Mobile Cloud Computing(MCC)becomes an emerging computing paradigm,where Mobile Devices(MDs)are in the place for offloading task to the nearest resource-rich cloud servers.To promote the system’s performance,the MCC i...Mobile Cloud Computing(MCC)becomes an emerging computing paradigm,where Mobile Devices(MDs)are in the place for offloading task to the nearest resource-rich cloud servers.To promote the system’s performance,the MCC is performed.However,it holds with more overhead complexity in storage and energy,which degrades the network efficiency.Hence the scholar concentrates on decreasing the overhead issue by applying the task offloading process.The major issue in this mechanism is having most cost-effective communication among the devices.This research paper suggests a new optimization strategy for performing the offloading task in MCC.The developed hybrid approach offloads the task to the nearby server to enhance the performance of the MCC by finishing the task within the deadline.A new cost function is derived with the adoption of the average delay of tasks,the energy consumption level,battery lifetime,processing capabilities,storage capacity,response time,communication cost,etc for optimizing the task offloading.Thus,a new task offloading is optimized via a newly recommended hybrid optimizer with the adoption of Probability Condition of Satin Bowerbird Forensic Optimization(PCSBFO),which is developed with the combination of Satin Bowerbird Optimization(SBO)and Forensic-Based Investigation(FBI)to achieve optimal solutions.Additionally,the developed PCSBFO considers the multi-objective constraints such as average delay,energy consumption,and offloading expenditure for ensuring the quality of service,and satisfactory level of the end user in the MCC.This suggested lightweight paradigm addresses the difficulties and minimizes the efforts while developing,deploying,and managing to offload using optimization algorithms to help better available frameworks.Further,the creation of APAs is done to enable the mobile applications to extract maximum utility out of the volumes of available resources.The experiment results show that the suggested hybrid optimization-based task…展开更多
Gauss radial basis functions(GRBF)are frequently employed in data fitting and machine learning.Their linear independence property can theoretically guarantee the avoidance of data redundancy.In this paper,one of the m...Gauss radial basis functions(GRBF)are frequently employed in data fitting and machine learning.Their linear independence property can theoretically guarantee the avoidance of data redundancy.In this paper,one of the main contributions is proving this property using linear algebra instead of profound knowledge.This makes it easy to read and understand this fundamental fact.The proof of linear independence of a set of Gauss functions relies on the constructing method for one-dimensional space and on the deducing method for higher dimensions.Additionally,under the condition of preserving the same moments between the original function and interpolating function,both the interpolating existence and uniqueness are proven for GRBF in one-dimensional space.The final work demonstrates the application of the GRBF method to locate lunar olivine.By combining preprocessed data using GRBF with the removing envelope curve method,a program is created to find the position of lunar olivine based on spectrum data,and the numerical experiment shows that it is an effective scheme.展开更多
Saikosaponins are the major pharmacologically active components in Bupleurum genus and exhibit significant application potential in multiple fields such as immune regulation and anti-tumor activity.To elucidate the bi...Saikosaponins are the major pharmacologically active components in Bupleurum genus and exhibit significant application potential in multiple fields such as immune regulation and anti-tumor activity.To elucidate the biosynthetic pathway of saikosaponins,we identified two cytochrome P450 monooxygenases,CYP716A41 and CYP716Y4,in Bupleurum chinense.These enzymes catalyze the C-28 oxidation and C-16 hydroxylation of oleanane-type triterpene skeletons,respectively.The catalytic efficiency of CYP716A41 from a southern B.chinense variety was significantly higher than that from a northern variety.Molecular docking and mutagenesis experiments revealed that amino acid residues at sites 9 and 35 may contribute to this difference in catalytic efficiency.Additionally,under cold stress,the expression levels of both CYP450 genes and the saikosaponin contents in the leaves of southern varieties were significantly higher compared to those in northern varieties.The variation in the catalytic efficiency of CYP716A41 and the differential expression of the two CYP450 genes under cold stress during winter are associated with the differences in saikosaponin biosynthesis in the leaves of southern and northern B.chinense varieties.This is consistent with the distinct medicinal usage practices observed between southern and northern China.展开更多
Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based...Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.展开更多
