Under solvothermal conditions,1,4‑naphthalenedicarboxylic acid(H_(2)ndc)and 9,9′‑dihexyl‑2,7‑di(pyridin‑4‑yl)fluorene(hfdp)reacted with Co^(2+)ions and Cd^(2+)ions to form two coordination polymers,[Co(hfdp)(ndc)(H2O...Under solvothermal conditions,1,4‑naphthalenedicarboxylic acid(H_(2)ndc)and 9,9′‑dihexyl‑2,7‑di(pyridin‑4‑yl)fluorene(hfdp)reacted with Co^(2+)ions and Cd^(2+)ions to form two coordination polymers,[Co(hfdp)(ndc)(H2O)]·DMA}n(1)and{[Cd(hfdp)(ndc)(H_(2)O)]·DMA}_(n)(2),respectively(DMA=N,N‑dimethylacetamide).Single‑crystal X‑ray diffraction analyses showed that both complexes 1 and 2 contain similar structures.Topological analysis indicates that complexes 1 and 2 have a{44·62}planar structure.In addition,both complexes reveal good thermal stability and fluorescence sensing performance.They exhibited good sensitivity and selectivity towards 2,4,6‑trinitrophenol(TNP)by fluorescent quenching.The limits of detection of 1 and 2 for TNP were 0.107 and 0.327μmol·L^(-1),respectively.CCDC:2475515,1;2475516,2.展开更多
Four distinct coordination polymers(CPs)were successfully synthesized by altering solvent types and adjusting ligand concentrations,and their crystal structures were investigated.[Co(L)(FDCA)(H_(2)O)_(2)]·0.5H_(2...Four distinct coordination polymers(CPs)were successfully synthesized by altering solvent types and adjusting ligand concentrations,and their crystal structures were investigated.[Co(L)(FDCA)(H_(2)O)_(2)]·0.5H_(2)O(1)was synthesized as a 2D structure using Coas the metal source,methanol‑water(4∶6,V/V)as the solvent,and specific concentrations of 2,5‑furandicarboxylic acid(H_(2)FDCA)and 1,3,5‑triimidazole benzene(L).Adjusting to pure water and lowering the concentration of L yielded the 1D chain structure of[Co(HL)2(H_(2)O)_(2)](FDCA)_(2)·6H_(2)O(2).Using Cu(Ⅱ)as the metal source,methanol/water(9∶1,V/V)as the solvent,and specific concentrations of L and H2FDCA,the 1D chain structure of[Cu(L)(FDCA)(H_(2)O)]·2H_(2)O(3)was synthesized.Upon increasing the concentrations of L and H2FDCA,and switching the solvent to pure water,the 1D chain structure of[Cu(HL)_(2)(H_(2)O)_(2)](FDCA)_(2)·6H_(2)O(4)was obtained.This shows that changing the solvent and ligand concentrations can affect the structural changes of CPs.In addition,the solid‑state photoluminescence of CPs 1‑4 at room temperature was studied,and their morphological changes were observed via scanning electron microscopy.Density functional theory calculations revealed that the negative charge concentrates on the O and N atoms of the ligand,facilitating ligand‑metal ion coordination.CCDC:2403934,1;2403935,2;2403936,3;2403938,4.展开更多
The recycling of neptunium(Np)from nuclear wastes is crucial for the sustainable development of nuclear energy,yet it is still a challenging task owing to the complexity of Np chemistry.Precise control of oxidation st...The recycling of neptunium(Np)from nuclear wastes is crucial for the sustainable development of nuclear energy,yet it is still a challenging task owing to the complexity of Np chemistry.Precise control of oxidation state is highly desirable for the effective recovery of Np.In this study,we report an innovative strategy for Np recovery through in-situ coordination and reduction of Np(Ⅴ)in a biphasic extraction system.By leveraging the synergistic effects of coordination by a P=O donating ligand(trialkyl phosphine oxide,TRPO)and reduction by hydroquinone(HQ)in the organic phase,efficient Np(Ⅴ)-to-Np(Ⅳ)conversion and high distribution ratio(D)of Np were achieved in a single extraction contact.The reduction mechanism of Np was elucidated through spectroscopic and theoretical analyses.This work enriches the redox chemistry of Np and provides a novel pathway for Np recovery in advanced nuclear fuel cycles.展开更多
In multi-modal emotion recognition,excessive reliance on historical context often impedes the detection of emotional shifts,while modality heterogeneity and unimodal noise limit recognition performance.Existing method...In multi-modal emotion recognition,excessive reliance on historical context often impedes the detection of emotional shifts,while modality heterogeneity and unimodal noise limit recognition performance.Existing methods struggle to dynamically adjust cross-modal complementary strength to optimize fusion quality and lack effective mechanisms to model the dynamic evolution of emotions.To address these issues,we propose a multi-level dynamic gating and emotion transfer framework for multi-modal emotion recognition.A dynamic gating mechanism is applied across unimodal encoding,cross-modal alignment,and emotion transfer modeling,substantially improving noise robustness and feature alignment.First,we construct a unimodal encoder based on gated recurrent units and feature-selection gating to suppress intra-modal noise and enhance contextual representation.Second,we design a gated-attention crossmodal encoder that dynamically calibrates the complementary contributions of visual and audio modalities to the dominant textual features and eliminates redundant information.Finally,we introduce a gated enhanced emotion transfer module that explicitly models the temporal dependence of emotional evolution in dialogues via transfer gating and optimizes continuity modeling with a comparative learning loss.Experimental results demonstrate that the proposed method outperforms state-of-the-art models on the public MELD and IEMOCAP datasets.展开更多
Prussian blue analogs(PBAs)are considered one of the excellent cathode materials for sodium-ion batteries due to their low cost and high theoretical specific capacity,especially sodium-rich iron-based PBAs(FeHCF)can p...Prussian blue analogs(PBAs)are considered one of the excellent cathode materials for sodium-ion batteries due to their low cost and high theoretical specific capacity,especially sodium-rich iron-based PBAs(FeHCF)can provide higher energy density.FeHCF has a poor charge/discharge platform stability at high voltages(FeC_(6)moiety),which is mainly affected by its coordination environment.In this research,Cu^(+)(six-coordinated),which is close to the ionic radius of Fe^(2+),was used for substitution,the FeC_(6)vacancies of FeHCF were reduced,and the coordination environment was optimized.The low Cu^(+)-substituted FeHCF(Cu^(+)0.625)has an optimal electrochemical performance at 8.5 mA/g with a reversible specific capacity of 142 mA h/g and FeC_(6)moiety contribution of more than 68 mA h/g,which is superior to that of unmodified and other Cu^(2+)-substituted FeHCFs.In situ tests demonstrate the reversible structural stability of the Cu^(+)0.625,supporting the stability of their high-voltage platform capacity.This Cu^(+)substitution strategy further enriches the approach to optimize the coordination environment of sodium-rich FeHCF.展开更多
Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination syst...Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination system for Connected and Automated Vehicles(CAVs)at single-lane intersections,particularly in the context of left-hand side driving on roads.The goal is to facilitate smooth right turns for certain vehicles without creating bottlenecks.We consider that all approaching vehicles share relevant information through vehicular communications.The Intersection Coordination Unit(ICU)processes this information and communicates the optimal crossing or turning times to the vehicles.The primary objective of this coordination is to minimize overall traffic delays,which also helps improve the fuel consumption of vehicles.By considering information from upcoming vehicles at the intersection,the coordination system solves an optimization problem to determine the best timing for executing right turns,ultimately minimizing the total delay for all vehicles.The proposed coordination system is evaluated at a typical urban intersection,and its performance is compared to traditional traffic systems.Numerical simulation results indicate that the proposed coordination system significantly enhances the average traffic speed and fuel consumption compared to the traditional traffic system in various scenarios.展开更多
Acceptorless dehydrogenative coupling of pyridinemethanol with ketones is one of the most reliable methodologies to access functionalized 1,8-naphthyridine derivatives.However,it is challenging to develop environmenta...Acceptorless dehydrogenative coupling of pyridinemethanol with ketones is one of the most reliable methodologies to access functionalized 1,8-naphthyridine derivatives.However,it is challenging to develop environmentally friendly catalytic systems,especially in constructing efficient and recyclable catalysts under water or solvent-free conditions.Here,we designed two novel coordination polymers Cd-CPs and Fe-CPs to investigate their catalytic performance in water.Gratifyingly,it was observed that Cd-CPs as a multifunctional catalyst was successfully applied to establish a universal pathway for direct fabrication of 1,8-naphthyridine derivatives under water conditions,while it was effective for the synthesis of1,3,5-triazines through acceptorless dehydrogenative coupling strategies.The features of broad substrate,high atom efficiency,and good catalyst reusability highlight the feasibility of this transformation.In additional,we demonstrated the spindle-like structures Fe-P,derived from the Fe-CPs via phosphorylation,which can be used as an efficient electrocatalyst for oxygen evolution reaction with good stability.This work provides two highly efficient non-noble metal catalysts for functionalized 1,8-naphthyridine derivatives production and oxygen evolution reaction,and opens a new avenue to further fabricate diverse metal catalysts with high catalytic performance in water.展开更多
The emergence of precision electronic devices and wearable electronic products urgently requires high-performance multifunctional electromagnetic wave(EMW)absorbers to meet the applicability and versatility in various...The emergence of precision electronic devices and wearable electronic products urgently requires high-performance multifunctional electromagnetic wave(EMW)absorbers to meet the applicability and versatility in various applications.Herein,a dual-network(DN)gel was successfully prepared using acrylamide and sodium lignosulphonate as the basic units by simple chemical cross-linking and physical cross-linking methods.Specifically,the hydrogel forms two types of cross-linking networks through metal coordination and hydrogen bonding.Benefiting from the combined effects of dipole polarization and conductivity loss,the gel achieves an effective absorption bandwidth(EAB)of 6.74 GHz at a thickness of only 1.89 mm,demonstrating excellent EMW absorption performance.In addition,this unique structural configuration endows the EMW absorber with multifunctional features,such as remarkable tensile strength,good environmental compatibility,ultraviolet(UV)resistance,and excellent adhesion.Integrating multiple functional features into the EMW gels displays a broad application prospect in a variety of application scenarios.This research reveals the significance of DN structure design in the electromagnetic wave absorption(EWA)performance of gel-based materials,providing a substantial foundation for the multifunctional design of gel-based absorbers.展开更多
Recognizing human interactions in RGB videos is a critical task in computer vision,with applications in video surveillance.Existing deep learning-based architectures have achieved strong results,but are computationall...Recognizing human interactions in RGB videos is a critical task in computer vision,with applications in video surveillance.Existing deep learning-based architectures have achieved strong results,but are computationally intensive,sensitive to video resolution changes and often fail in crowded scenes.We propose a novel hybrid system that is computationally efficient,robust to degraded video quality and able to filter out irrelevant individuals,making it suitable for real-life use.The system leverages multi-modal handcrafted features for interaction representation and a deep learning classifier for capturing complex dependencies.Using Mask R-CNN and YOLO11-Pose,we extract grayscale silhouettes and keypoint coordinates of interacting individuals,while filtering out irrelevant individuals using a proposed algorithm.From these,we extract silhouette-based features(local ternary pattern and histogram of optical flow)and keypoint-based features(distances,angles and velocities)that capture distinct spatial and temporal information.A Bidirectional Long Short-Term Memory network(BiLSTM)then classifies the interactions.Extensive experiments on the UT Interaction,SBU Kinect Interaction and the ISR-UOL 3D social activity datasets demonstrate that our system achieves competitive accuracy.They also validate the effectiveness of the chosen features and classifier,along with the proposed system’s computational efficiency and robustness to occlusion.展开更多
The precise tuning of magnetic nanoparticle size and magnetic domains,thereby shaping magnetic properties.However,the dynamic evolution mechanisms of magnetic domain configurations in relation to electromagnetic(EM)at...The precise tuning of magnetic nanoparticle size and magnetic domains,thereby shaping magnetic properties.However,the dynamic evolution mechanisms of magnetic domain configurations in relation to electromagnetic(EM)attenuation behavior remain poorly understood.To address this gap,a thermodynamically controlled periodic coordination strategy is proposed to achieve precise modulation of magnetic nanoparticle spacing.This approach unveils the evolution of magnetic domain configurations,progressing from individual to coupled and ultimately to crosslinked domain configurations.A unique magnetic coupling phenomenon surpasses the Snoek limit in low-frequency range,which is observed through micromagnetic simulation.The crosslinked magnetic configuration achieves effective low-frequency EM wave absorption at 3.68 GHz,encompassing nearly the entire C-band.This exceptional magnetic interaction significantly enhances radar camouflage and thermal insulation properties.Additionally,a robust gradient metamaterial design extends coverage across the full band(2–40 GHz),effectively mitigating the impact of EM pollution on human health and environment.This comprehensive study elucidates the evolution mechanisms of magnetic domain configurations,addresses gaps in dynamic magnetic modulation,and provides novel insights for the development of high-performance,low-frequency EM wave absorption materials.展开更多
