its high capacity and facile synthesis.In this study,density functional theory calculations were performed to systematically investigate the phase stability,ionic conductivity,and voltage characteristics of Na_(2)Fe_(2)OS_(2)as a model system for anti-perovskite layered cathode materials.The compound exhibits excellent phase stability,and its equilibrium potential was calculated for the series Na_(x)Fe_(2)OCh_(2)(0<±<2)(where Ch represents chalcogenides).Naion transport analysis using the climbing image nudged elastic band method reveals a relatively low migration barrier(~0.47eV)along a dingonal pathway,indicating efficient Na^(+)mobility.To expand the materials design space,we systematically explored the effects of substituting Fe with various transition metals and replacing S with Se in NaaTM_(2)OCh_(2)structures.Among the variants studied,Na_(2)Mn_(2)OS_(2) demonstrates the most favorable combination of high voltage(~2.51V),robust phase stability,and superior energy density(~427 W-h/kg).This comprehensive comparison of transition metal substitutions provides vnluable insights for the rational design and experimental development of next-generation anti-perovskite layered cathode materials for sodium-ion batteries.
基金the National Natural Science Foundation of China(22208320)the Science and Technology Program of Henan Province(212102210044)The Henan Association for Science and Technology Youth Talent Support Program(2022HYTP026).
文摘Combining the advantages of high efficiency,low-pressure drop,and large throughput,the pore arrayenhanced tube-in-tube microchannel(PA-TMC) is a promising microreactor for industrial applications.However,most of the mass transfer takes place in the upstream pore region,while the contribution of the downstream annulus is limited.In this work,helical wires were introduced into the annulus by adhering to the outer surface of the inner tube.Mixing behavior and mass transfer of liquid-liquid twophase flow in PA-TMC with different helical wires have been systematically studied by a combination of experiments and volume of fluid(VOF) method.The introduction of helical wires improves the overall volumetric mass transfer coefficient KLa by up to 133% and the mass transfer efficiency E by up to 117%.The simulation results show that the helical wire brings extra phase mixing regions and increases the specific interface area,while accelerating the fluid flow and expanding the area of enhanced turbulent dissipation rate.Influences of helical wires in various configurations are compared by the comprehensive index I concerning the pressure drop and mass transfer performance simultaneously and a new correlation between KLa and specific energy consumption φ is proposed.This research deepens the understanding of the mixing behavior and mass transfer in the PA-TMCs and provides practical experience for the process intensification of microchannel reactors.
基金co-supported by the National Key Research and Development Program of China(No. 2021YFB3301504)the National Natural Science Foundation of China (Nos. 62072415, 62036010, 42301526, 62372416 and 62472389)the National Natural Science Foundation of Henan Province, China (No. 242300421215)
文摘Accurate recognition of flight deck operations for carrier-based aircraft, based on operation trajectories, is critical for optimizing carrier-based aircraft performance. This recognition involves understanding short-term and long-term spatial collaborative relationships among support agents and positions from long spatial–temporal trajectories. While the existing methods excel at recognizing collaborative behaviors from short trajectories, they often struggle with long spatial–temporal trajectories. To address this challenge, this paper introduces a dynamic graph method to enhance flight deck operation recognition. First, spatial–temporal collaborative relationships are modeled as a dynamic graph. Second, a discretized and compressed method is proposed to assign values to the states of this dynamic graph. To extract features that represent diverse collaborative relationships among agents and account for the duration of these relationships, a biased random walk is then conducted. Subsequently, the Swin Transformer is employed to comprehend spatial–temporal collaborative relationships, and a fully connected layer is applied to deck operation recognition. Finally, to address the scarcity of real datasets, a simulation pipeline is introduced to generate deck operations in virtual flight deck scenarios. Experimental results on the simulation dataset demonstrate the superior performance of the proposed method.
基金in part by the National Science Foundation of China under Grant No.62276238in part by the National Science Foundation for Distinguished Young Scholars of China under Grant No.62325602in part by the Natural Science Foundation of Henan,China under Grant No.232300421095.
