With the development of autonomous driving technologies,modern vehicles are confronted with two major challenges.On one hand,the rapid growth in electronic control units and data-intensive applications has led to a sh...With the development of autonomous driving technologies,modern vehicles are confronted with two major challenges.On one hand,the rapid growth in electronic control units and data-intensive applications has led to a sharp increase in invehicle data traffic,thereby demanding much higher communication bandwidth,lower latency,and enhanced security.On the other hand,ensuring driving safety calls for more advanced thermal management systems,as traditional point-type sensors face deployment challenges due to their limited monitoring range.展开更多
Plant root systems,a crucial component of biogeotechnics,have been recognized as a promising and sustainable strategy to address novel challenges in geotechnical engineering,i.e.,climate change(Ng et al.,2022).Root-so...Plant root systems,a crucial component of biogeotechnics,have been recognized as a promising and sustainable strategy to address novel challenges in geotechnical engineering,i.e.,climate change(Ng et al.,2022).Root-soil composite and root-reinforced slopes have re-ceived widespread attention in recent decades,due to the ability of root to regulate soil properties through mechanical reinforcement and hy-draulic transpiration(Li&Duan,2023;Ni et al.,2024).Fig.1 provides a co-occurrence network plot of plant root-based soil reinforcement strategies published over the last decade,where three clusters are identified with different colors.On the left of the network map,clusters in red and blue are primarily driven by geotechnical investigations of vegetated slopes(i.e.,plant root reinforced slopes)and root-soil com-posite/root-permeated soils,as denoted by the terms like"model","test","slope","strength"and"vegetation",while the green cluster on the right side demonstrates botany-related domains,for instance,"plant growth",Indeed,the reinforcement of vegetated soil strength is com-plex and varies significantly with an abundance of factors,both me-chanically and hydraulically.Particularly,the impact of root mor-phology and architecture cannot be negligible,including keywords"root area ratio"root distribution""root morphology"root diame-ter"root density"in Fig.1 with the root size and root depth ranking foremost.展开更多
A space-ground integrated network(SGIN)will be a future network for the heterogeneous convergence of space-and ground-based networks.The SGIN envisions satellites with the capability to adapt to various communication ...A space-ground integrated network(SGIN)will be a future network for the heterogeneous convergence of space-and ground-based networks.The SGIN envisions satellites with the capability to adapt to various communication protocols,enabling the convergence of diverse network systems.A crucial aspect of satellite payload in the SGIN is the recognition of satellite signal types and their modulation modes,which substantially enhances the processing of heterogeneous wireless signals at the baseband processing.A multitask learning(MTL)model-based convolutional neural network(CNN)architecture is proposed,which addresses the recognition problem.An MTL model-based CNN architecture is proposed,which addresses the recognition problem.This model is composed of 3 key components:A multi-input part that processes in-phase/quadrature(IQ)complex signals and power spectral density data,a set of shared part that facilitates the model’s efficiency and mitigate overfitting,and a multitask output part capable of concurrently recognizing signal types and modulation modes.Furthermore,we have developed a dataset that encompasses 5 satellite signal protocols,i.e.,signal type,and 6 modulation modes,derived from the digital video broadcasting(DVB)protocols and the tracking,telemetry,and command(TT&C)standards of the consultative committee for space data systems(CCSDS).This dataset also takes into account the impact of the additive white Gaussian noise(AWGN)channel and land mobile satellite(LMS)channel models.Simulation experiments validate the effectiveness of the proposed MTL model in accurately identifying various satellite signal protocols and modulation techniques.展开更多
Artificial intelligence(AI)in education is experiencing a transformative shift,fueled by foundation models with unprecedented capabilities.These advancements are reshaping educational paradigms and addressing challeng...Artificial intelligence(AI)in education is experiencing a transformative shift,fueled by foundation models with unprecedented capabilities.These advancements are reshaping educational paradigms and addressing challenges such as diverse student needs,resource gaps,and engagement.1 This paper examines three key trends:the shift from perception to cognition,the transition from generalized to personalized learning,and the rise of multimodal systems,as shown in Figure 1.Together,these trends open up new opportunities to tackle persistent challenges in the education sector.展开更多
To the Editor,We read with great interest the recent Editorial by Li et al[1]on the potential of large language models(LLMs)in clinical decision support.Their assessment of the LLMs’strengths in data processing,diagn...To the Editor,We read with great interest the recent Editorial by Li et al[1]on the potential of large language models(LLMs)in clinical decision support.Their assessment of the LLMs’strengths in data processing,diagnostics,and workflow optimization is timely and well-grounded.We write to extend the discussion to a key limitation the authors themselves acknowledge:the lack of emotional intelligence in current AI systems.As Li et al[1]noted,LLMs remain“notably deficient in addressing emotional and ethical aspects.”展开更多
Capturing high-speed rotating uncooperative space targets is extremely challenging.Thus,to avoid potential collision risks,it is crucial to conduct detumbling operations before capturing.To minimize the impact of devi...Capturing high-speed rotating uncooperative space targets is extremely challenging.Thus,to avoid potential collision risks,it is crucial to conduct detumbling operations before capturing.To minimize the impact of deviations and repulsion on targets,while also decreasing reliance on attitude control systems,a detumbling strategy utilizing one of 2 detumbling devices to maneuver an uncooperative space target based on current control is proposed in this paper.First,analytical models for the magnetic field and its error are established to validate the proposed method.Then,the detumbling strategies for targets of different radii are analyzed based on those models.Subsequently,the strategy’s effectiveness is verified through the consistency between finite element model(FEM)results and analytical solutions.Analysis of 2 typical cases shows significant advantages in reducing power consumption and stabilizing target orbits.Finally,comparison of ground experiments and analytical methods demonstrate the accuracy of the proposed strategy.展开更多
文摘With the development of autonomous driving technologies,modern vehicles are confronted with two major challenges.On one hand,the rapid growth in electronic control units and data-intensive applications has led to a sharp increase in invehicle data traffic,thereby demanding much higher communication bandwidth,lower latency,and enhanced security.On the other hand,ensuring driving safety calls for more advanced thermal management systems,as traditional point-type sensors face deployment challenges due to their limited monitoring range.