Wheat(Triticum aestivum)faces significant threats from diseases such as powdery mildew(Blumeria graminis)and Fusarium head blight(FHB;caused by Fusarium graminearum),which cause severe yield losses.Moreover,the antago...Wheat(Triticum aestivum)faces significant threats from diseases such as powdery mildew(Blumeria graminis)and Fusarium head blight(FHB;caused by Fusarium graminearum),which cause severe yield losses.Moreover,the antagonism between yield-related traits and disease resistance makes yield resistance coordination a major challenge in wheat breeding.The lack of genetic resources combining both disease resistance and high yield constrains the elucidation of underlying resistance-yield trade-off mechanisms,thereby hindering the development of high-yield and disease-resistant wheat cultivars.Remarkably,Yangmai 33(YM33),a notable wheat cultivar with resistance to both powdery mildew and FHB as well as high-yield performance,was recently developed.It offers a unique opportunity to dissect the genomic architecture underlying the coordination between disease resistance and yield.展开更多
A novel coordination polymer(CP){[Cd_(2)(L)(1,4-bimb)_(1.5)(DMF)_(2)]·DMF}n(1)(H_(4)L=5,5'-[1,1'-biphenyl-4,4'-diylbis(oxy)]diisophthalic acid,1,4-bimb=1,4-bis(imidazole-1-ylmethyl)-benzene)has been d...A novel coordination polymer(CP){[Cd_(2)(L)(1,4-bimb)_(1.5)(DMF)_(2)]·DMF}n(1)(H_(4)L=5,5'-[1,1'-biphenyl-4,4'-diylbis(oxy)]diisophthalic acid,1,4-bimb=1,4-bis(imidazole-1-ylmethyl)-benzene)has been designed and synthesized through solvothermal reaction.Structural analysis shows that Cd(Ⅱ)is connected by H4L and 1,4-bimb to form a 2D network,and 1,4-bimb further expands the 2D network into a 3D framework.CP 1 can be used as an excellent fluorescence sensor for Fe^(3+)and 4-nitrophenol(4-NP),with low detection limits and good anti-interference.The detection limits of Fe^(3+)and 4-NP were 0.034 and 0.031μmol·L^(-1),respectively.In addition,the fluorescence quenching mechanism was studied.1 was successfully applied to determine Fe^(3+)and 4-NP content in the Yanhe River water sample.CCDC:2351092.展开更多
Reaction of the non-substituted/substituted unsymmetric pinene-derived complex[Pt(N^C^N')Cl]with the aryl isocyanide 2,6-dimethylphenyl isocyanide(CNXyl)afforded a mixture of two isomeric species:the ionic complex...Reaction of the non-substituted/substituted unsymmetric pinene-derived complex[Pt(N^C^N')Cl]with the aryl isocyanide 2,6-dimethylphenyl isocyanide(CNXyl)afforded a mixture of two isomeric species:the ionic complex[Pt(κ^(3)-N^C^N')(CNXyl)]Cl([A]Cl)and the molecular complex[Pt(κ^(2)-N^C^N')(CNXyl)Cl](B).Isomer B was almost the dominating product.The structures of the isomer B derivatives bearing-CF_(3)and-Cl substituents on the pyridine ring of the pinene moiety(5B and 7B,respectively)have been confirmed by single-crystal X-ray diffraction,revealing a slightly distorted square planar geometry with trans-N_(N^C^N'),CNR configuration(The terminal N atom of theκ^(2)-N^C^N'ligand is trans to the isocyanide ligand CNXyl.).Isomer B is thermodynamically more stable,as confirmed by theoretical calculations.CCDC:2416415,5B;2416414,7B.展开更多
Objective To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data.Methods Clinical indicators,echocar...Objective To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data.Methods Clinical indicators,echocardiographic data,traditional Chinese medicine(TCM)tongue manifestations,and facial features were collected from patients who underwent coro-nary computed tomography angiography(CTA)in the Cardiac Care Unit(CCU)of Shanghai Tenth People's Hospital between May 1,2023 and May 1,2024.An adaptive weighted multi-modal data fusion(AWMDF)model based on deep learning was constructed to predict the severity of coronary artery stenosis.The model was evaluated using metrics including accura-cy,precision,recall,F1 score,and the area under the receiver operating characteristic(ROC)curve(AUC).Further performance assessment was conducted through comparisons with six ensemble machine learning methods,data ablation,model component ablation,and various decision-level fusion strategies.Results A total of 158 patients were included in the study.The AWMDF model achieved ex-cellent predictive performance(AUC=0.973,accuracy=0.937,precision=0.937,recall=0.929,and F1 score=0.933).Compared with model ablation,data ablation experiments,and various traditional machine learning models,the AWMDF model demonstrated superior per-formance.Moreover,the adaptive weighting strategy outperformed alternative approaches,including simple weighting,averaging,voting,and fixed-weight schemes.Conclusion The AWMDF model demonstrates potential clinical value in the non-invasive prediction of coronary artery disease and could serve as a tool for clinical decision support.展开更多
Studying the coupling coordination development of new energy vehicles(NEVs)and the ecological environment in China is helpful in promoting the development of NEVs in the country and is of great significance in promoti...Studying the coupling coordination development of new energy vehicles(NEVs)and the ecological environment in China is helpful in promoting the development of NEVs in the country and is of great significance in promoting high-quality development of new energy in China.This paper constructs an evaluation index system for the development of NEVs and the ecological environment.It uses game theory combining weighting model,particle swarm optimized projection tracking evaluation model,coupling coordination degree model,and machine learning algorithms to calculate and analyze the level of coupling coordination development of NEVs and the ecological environment in China from 2010 to 2021,and identifies the driving factors.The research results show that:(i)From 2010 to 2021,the development index of NEVs in China has steadily increased from 0.085 to 0.634,while the ecological environment level index significantly rose from 0.170 to 0.884,reflecting the continuous development of China in both NEVs and the ecological environment.(ii)From 2010 to 2012,the two systems—new energy vehicle(NEV)development and the ecological environment—were in a period of imbalance and decline.From 2013 to 2016,they underwent a transition period,and from 2017 to 2021,they entered a period of coordinated development showing a trend of benign and continuous improvement.By 2021,they reached a good level of coordination.(iii)Indicators such as the number of patents granted for NEVs,water consumption per unit of GDP,and energy consumption per unit of GDP are the main driving factors affecting the coupling coordination development of NEVs and the ecological environment in China.展开更多