文摘The Heterogeneous Capacitated Vehicle Routing Problem(HCVRP),which involves efficiently routing vehicles with diverse capacities to fulfill various customer demands at minimal cost,poses an NP-hard challenge in combinatorial optimization.Recently,reinforcement learning approaches such as 2D Array Pointer Networks(2D-Ptr)have demonstrated remarkable speed in decision-making by modeling multiple agents’concurrent choices as a sequence of consecutive actions.However,these learning-based models often struggle with generalization,meaning they cannot seamlessly adapt to new scenarios with varying numbers of vehicles or customers without retraining.Inspired by the potential of multi-teacher knowledge distillation to harness diverse knowledge from multiple sources and craft a comprehensive student model,we propose to enhance the generalization capability of 2D-Ptr through Multiple Teacher-forcing Knowledge Distillation(MTKD).We initially train 12 unique 2D-Ptr models under various settings to serve as teacher models.Subsequently,we randomly sample a teacher model and a batch of problem instances,focusing on those where the chosen teacher performed best.This teacher model then solves these instances,generating high-reward action sequences to guide knowledge transfer to the student model.We conduct rigorous evaluations across four distinct datasets,each comprising four HCVRP instances of varying scales.Our empirical findings underscore the proposed method superiority over existing learning-based methods in terms of both computational efficiency and solution quality.
基金supported by funding from the National Natural Science Foundation of China(Grant Nos.62325602,62406292,62302459,62406293,and 62036010)。
文摘The efficiency of carrier-based aircraft support operation scheduling critically impacts aircraft carrier operational effectiveness by determining sortie generation rates,yet faces significant challenges in complex deck environments characterized by resource coupling,dynamic constraints,and highdimensional state-action spaces.Traditional optimization algorithms and vanilla reinforcement learning(RL)struggle with computational inefficiency,sparse rewards,and adaptability to dynamic scenarios,while human expert systems are constrained by the quality of expert knowledge,and poor expert guidance may even have a negative impact.To address these limitations,this paper proposes a human experience-guided actor-critic reinforcement learning framework that synergizes domain expertise with adaptive learning.First,a dynamic Markov decision process(MDP)model is developed to rigorously simulate carrier deck operations,explicitly encoding constraints on positions,resources,and collision avoidance.Building upon this foundation,a human experience database is constructed to enable real-time pattern-matching-based intervention during agent-environment interactions,dynamically correcting wrong actions to avoid catastrophic states while refining exploration efficiency.Finally,the policy and value network objectives are reshaped to incorporate human intent through hybrid reward functions and adaptive guidance weighting,ensuring balanced integration of expert knowledge with RL's exploration capabilities.Extensive simulations across three scenarios demonstrate superior performance compared to state-of-the-art methods and maintain robustness under suboptimal human guidance.These results validate the framework's ability to harmonize human expertise with adaptive learning,offering a practical solution for real-world carriers.
基金the National Natural Science Foundation of China(No.62272421)。
文摘Non-line-of-sight imaging recovers hidden objects around the corner by analyzing the diffuse reflection light on the relay surface that carries hidden scene information.Due to its huge application potential in the fields of autonomous driving,defense,medical imaging,and post-disaster rescue,non-line-of-sight imaging has attracted considerable attention from researchers at home and abroad,especially in recent years.The research on non-line-of-sight imaging primarily focuses on imaging systems,forward models,and reconstruction algorithms.This paper systematically summarizes the existing non-line-of-sight imaging technology in both active and passive scenes,and analyzes the challenges and future directions of non-line-of-sight imaging technology.
基金supported by the Major Innovation Project for the Integration of Science,Education,and Industry of Qilu University of Technology(Shandong Academy of Sciences)(Nos.2023HYZX01,2023JBZ02)the Open Project of Key Laboratory of Computing Power Network and Information Security,Ministry of Education,Qilu University of Technology(Shandong Academy of Sciences)(No.2023ZD007)+2 种基金the Talent Research Projects of Qilu University of Technology(Shandong Academy of Sciences)(No.2023RCKY136)the Technology and Innovation Major Project of the Ministry of Science and Technology of China(No.2022ZD0118600)the Jinan‘20 New Colleges and Universities’Funded Project(No.202333043)。
文摘Accurate wind speed measurements on maritime vessels are crucial for weather forecasting,sea state prediction,and safe navigation.However,vessel motion and challenging environmental conditions often affect measurement precision.To address this issue,this study proposes an innovative framework for correcting and predicting shipborne wind speed.By integrating a main network with a momentum updating network,the proposed framework effectively extracts features from the time and frequency domains,thereby allowing for precise adjustments and predictions of shipborne wind speed data.Validation using real sensor data collected at the Qingdao Oceanographic Institute demonstrates that the proposed method outperforms existing approaches in single-and multi-step predictions compared to existing methods,achieving higher accuracy in wind speed forecasting.The proposed innovative approach offers a promising direction for future validation in more realistic maritime onboard scenarios.