基金supported by Natural Science Foundation of Chongqing(No.CSTB2022NSCQ-LZX0001)High-end Foreign Expert Introduction program(No.G2022165004L)+1 种基金High-end Foreign Expert Introduction program(No.DL2021165001L)The fi-nancial supports are gratefully acknowledged.
文摘Plant root systems,a crucial component of biogeotechnics,have been recognized as a promising and sustainable strategy to address novel challenges in geotechnical engineering,i.e.,climate change(Ng et al.,2022).Root-soil composite and root-reinforced slopes have re-ceived widespread attention in recent decades,due to the ability of root to regulate soil properties through mechanical reinforcement and hy-draulic transpiration(Li&Duan,2023;Ni et al.,2024).Fig.1 provides a co-occurrence network plot of plant root-based soil reinforcement strategies published over the last decade,where three clusters are identified with different colors.On the left of the network map,clusters in red and blue are primarily driven by geotechnical investigations of vegetated slopes(i.e.,plant root reinforced slopes)and root-soil com-posite/root-permeated soils,as denoted by the terms like"model","test","slope","strength"and"vegetation",while the green cluster on the right side demonstrates botany-related domains,for instance,"plant growth",Indeed,the reinforcement of vegetated soil strength is com-plex and varies significantly with an abundance of factors,both me-chanically and hydraulically.Particularly,the impact of root mor-phology and architecture cannot be negligible,including keywords"root area ratio"root distribution""root morphology"root diame-ter"root density"in Fig.1 with the root size and root depth ranking foremost.
基金supported by the National Key Research and Development Program(grant number 2021Y FB2900604)Young Elite Scientists Sponsorship Program by CAST(grant number 2022QNRC001).
文摘A space-ground integrated network(SGIN)will be a future network for the heterogeneous convergence of space-and ground-based networks.The SGIN envisions satellites with the capability to adapt to various communication protocols,enabling the convergence of diverse network systems.A crucial aspect of satellite payload in the SGIN is the recognition of satellite signal types and their modulation modes,which substantially enhances the processing of heterogeneous wireless signals at the baseband processing.A multitask learning(MTL)model-based convolutional neural network(CNN)architecture is proposed,which addresses the recognition problem.An MTL model-based CNN architecture is proposed,which addresses the recognition problem.This model is composed of 3 key components:A multi-input part that processes in-phase/quadrature(IQ)complex signals and power spectral density data,a set of shared part that facilitates the model’s efficiency and mitigate overfitting,and a multitask output part capable of concurrently recognizing signal types and modulation modes.Furthermore,we have developed a dataset that encompasses 5 satellite signal protocols,i.e.,signal type,and 6 modulation modes,derived from the digital video broadcasting(DVB)protocols and the tracking,telemetry,and command(TT&C)standards of the consultative committee for space data systems(CCSDS).This dataset also takes into account the impact of the additive white Gaussian noise(AWGN)channel and land mobile satellite(LMS)channel models.Simulation experiments validate the effectiveness of the proposed MTL model in accurately identifying various satellite signal protocols and modulation techniques.
基金funded by the NSFC(no.62172393)the Major Public Welfare Project of Henan Province(no.201300311200).
文摘Artificial intelligence(AI)in education is experiencing a transformative shift,fueled by foundation models with unprecedented capabilities.These advancements are reshaping educational paradigms and addressing challenges such as diverse student needs,resource gaps,and engagement.1 This paper examines three key trends:the shift from perception to cognition,the transition from generalized to personalized learning,and the rise of multimodal systems,as shown in Figure 1.Together,these trends open up new opportunities to tackle persistent challenges in the education sector.
文摘To the Editor,We read with great interest the recent Editorial by Li et al[1]on the potential of large language models(LLMs)in clinical decision support.Their assessment of the LLMs’strengths in data processing,diagnostics,and workflow optimization is timely and well-grounded.We write to extend the discussion to a key limitation the authors themselves acknowledge:the lack of emotional intelligence in current AI systems.As Li et al[1]noted,LLMs remain“notably deficient in addressing emotional and ethical aspects.”
基金supported by the National Natural Science Foundation of China(11972078).
文摘Capturing high-speed rotating uncooperative space targets is extremely challenging.Thus,to avoid potential collision risks,it is crucial to conduct detumbling operations before capturing.To minimize the impact of deviations and repulsion on targets,while also decreasing reliance on attitude control systems,a detumbling strategy utilizing one of 2 detumbling devices to maneuver an uncooperative space target based on current control is proposed in this paper.First,analytical models for the magnetic field and its error are established to validate the proposed method.Then,the detumbling strategies for targets of different radii are analyzed based on those models.Subsequently,the strategy’s effectiveness is verified through the consistency between finite element model(FEM)results and analytical solutions.Analysis of 2 typical cases shows significant advantages in reducing power consumption and stabilizing target orbits.Finally,comparison of ground experiments and analytical methods demonstrate the accuracy of the proposed strategy.