Traditional Chinese medicine(TCM)demonstrates distinctive advantages in disease prevention and treatment.However,analyzing its biological mechanisms through the modern medical research paradigm of“single drug,single ...Traditional Chinese medicine(TCM)demonstrates distinctive advantages in disease prevention and treatment.However,analyzing its biological mechanisms through the modern medical research paradigm of“single drug,single target”presents significant challenges due to its holistic approach.Network pharmacology and its core theory of network targets connect drugs and diseases from a holistic and systematic perspective based on biological networks,overcoming the limitations of reductionist research models and showing considerable value in TCM research.Recent integration of network target computational and experimental methods with artificial intelligence(AI)and multi-modal multi-omics technologies has substantially enhanced network pharmacology methodology.The advancement in computational and experimental techniques provides complementary support for network target theory in decoding TCM principles.This review,centered on network targets,examines the progress of network target methods combined with AI in predicting disease molecular mechanisms and drug-target relationships,alongside the application of multi-modal multi-omics technologies in analyzing TCM formulae,syndromes,and toxicity.Looking forward,network target theory is expected to incorporate emerging technologies while developing novel approaches aligned with its unique characteristics,potentially leading to significant breakthroughs in TCM research and advancing scientific understanding and innovation in TCM.展开更多
The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring ef...The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.展开更多
With the advent of the next-generation Air Traffic Control(ATC)system,there is growing interest in using Artificial Intelligence(AI)techniques to enhance Situation Awareness(SA)for ATC Controllers(ATCOs),i.e.,Intellig...With the advent of the next-generation Air Traffic Control(ATC)system,there is growing interest in using Artificial Intelligence(AI)techniques to enhance Situation Awareness(SA)for ATC Controllers(ATCOs),i.e.,Intelligent SA(ISA).However,the existing AI-based SA approaches often rely on unimodal data and lack a comprehensive description and benchmark of the ISA tasks utilizing multi-modal data for real-time ATC environments.To address this gap,by analyzing the situation awareness procedure of the ATCOs,the ISA task is refined to the processing of the two primary elements,i.e.,spoken instructions and flight trajectories.Subsequently,the ISA is further formulated into Controlling Intent Understanding(CIU)and Flight Trajectory Prediction(FTP)tasks.For the CIU task,an innovative automatic speech recognition and understanding framework is designed to extract the controlling intent from unstructured and continuous ATC communications.For the FTP task,the single-and multi-horizon FTP approaches are investigated to support the high-precision prediction of the situation evolution.A total of 32 unimodal/multi-modal advanced methods with extensive evaluation metrics are introduced to conduct the benchmarks on the real-world multi-modal ATC situation dataset.Experimental results demonstrate the effectiveness of AI-based techniques in enhancing ISA for the ATC environment.展开更多
A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such...A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such as casual and athletic styles,and consider attributes like color and texture when selecting outfits.To achieve personalized outfit recommendations in line with user style preferences,this paper proposes a personal style guided outfit recommendation with multi-modal fashion compatibility modeling,termed as PSGNet.Firstly,a style classifier is designed to categorize fashion images of various clothing types and attributes into distinct style categories.Secondly,a personal style prediction module extracts user style preferences by analyzing historical data.Then,to address the limitations of single-modal representations and enhance fashion compatibility,both fashion images and text data are leveraged to extract multi-modal features.Finally,PSGNet integrates these components through Bayesian personalized ranking(BPR)to unify the personal style and fashion compatibility,where the former is used as personal style features and guides the output of the personalized outfit recommendation tailored to the target user.Extensive experiments on large-scale datasets demonstrate that the proposed model is efficient on the personalized outfit recommendation.展开更多
With the boom in maritime activities,the need for highly reliable maritime communication is becoming urgent,which is an important component of 5G/6G communication networks.However,the bandwidth reuse characteristic of...With the boom in maritime activities,the need for highly reliable maritime communication is becoming urgent,which is an important component of 5G/6G communication networks.However,the bandwidth reuse characteristic of 5G/6G networks will inevitably lead to severe interference,resulting in degradation in the communication performance of maritime users.In this paper,we propose a safe deep reinforcement learning based interference coordination scheme to jointly optimize the power control and bandwidth allocation in maritime communication systems,and exploit the quality-of-service requirements of users as the risk value references to evaluate the communication policies.In particular,this scheme designs a deep neural network to select the communication policies through the evaluation network and update the parameters using the target network,which improves the communication performance and speeds up the convergence rate.Moreover,the Nash equilibrium of the interference coordination game and the computational complexity of the proposed scheme are analyzed.Simulation and experimental results verify the performance gain of the proposed scheme compared with benchmarks.展开更多
文摘Under solvothermal conditions,1,4‑naphthalenedicarboxylic acid(H_(2)ndc)and 9,9′‑dihexyl‑2,7‑di(pyridin‑4‑yl)fluorene(hfdp)reacted with Co^(2+)ions and Cd^(2+)ions to form two coordination polymers,[Co(hfdp)(ndc)(H2O)]·DMA}n(1)and{[Cd(hfdp)(ndc)(H_(2)O)]·DMA}_(n)(2),respectively(DMA=N,N‑dimethylacetamide).Single‑crystal X‑ray diffraction analyses showed that both complexes 1 and 2 contain similar structures.Topological analysis indicates that complexes 1 and 2 have a{44·62}planar structure.In addition,both complexes reveal good thermal stability and fluorescence sensing performance.They exhibited good sensitivity and selectivity towards 2,4,6‑trinitrophenol(TNP)by fluorescent quenching.The limits of detection of 1 and 2 for TNP were 0.107 and 0.327μmol·L^(-1),respectively.CCDC:2475515,1;2475516,2.