基金supported by National Key Research and Development Program of China under Grant 2024YFE0210800National Natural Science Foundation of China under Grant 62495062Beijing Natural Science Foundation under Grant L242017.
文摘The Dynamical Density Functional Theory(DDFT)algorithm,derived by associating classical Density Functional Theory(DFT)with the fundamental Smoluchowski dynamical equation,describes the evolution of inhomo-geneous fluid density distributions over time.It plays a significant role in studying the evolution of density distributions over time in inhomogeneous systems.The Sunway Bluelight II supercomputer,as a new generation of China’s developed supercomputer,possesses powerful computational capabilities.Porting and optimizing industrial software on this platform holds significant importance.For the optimization of the DDFT algorithm,based on the Sunway Bluelight II supercomputer and the unique hardware architecture of the SW39000 processor,this work proposes three acceleration strategies to enhance computational efficiency and performance,including direct parallel optimization,local-memory constrained optimization for CPEs,and multi-core groups collaboration and communication optimization.This method combines the characteristics of the program’s algorithm with the unique hardware architecture of the Sunway Bluelight II supercomputer,optimizing the storage and transmission structures to achieve a closer integration of software and hardware.For the first time,this paper presents Sunway-Dynamical Density Functional Theory(SW-DDFT).Experimental results show that SW-DDFT achieves a speedup of 6.67 times within a single-core group compared to the original DDFT implementation,with six core groups(a total of 384 CPEs),the maximum speedup can reach 28.64 times,and parallel efficiency can reach 71%,demonstrating excellent acceleration performance.
基金supported by the Natural Science Foundation of Shandong Province,China(ZR2022MF237)the National Natural Science Foundation of China Youth Fund(62406155)the Major Innovation Project(2023JBZ02)of Qilu University of Technology(Shandong Academy of Sciences).
文摘The purpose of infrared and visible image fusion is to create a single image containing the texture details and significant object information of the source images,particularly in challenging environments.However,existing image fusion algorithms are generally suitable for normal scenes.In the hazy scene,a lot of texture information in the visible image is hidden,the results of existing methods are filled with infrared information,resulting in the lack of texture details and poor visual effect.To address the aforementioned difficulties,we propose a haze-free infrared and visible fusion method,termed HaIVFusion,which can eliminate the influence of haze and obtain richer texture information in the fused image.Specifically,we first design a scene information restoration network(SIRNet)to mine the masked texture information in visible images.Then,a denoising fusion network(DFNet)is designed to integrate the features extracted from infrared and visible images and remove the influence of residual noise as much as possible.In addition,we use color consistency loss to reduce the color distortion resulting from haze.Furthermore,we publish a dataset of hazy scenes for infrared and visible image fusion to promote research in extreme scenes.Extensive experiments show that HaIVFusion produces fused images with increased texture details and higher contrast in hazy scenes,and achieves better quantitative results,when compared to state-ofthe-art image fusion methods,even combined with state-of-the-art dehazing methods.
基金supported by the National Natural Science Foundation of China(42174115 and 42330311)the Special Fund of the Institute of Earthquake Forecasting,China Earthquake Administration(CEAIEF20230301)the State key laboratory of earthquake dynamics(LED2021B02).
文摘Structure and composition of Earth are fundamental importance in exploring the dynamic evolution of the crust and mantle.The Qinling Orogenic Belt(QOB)is located between the North China plate and the South China Plate,and is one of the main orogenic belts in China.To explore the composition and origin of anisotropy and the low wave velocity zone of the QOB,ten rock samples(gneiss and schist)were collected from the five sites of the QOB and the P-and S-wave velocities of these samples were measured under 0.6 to 2.0 GPa and 100 to 550℃.The wave velocities increase with increasing pressure and decreasing temperature.The V_(P)and V_(S)of the schist and gneiss match the velocity of the middle and lower crust of the QOB,indicating that schist and gneiss are important component of the QOB.All the schist and gneiss samples exhibit obvious seismic anisotropy with 1.64%-17.42%for V_(S)and 2.93%-14.78%for V_(P)under conditions of crust and upper mantle.The CPO/LPO and layering distribution of mica in rock samples are the main reasons for this anisotropy.The V_(S)structures below the five sampled sites from seismic ambient noise tomography were built to explore the effect of schist and gneiss on the composition and structure of the QOB.The results indicate that orientation-arranged gneiss and schist driven by the tectonic stresses might be a new origin of the character of V_(P)/V_(S),seismic anisotropy,and the low velocity zone in the QOB.