文摘Four distinct coordination polymers(CPs)were successfully synthesized by altering solvent types and adjusting ligand concentrations,and their crystal structures were investigated.[Co(L)(FDCA)(H_(2)O)_(2)]·0.5H_(2)O(1)was synthesized as a 2D structure using Coas the metal source,methanol‑water(4∶6,V/V)as the solvent,and specific concentrations of 2,5‑furandicarboxylic acid(H_(2)FDCA)and 1,3,5‑triimidazole benzene(L).Adjusting to pure water and lowering the concentration of L yielded the 1D chain structure of[Co(HL)2(H_(2)O)_(2)](FDCA)_(2)·6H_(2)O(2).Using Cu(Ⅱ)as the metal source,methanol/water(9∶1,V/V)as the solvent,and specific concentrations of L and H2FDCA,the 1D chain structure of[Cu(L)(FDCA)(H_(2)O)]·2H_(2)O(3)was synthesized.Upon increasing the concentrations of L and H2FDCA,and switching the solvent to pure water,the 1D chain structure of[Cu(HL)_(2)(H_(2)O)_(2)](FDCA)_(2)·6H_(2)O(4)was obtained.This shows that changing the solvent and ligand concentrations can affect the structural changes of CPs.In addition,the solid‑state photoluminescence of CPs 1‑4 at room temperature was studied,and their morphological changes were observed via scanning electron microscopy.Density functional theory calculations revealed that the negative charge concentrates on the O and N atoms of the ligand,facilitating ligand‑metal ion coordination.CCDC:2403934,1;2403935,2;2403936,3;2403938,4.
基金the financial support from the National Natural Science Foundation of China(22325603)the financial support from the National Natural Science Foundation of China(22376116)+3 种基金the financial support from the National Natural Science Foundation of China(22076130)the Young Elite Scientists Sponsorship Program by China Association for Science and Technology(CAST)(2023QNRC001)the Fundamental Research Funds for the Central Universities(20826041D4117)the Natural Science Foundation of Sichuan(2025ZNSFSC0109)。
文摘The recycling of neptunium(Np)from nuclear wastes is crucial for the sustainable development of nuclear energy,yet it is still a challenging task owing to the complexity of Np chemistry.Precise control of oxidation state is highly desirable for the effective recovery of Np.In this study,we report an innovative strategy for Np recovery through in-situ coordination and reduction of Np(Ⅴ)in a biphasic extraction system.By leveraging the synergistic effects of coordination by a P=O donating ligand(trialkyl phosphine oxide,TRPO)and reduction by hydroquinone(HQ)in the organic phase,efficient Np(Ⅴ)-to-Np(Ⅳ)conversion and high distribution ratio(D)of Np were achieved in a single extraction contact.The reduction mechanism of Np was elucidated through spectroscopic and theoretical analyses.This work enriches the redox chemistry of Np and provides a novel pathway for Np recovery in advanced nuclear fuel cycles.
基金funded by“the Fanying Special Program of the National Natural Science Foundation of China,grant number 62341307”“the Scientific research project of Jiangxi Provincial Department of Education,grant number GJJ200839”“theDoctoral startup fund of JiangxiUniversity of Technology,grant number 205200100402”.
文摘In multi-modal emotion recognition,excessive reliance on historical context often impedes the detection of emotional shifts,while modality heterogeneity and unimodal noise limit recognition performance.Existing methods struggle to dynamically adjust cross-modal complementary strength to optimize fusion quality and lack effective mechanisms to model the dynamic evolution of emotions.To address these issues,we propose a multi-level dynamic gating and emotion transfer framework for multi-modal emotion recognition.A dynamic gating mechanism is applied across unimodal encoding,cross-modal alignment,and emotion transfer modeling,substantially improving noise robustness and feature alignment.First,we construct a unimodal encoder based on gated recurrent units and feature-selection gating to suppress intra-modal noise and enhance contextual representation.Second,we design a gated-attention crossmodal encoder that dynamically calibrates the complementary contributions of visual and audio modalities to the dominant textual features and eliminates redundant information.Finally,we introduce a gated enhanced emotion transfer module that explicitly models the temporal dependence of emotional evolution in dialogues via transfer gating and optimizes continuity modeling with a comparative learning loss.Experimental results demonstrate that the proposed method outperforms state-of-the-art models on the public MELD and IEMOCAP datasets.
基金supported by the Key Talent Project of Gansu Province(2025RCXM017)the National Natural Science Foundation of China(52261040)+2 种基金the Postgraduate Innovation Star Program of Gansu Province(2025CXZX-476)the Major Science and Technology Project of Gansu Province(22ZD6GA008)the Innovation Driven Assistance Engineering Project of Gansu Association for Science and Technology(GXH20250325-5).
文摘Prussian blue analogs(PBAs)are considered one of the excellent cathode materials for sodium-ion batteries due to their low cost and high theoretical specific capacity,especially sodium-rich iron-based PBAs(FeHCF)can provide higher energy density.FeHCF has a poor charge/discharge platform stability at high voltages(FeC_(6)moiety),which is mainly affected by its coordination environment.In this research,Cu^(+)(six-coordinated),which is close to the ionic radius of Fe^(2+),was used for substitution,the FeC_(6)vacancies of FeHCF were reduced,and the coordination environment was optimized.The low Cu^(+)-substituted FeHCF(Cu^(+)0.625)has an optimal electrochemical performance at 8.5 mA/g with a reversible specific capacity of 142 mA h/g and FeC_(6)moiety contribution of more than 68 mA h/g,which is superior to that of unmodified and other Cu^(2+)-substituted FeHCFs.In situ tests demonstrate the reversible structural stability of the Cu^(+)0.625,supporting the stability of their high-voltage platform capacity.This Cu^(+)substitution strategy further enriches the approach to optimize the coordination environment of sodium-rich FeHCF.
基金supported by the Japan Society for the Promotion of Science(JSPS)Grants-in-Aid for Scientific Research(C)23K03898.