文摘Investigating highly effective electrocatalysts for high-temperature proton exchange membrane fuel cells(HT-PEMFC)requires the resistance to phosphate acid(PA)poisoning at cathodic oxygen reduction reaction(ORR).Recent advancements in catalysts have focused on alleviating phosphoric anion adsorption on Pt-based catalysts with modified electronic structure or catalytic interface and developing Fe-N-C based catalysts with immunity of PA poisoning.Fe-N-C-based catalysts have emerged as promising alternatives to Pt-based catalysts,offering significant potential to overcome the characteristic adsorption of phosphate anion on Pt.An overview of these developments provides insights into catalytic mechanisms and facilitates the design of more efficient catalysts.This review begins with an exploration of basic poisoning principles,followed by a critical summary of characterization techniques employed to identified the underlying mechanism of poisoning effect.Attention is then directed to endeavors aimed at enhancing the HT-PEMFC performance by well-designed catalysts.Finally,the opportunities and challenges in developing the anti-PA poisoning strategy and practical HT-PEMFC is discussed.Through these discussions,a comprehensive understanding of PA-poisoning bottlenecks and inspire future research directions is aim to provided.
文摘Through three millennia of practice,Traditional Chinese Medicine(TCM)has evolved by integrating knowledge from diverse disciplines,forging a distinct developmental path that respects its ancient foundations while incorporating innovation.TCM has achieved significant breakthroughs in elucidating its theoretical foundations using contemporary scientific methodologies,through the implementation of modernization initiatives over the past three decades.The TCM modernization program has yielded continuous innovations,propelling TCM into a high-quality development stage across both clinical practice and industrial applications.Notably,these advances have enhanced global recognition and adoption of TCM.
基金supported by the Key Research and Development Program of China(2021YFC3000704)Institute of Geophysics,China Earthquake Administration Grant DQJB23R18+1 种基金the USTC Research Funds of the Double First-Class Initiative(YD2080002012)NSFC Grant(U2239206)。
文摘Ambient noise tomography is an established technique in seismology,where calculating single-or ninecomponent noise cross-correlation functions(NCFs)is a fundamental first step.In this study,we introduced a novel CPU-GPU heterogeneous computing framework designed to significantly enhance the efficiency of computing 9-component NCFs from seismic ambient noise data.This framework not only accelerated the computational process by leveraging the Compute Unified Device Architecture(CUDA)but also improved the signal-to-noise ratio(SNR)through innovative stacking techniques,such as time-frequency domain phaseweighted stacking(tf-PWS).We validated the program using multiple datasets,confirming its superior computation speed,improved reliability,and higher signal-to-noise ratios for NCFs.Our comprehensive study provides detailed insights into optimizing the computational processes for noise cross-correlation functions,thereby enhancing the precision and efficiency of ambient noise imaging.
基金partially supported by the National Natural Science Foundation of China under Grants 62471493 and 62402257(for conceptualization and investigation)partially supported by the Natural Science Foundation of Shandong Province,China under Grants ZR2023LZH017,ZR2024MF066,and 2023QF025(for formal analysis and validation)+1 种基金partially supported by the Open Foundation of Key Laboratory of Computing Power Network and Information Security,Ministry of Education,Qilu University of Technology(Shandong Academy of Sciences)under Grant 2023ZD010(for methodology and model design)partially supported by the Russian Science Foundation(RSF)Project under Grant 22-71-10095-P(for validation and results verification).
文摘To address the challenge of missing modal information in entity alignment and to mitigate information loss or bias arising frommodal heterogeneity during fusion,while also capturing shared information acrossmodalities,this paper proposes a Multi-modal Pre-synergistic Entity Alignmentmodel based on Cross-modalMutual Information Strategy Optimization(MPSEA).The model first employs independent encoders to process multi-modal features,including text,images,and numerical values.Next,a multi-modal pre-synergistic fusion mechanism integrates graph structural and visual modal features into the textual modality as preparatory information.This pre-fusion strategy enables unified perception of heterogeneous modalities at the model’s initial stage,reducing discrepancies during the fusion process.Finally,using cross-modal deep perception reinforcement learning,the model achieves adaptive multilevel feature fusion between modalities,supporting learningmore effective alignment strategies.Extensive experiments on multiple public datasets show that the MPSEA method achieves gains of up to 7% in Hits@1 and 8.2% in MRR on the FBDB15K dataset,and up to 9.1% in Hits@1 and 7.7% in MRR on the FBYG15K dataset,compared to existing state-of-the-art methods.These results confirm the effectiveness of the proposed model.