文摘Traffic at urban intersections frequently encounters unexpected obstructions,resulting in congestion due to uncooperative and priority-based driving behavior.This paper presents an optimal right-turn coordination system for Connected and Automated Vehicles(CAVs)at single-lane intersections,particularly in the context of left-hand side driving on roads.The goal is to facilitate smooth right turns for certain vehicles without creating bottlenecks.We consider that all approaching vehicles share relevant information through vehicular communications.The Intersection Coordination Unit(ICU)processes this information and communicates the optimal crossing or turning times to the vehicles.The primary objective of this coordination is to minimize overall traffic delays,which also helps improve the fuel consumption of vehicles.By considering information from upcoming vehicles at the intersection,the coordination system solves an optimization problem to determine the best timing for executing right turns,ultimately minimizing the total delay for all vehicles.The proposed coordination system is evaluated at a typical urban intersection,and its performance is compared to traditional traffic systems.Numerical simulation results indicate that the proposed coordination system significantly enhances the average traffic speed and fuel consumption compared to the traditional traffic system in various scenarios.
基金financial support of this work by the National Natural Science Foundation of China(No.21861039)Postgraduate Research&Practice Innovation Program of Jiangsu Province(No.KYCX24_2530)the Fundamental Research Funds for the Central Universities。
文摘Acceptorless dehydrogenative coupling of pyridinemethanol with ketones is one of the most reliable methodologies to access functionalized 1,8-naphthyridine derivatives.However,it is challenging to develop environmentally friendly catalytic systems,especially in constructing efficient and recyclable catalysts under water or solvent-free conditions.Here,we designed two novel coordination polymers Cd-CPs and Fe-CPs to investigate their catalytic performance in water.Gratifyingly,it was observed that Cd-CPs as a multifunctional catalyst was successfully applied to establish a universal pathway for direct fabrication of 1,8-naphthyridine derivatives under water conditions,while it was effective for the synthesis of1,3,5-triazines through acceptorless dehydrogenative coupling strategies.The features of broad substrate,high atom efficiency,and good catalyst reusability highlight the feasibility of this transformation.In additional,we demonstrated the spindle-like structures Fe-P,derived from the Fe-CPs via phosphorylation,which can be used as an efficient electrocatalyst for oxygen evolution reaction with good stability.This work provides two highly efficient non-noble metal catalysts for functionalized 1,8-naphthyridine derivatives production and oxygen evolution reaction,and opens a new avenue to further fabricate diverse metal catalysts with high catalytic performance in water.
基金supported by the National Natural Science Foundation of China(Nos.52231007,51872238,52074227,and 21806129)the Fundamental Research Funds for the Central Universities(Nos.3102018zy045,3102019AX11,and 5000220455)the Natural Science Basic Research Plan in Shaanxi Province of China(Nos.2017JQ5116 and 2020JM-118).
文摘The emergence of precision electronic devices and wearable electronic products urgently requires high-performance multifunctional electromagnetic wave(EMW)absorbers to meet the applicability and versatility in various applications.Herein,a dual-network(DN)gel was successfully prepared using acrylamide and sodium lignosulphonate as the basic units by simple chemical cross-linking and physical cross-linking methods.Specifically,the hydrogel forms two types of cross-linking networks through metal coordination and hydrogen bonding.Benefiting from the combined effects of dipole polarization and conductivity loss,the gel achieves an effective absorption bandwidth(EAB)of 6.74 GHz at a thickness of only 1.89 mm,demonstrating excellent EMW absorption performance.In addition,this unique structural configuration endows the EMW absorber with multifunctional features,such as remarkable tensile strength,good environmental compatibility,ultraviolet(UV)resistance,and excellent adhesion.Integrating multiple functional features into the EMW gels displays a broad application prospect in a variety of application scenarios.This research reveals the significance of DN structure design in the electromagnetic wave absorption(EWA)performance of gel-based materials,providing a substantial foundation for the multifunctional design of gel-based absorbers.
基金supported and funded by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R410),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Recognizing human interactions in RGB videos is a critical task in computer vision,with applications in video surveillance.Existing deep learning-based architectures have achieved strong results,but are computationally intensive,sensitive to video resolution changes and often fail in crowded scenes.We propose a novel hybrid system that is computationally efficient,robust to degraded video quality and able to filter out irrelevant individuals,making it suitable for real-life use.The system leverages multi-modal handcrafted features for interaction representation and a deep learning classifier for capturing complex dependencies.Using Mask R-CNN and YOLO11-Pose,we extract grayscale silhouettes and keypoint coordinates of interacting individuals,while filtering out irrelevant individuals using a proposed algorithm.From these,we extract silhouette-based features(local ternary pattern and histogram of optical flow)and keypoint-based features(distances,angles and velocities)that capture distinct spatial and temporal information.A Bidirectional Long Short-Term Memory network(BiLSTM)then classifies the interactions.Extensive experiments on the UT Interaction,SBU Kinect Interaction and the ISR-UOL 3D social activity datasets demonstrate that our system achieves competitive accuracy.They also validate the effectiveness of the chosen features and classifier,along with the proposed system’s computational efficiency and robustness to occlusion.
基金supported by the National Natural Science Foundation of China(22265021,52231007,and 12327804)the Aeronautical Science Foundation of China(2020Z056056003)Jiangxi Provincial Natural Science Foundation(20232BAB212004).
文摘The precise tuning of magnetic nanoparticle size and magnetic domains,thereby shaping magnetic properties.However,the dynamic evolution mechanisms of magnetic domain configurations in relation to electromagnetic(EM)attenuation behavior remain poorly understood.To address this gap,a thermodynamically controlled periodic coordination strategy is proposed to achieve precise modulation of magnetic nanoparticle spacing.This approach unveils the evolution of magnetic domain configurations,progressing from individual to coupled and ultimately to crosslinked domain configurations.A unique magnetic coupling phenomenon surpasses the Snoek limit in low-frequency range,which is observed through micromagnetic simulation.The crosslinked magnetic configuration achieves effective low-frequency EM wave absorption at 3.68 GHz,encompassing nearly the entire C-band.This exceptional magnetic interaction significantly enhances radar camouflage and thermal insulation properties.Additionally,a robust gradient metamaterial design extends coverage across the full band(2–40 GHz),effectively mitigating the impact of EM pollution on human health and environment.This comprehensive study elucidates the evolution mechanisms of magnetic domain configurations,addresses gaps in dynamic magnetic modulation,and provides novel insights for the development of high-performance,low-frequency EM wave absorption materials.
基金supported by the National Key R&D Program of China(2024YFD1201100)the research program from the Zhongshan Biological Breeding Laboratory(ZSBBL-KY2023-02)the National Natural Science Foundation of China(32341037).
文摘Wheat(Triticum aestivum)faces significant threats from diseases such as powdery mildew(Blumeria graminis)and Fusarium head blight(FHB;caused by Fusarium graminearum),which cause severe yield losses.Moreover,the antagonism between yield-related traits and disease resistance makes yield resistance coordination a major challenge in wheat breeding.The lack of genetic resources combining both disease resistance and high yield constrains the elucidation of underlying resistance-yield trade-off mechanisms,thereby hindering the development of high-yield and disease-resistant wheat cultivars.Remarkably,Yangmai 33(YM33),a notable wheat cultivar with resistance to both powdery mildew and FHB as well as high-yield performance,was recently developed.It offers a unique opportunity to dissect the genomic architecture underlying the coordination between disease resistance and yield.
文摘A novel coordination polymer(CP){[Cd_(2)(L)(1,4-bimb)_(1.5)(DMF)_(2)]·DMF}n(1)(H_(4)L=5,5'-[1,1'-biphenyl-4,4'-diylbis(oxy)]diisophthalic acid,1,4-bimb=1,4-bis(imidazole-1-ylmethyl)-benzene)has been designed and synthesized through solvothermal reaction.Structural analysis shows that Cd(Ⅱ)is connected by H4L and 1,4-bimb to form a 2D network,and 1,4-bimb further expands the 2D network into a 3D framework.CP 1 can be used as an excellent fluorescence sensor for Fe^(3+)and 4-nitrophenol(4-NP),with low detection limits and good anti-interference.The detection limits of Fe^(3+)and 4-NP were 0.034 and 0.031μmol·L^(-1),respectively.In addition,the fluorescence quenching mechanism was studied.1 was successfully applied to determine Fe^(3+)and 4-NP content in the Yanhe River water sample.CCDC:2351092.
文摘Reaction of the non-substituted/substituted unsymmetric pinene-derived complex[Pt(N^C^N')Cl]with the aryl isocyanide 2,6-dimethylphenyl isocyanide(CNXyl)afforded a mixture of two isomeric species:the ionic complex[Pt(κ^(3)-N^C^N')(CNXyl)]Cl([A]Cl)and the molecular complex[Pt(κ^(2)-N^C^N')(CNXyl)Cl](B).Isomer B was almost the dominating product.The structures of the isomer B derivatives bearing-CF_(3)and-Cl substituents on the pyridine ring of the pinene moiety(5B and 7B,respectively)have been confirmed by single-crystal X-ray diffraction,revealing a slightly distorted square planar geometry with trans-N_(N^C^N'),CNR configuration(The terminal N atom of theκ^(2)-N^C^N'ligand is trans to the isocyanide ligand CNXyl.).Isomer B is thermodynamically more stable,as confirmed by theoretical calculations.CCDC:2416415,5B;2416414,7B.
基金Construction Program of the Key Discipline of State Administration of Traditional Chinese Medicine of China(ZYYZDXK-2023069)Research Project of Shanghai Municipal Health Commission (2024QN018)Shanghai University of Traditional Chinese Medicine Science and Technology Development Program (23KFL005)。
文摘Objective To develop a non-invasive predictive model for coronary artery stenosis severity based on adaptive multi-modal integration of traditional Chinese and western medicine data.Methods Clinical indicators,echocardiographic data,traditional Chinese medicine(TCM)tongue manifestations,and facial features were collected from patients who underwent coro-nary computed tomography angiography(CTA)in the Cardiac Care Unit(CCU)of Shanghai Tenth People's Hospital between May 1,2023 and May 1,2024.An adaptive weighted multi-modal data fusion(AWMDF)model based on deep learning was constructed to predict the severity of coronary artery stenosis.The model was evaluated using metrics including accura-cy,precision,recall,F1 score,and the area under the receiver operating characteristic(ROC)curve(AUC).Further performance assessment was conducted through comparisons with six ensemble machine learning methods,data ablation,model component ablation,and various decision-level fusion strategies.Results A total of 158 patients were included in the study.The AWMDF model achieved ex-cellent predictive performance(AUC=0.973,accuracy=0.937,precision=0.937,recall=0.929,and F1 score=0.933).Compared with model ablation,data ablation experiments,and various traditional machine learning models,the AWMDF model demonstrated superior per-formance.Moreover,the adaptive weighting strategy outperformed alternative approaches,including simple weighting,averaging,voting,and fixed-weight schemes.Conclusion The AWMDF model demonstrates potential clinical value in the non-invasive prediction of coronary artery disease and could serve as a tool for clinical decision support.
基金Supported by the Postgraduate Research&Practice Innovation Program of Jiangsu Province(KYCX24_0102)the China Scholarship Council Program(202406190114)。
文摘Studying the coupling coordination development of new energy vehicles(NEVs)and the ecological environment in China is helpful in promoting the development of NEVs in the country and is of great significance in promoting high-quality development of new energy in China.This paper constructs an evaluation index system for the development of NEVs and the ecological environment.It uses game theory combining weighting model,particle swarm optimized projection tracking evaluation model,coupling coordination degree model,and machine learning algorithms to calculate and analyze the level of coupling coordination development of NEVs and the ecological environment in China from 2010 to 2021,and identifies the driving factors.The research results show that:(i)From 2010 to 2021,the development index of NEVs in China has steadily increased from 0.085 to 0.634,while the ecological environment level index significantly rose from 0.170 to 0.884,reflecting the continuous development of China in both NEVs and the ecological environment.(ii)From 2010 to 2012,the two systems—new energy vehicle(NEV)development and the ecological environment—were in a period of imbalance and decline.From 2013 to 2016,they underwent a transition period,and from 2017 to 2021,they entered a period of coordinated development showing a trend of benign and continuous improvement.By 2021,they reached a good level of coordination.(iii)Indicators such as the number of patents granted for NEVs,water consumption per unit of GDP,and energy consumption per unit of GDP are the main driving factors affecting the coupling coordination development of NEVs and the ecological environment in China.
文摘Traditional Chinese medicine(TCM)demonstrates distinctive advantages in disease prevention and treatment.However,analyzing its biological mechanisms through the modern medical research paradigm of“single drug,single target”presents significant challenges due to its holistic approach.Network pharmacology and its core theory of network targets connect drugs and diseases from a holistic and systematic perspective based on biological networks,overcoming the limitations of reductionist research models and showing considerable value in TCM research.Recent integration of network target computational and experimental methods with artificial intelligence(AI)and multi-modal multi-omics technologies has substantially enhanced network pharmacology methodology.The advancement in computational and experimental techniques provides complementary support for network target theory in decoding TCM principles.This review,centered on network targets,examines the progress of network target methods combined with AI in predicting disease molecular mechanisms and drug-target relationships,alongside the application of multi-modal multi-omics technologies in analyzing TCM formulae,syndromes,and toxicity.Looking forward,network target theory is expected to incorporate emerging technologies while developing novel approaches aligned with its unique characteristics,potentially leading to significant breakthroughs in TCM research and advancing scientific understanding and innovation in TCM.
基金supported by the National Natural Science Foundation of China(Grant Nos.62071315 and 62271336).
文摘The multi-modal characteristics of mineral particles play a pivotal role in enhancing the classification accuracy,which is critical for obtaining a profound understanding of the Earth's composition and ensuring effective exploitation utilization of its resources.However,the existing methods for classifying mineral particles do not fully utilize these multi-modal features,thereby limiting the classification accuracy.Furthermore,when conventional multi-modal image classification methods are applied to planepolarized and cross-polarized sequence images of mineral particles,they encounter issues such as information loss,misaligned features,and challenges in spatiotemporal feature extraction.To address these challenges,we propose a multi-modal mineral particle polarization image classification network(MMGC-Net)for precise mineral particle classification.Initially,MMGC-Net employs a two-dimensional(2D)backbone network with shared parameters to extract features from two types of polarized images to ensure feature alignment.Subsequently,a cross-polarized intra-modal feature fusion module is designed to refine the spatiotemporal features from the extracted features of the cross-polarized sequence images.Ultimately,the inter-modal feature fusion module integrates the two types of modal features to enhance the classification precision.Quantitative and qualitative experimental results indicate that when compared with the current state-of-the-art multi-modal image classification methods,MMGC-Net demonstrates marked superiority in terms of mineral particle multi-modal feature learning and four classification evaluation metrics.It also demonstrates better stability than the existing models.
基金supported by the National Natural Science Foundation of China(Nos.62371323,62401380,U2433217,U2333209,and U20A20161)Natural Science Foundation of Sichuan Province,China(Nos.2025ZNSFSC1476)+2 种基金Sichuan Science and Technology Program,China(Nos.2024YFG0010 and 2024ZDZX0046)the Institutional Research Fund from Sichuan University(Nos.2024SCUQJTX030)the Open Fund of Key Laboratory of Flight Techniques and Flight Safety,CAAC(Nos.GY2024-01A).
文摘With the advent of the next-generation Air Traffic Control(ATC)system,there is growing interest in using Artificial Intelligence(AI)techniques to enhance Situation Awareness(SA)for ATC Controllers(ATCOs),i.e.,Intelligent SA(ISA).However,the existing AI-based SA approaches often rely on unimodal data and lack a comprehensive description and benchmark of the ISA tasks utilizing multi-modal data for real-time ATC environments.To address this gap,by analyzing the situation awareness procedure of the ATCOs,the ISA task is refined to the processing of the two primary elements,i.e.,spoken instructions and flight trajectories.Subsequently,the ISA is further formulated into Controlling Intent Understanding(CIU)and Flight Trajectory Prediction(FTP)tasks.For the CIU task,an innovative automatic speech recognition and understanding framework is designed to extract the controlling intent from unstructured and continuous ATC communications.For the FTP task,the single-and multi-horizon FTP approaches are investigated to support the high-precision prediction of the situation evolution.A total of 32 unimodal/multi-modal advanced methods with extensive evaluation metrics are introduced to conduct the benchmarks on the real-world multi-modal ATC situation dataset.Experimental results demonstrate the effectiveness of AI-based techniques in enhancing ISA for the ATC environment.
基金Shanghai Frontier Science Research Center for Modern Textiles,Donghua University,ChinaOpen Project of Henan Key Laboratory of Intelligent Manufacturing of Mechanical Equipment,Zhengzhou University of Light Industry,China(No.IM202303)National Key Research and Development Program of China(No.2019YFB1706300)。
文摘A personalized outfit recommendation has emerged as a hot research topic in the fashion domain.However,existing recommendations do not fully exploit user style preferences.Typically,users prefer particular styles such as casual and athletic styles,and consider attributes like color and texture when selecting outfits.To achieve personalized outfit recommendations in line with user style preferences,this paper proposes a personal style guided outfit recommendation with multi-modal fashion compatibility modeling,termed as PSGNet.Firstly,a style classifier is designed to categorize fashion images of various clothing types and attributes into distinct style categories.Secondly,a personal style prediction module extracts user style preferences by analyzing historical data.Then,to address the limitations of single-modal representations and enhance fashion compatibility,both fashion images and text data are leveraged to extract multi-modal features.Finally,PSGNet integrates these components through Bayesian personalized ranking(BPR)to unify the personal style and fashion compatibility,where the former is used as personal style features and guides the output of the personalized outfit recommendation tailored to the target user.Extensive experiments on large-scale datasets demonstrate that the proposed model is efficient on the personalized outfit recommendation.
文摘With the boom in maritime activities,the need for highly reliable maritime communication is becoming urgent,which is an important component of 5G/6G communication networks.However,the bandwidth reuse characteristic of 5G/6G networks will inevitably lead to severe interference,resulting in degradation in the communication performance of maritime users.In this paper,we propose a safe deep reinforcement learning based interference coordination scheme to jointly optimize the power control and bandwidth allocation in maritime communication systems,and exploit the quality-of-service requirements of users as the risk value references to evaluate the communication policies.In particular,this scheme designs a deep neural network to select the communication policies through the evaluation network and update the parameters using the target network,which improves the communication performance and speeds up the convergence rate.Moreover,the Nash equilibrium of the interference coordination game and the computational complexity of the proposed scheme are analyzed.Simulation and experimental results verify the performance gain of the proposed scheme compared with benchmarks.