Task scheduling in cloud computing is a multi-objective optimization problem,often involving conflicting objectives such as minimizing execution time,reducing operational cost,and maximizing resource utilization.Howev...Task scheduling in cloud computing is a multi-objective optimization problem,often involving conflicting objectives such as minimizing execution time,reducing operational cost,and maximizing resource utilization.However,traditional approaches frequently rely on single-objective optimization methods which are insufficient for capturing the complexity of such problems.To address this limitation,we introduce MDMOSA(Multi-objective Dwarf Mongoose Optimization with Simulated Annealing),a hybrid that integrates multi-objective optimization for efficient task scheduling in Infrastructure-as-a-Service(IaaS)cloud environments.MDMOSA harmonizes the exploration capabilities of the biologically inspired Dwarf Mongoose Optimization(DMO)with the exploitation strengths of Simulated Annealing(SA),achieving a balanced search process.The algorithm aims to optimize task allocation by reducing makespan and financial cost while improving system resource utilization.We evaluate MDMOSA through extensive simulations using the real-world Google Cloud Jobs(GoCJ)dataset within the CloudSim environment.Comparative analysis against benchmarked algorithms such as SMOACO,MOTSGWO,and MFPAGWO reveals that MDMOSA consistently achieves superior performance in terms of scheduling efficiency,cost-effectiveness,and scalability.These results confirm the potential of MDMOSA as a robust and adaptable solution for resource scheduling in dynamic and heterogeneous cloud computing infrastructures.展开更多
Deployable Composite Thin-Walled Structures(DCTWS)are widely used in space applications due to their ability to compactly fold and self-deploy in orbit,enabled by cutouts.Cutout design is crucial for balancing structu...Deployable Composite Thin-Walled Structures(DCTWS)are widely used in space applications due to their ability to compactly fold and self-deploy in orbit,enabled by cutouts.Cutout design is crucial for balancing structural rigidity and flexibility,ensuring material integrity during large deformations,and providing adequate load-bearing capacity and stability once deployed.Most research has focused on optimizing cutout size and shape,while topology optimization offers a broader design space.However,the anisotropic properties of woven composite laminates,complex failure criteria,and multi-performance optimization needs have limited the exploration of topology optimization in this field.This work derives the sensitivities of bending stiffness,critical buckling load,and the failure index of woven composite materials with respect to element density,and formulates both single-objective and multi-objective topology optimization models using a linear weighted aggregation approach.The developed method was integrated with the commercial finite element software ABAQUS via a Python script,allowing efficient application to cutout design in various DCTWS configurations to maximize bending stiffness and critical buckling load under material failure constraints.Optimization of a classical tubular hinge resulted in improvements of 107.7%in bending stiffness and 420.5%in critical buckling load compared to level-set topology optimization results reported in the literature,validating the effectiveness of the approach.To facilitate future research and encourage the broader adoption of topology optimization techniques in DCTWS design,the source code for this work is made publicly available via a Git Hub link:https://github.com/jinhao-ok1/Topo-for-DCTWS.git.展开更多
In a wide range of engineering applications,complex constrained multi-objective optimization problems(CMOPs)present significant challenges,as the complexity of constraints often hampers algorithmic convergence and red...In a wide range of engineering applications,complex constrained multi-objective optimization problems(CMOPs)present significant challenges,as the complexity of constraints often hampers algorithmic convergence and reduces population diversity.To address these challenges,we propose a novel algorithm named Constraint IntensityDriven Evolutionary Multitasking(CIDEMT),which employs a two-stage,tri-task framework to dynamically integrates problem structure and knowledge transfer.In the first stage,three cooperative tasks are designed to explore the Constrained Pareto Front(CPF),the Unconstrained Pareto Front(UPF),and theε-relaxed constraint boundary,respectively.A CPF-UPF relationship classifier is employed to construct a problem-type-aware evolutionary strategy pool.At the end of the first stage,each task selects strategies from this strategy pool based on the specific type of problem,thereby guiding the subsequent evolutionary process.In the second stage,while each task continues to evolve,aτ-driven knowledge transfer mechanism is introduced to selectively incorporate effective solutions across tasks.enhancing the convergence and feasibility of the main task.Extensive experiments conducted on 32 benchmark problems from three test suites(LIRCMOP,DASCMOP,and DOC)demonstrate that CIDEMT achieves the best Inverted Generational Distance(IGD)values on 24 problems and the best Hypervolume values(HV)on 22 problems.Furthermore,CIDEMT significantly outperforms six state-of-the-art constrained multi-objective evolutionary algorithms(CMOEAs).These results confirm CIDEMT’s superiority in promoting convergence,diversity,and robustness in solving complex CMOPs.展开更多
Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may r...Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.展开更多
Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server.Despite rapid progress,federated learning still faces s...Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server.Despite rapid progress,federated learning still faces several unsolved challenges.Specifically,communication costs and system heterogeneity,such as nonidentical data distribution,hinder federated learning's progress.Several approaches have recently emerged for federated learning involving heterogeneous clients with varying computational capabilities(namely,heterogeneous federated learning).However,heterogeneous federated learning faces two key challenges:optimising model size and determining client selection ratios.Moreover,efficiently aggregating local models from clients with diverse capabilities is crucial for addressing system heterogeneity and communication efficiency.This paper proposes an evolutionary multiobjective optimisation framework for heterogeneous federated learning(MOHFL)to address these issues.Our approach elegantly formulates and solves a biobjective optimisation problem that minimises communication cost and model error rate.The decision variables in this framework comprise model sizes and client selection ratios for each Q client cluster,yielding a total of 2×Q optimisation parameters to be tuned.We develop a partition-based strategy for MOHFL that segregates clients into clusters based on their communication and computation capabilities.Additionally,we implement an adaptive model sizing mechanism that dynamically assigns appropriate subnetwork architectures to clients based on their computational constraints.We also propose a unified aggregation framework to combine models of varying sizes from heterogeneous clients effectively.Extensive experiments on multiple datasets demonstrate the effectiveness and superiority of our proposed method compared to existing approaches.展开更多
In recent years,researchers have extensively investigated the Hankel determinant,which consists of coefficients appearing in a holomorphic function’s Taylor-Maclaurin series.Hankel matrices are widely used in Markov ...In recent years,researchers have extensively investigated the Hankel determinant,which consists of coefficients appearing in a holomorphic function’s Taylor-Maclaurin series.Hankel matrices are widely used in Markov processes,non-stationary signals,and other mathematical disciplines.The aim of the current research article is to first improve the bounds of coefficient-related problems by employing the well-known Carathéodory function.The problems that we are going to improve were obtained by Tang et al.The sharp estimates of the most difficult problem of geometric function theory known as the third-order Hankel determinant are also contributed here.Zalcman and Fekete-Szegöinequalities are also studied here for the defined family of holomorphic functions.展开更多
Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrain...Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrained onboard devices to nearby Roadside Unit(RSU),thereby achieving lower delay and energy consumption.However,due to the limited storage capacity and energy budget of RSUs,it is challenging to meet the demands of the highly dynamic Internet of Vehicles(IoV)environment.Therefore,determining reasonable service caching and computation offloading strategies is crucial.To address this,this paper proposes a joint service caching scheme for cloud-edge collaborative IoV computation offloading.By modeling the dynamic optimization problem using Markov Decision Processes(MDP),the scheme jointly optimizes task delay,energy consumption,load balancing,and privacy entropy to achieve better quality of service.Additionally,a dynamic adaptive multi-objective deep reinforcement learning algorithm is proposed.Each Double Deep Q-Network(DDQN)agent obtains rewards for different objectives based on distinct reward functions and dynamically updates the objective weights by learning the value changes between objectives using Radial Basis Function Networks(RBFN),thereby efficiently approximating the Pareto-optimal decisions for multiple objectives.Extensive experiments demonstrate that the proposed algorithm can better coordinate the three-tier computing resources of cloud,edge,and vehicles.Compared to existing algorithms,the proposed method reduces task delay and energy consumption by 10.64%and 5.1%,respectively.展开更多
Spaceborne antennas are essential for remote sensing,deep-space communication,and Earth observation,yet their trajectory planning is complicated by nonlinear base-manipulator coupling and antenna flexibility.To addres...Spaceborne antennas are essential for remote sensing,deep-space communication,and Earth observation,yet their trajectory planning is complicated by nonlinear base-manipulator coupling and antenna flexibility.To address these challenges,this paper proposes a multi-objective trajectory optimization framework.The system dynamics capture both nonlinear rigid-flexible coupling and antenna deformation through a reduced-order formulation.To enhance discretization efficiency,a predictive-terminal hp-adaptive pseudospectral method is employed,assigning collocation density based on task-phase characteristics:finer resolution is applied to dynamic segments requiring higher accuracy,especially near the terminal phase.This enables efficient transcription of the continuous-time problem into a Nonlinear Programming Problem(NLP).The resulting NLP is then solved using a multi-objective optimization strategy based on the nondominated sorting genetic algorithm II,which explores trade-offs among antenna pointing accuracy,energy consumption,and structural vibration.Numerical results demonstrate that the proposed method achieves a reduction of approximately 14.0% in control energy and 41.8%in peak actuation compared to a GPOPS-II baseline,while significantly enhancing vibration suppression.The resulting Pareto front reveals structured trade-offs and clustered solutions,offering robust and diverse options for precision,low-disturbance mission planning.展开更多
Rapid urbanization in China has led to spatial antagonism between urban development and farmland protection and ecological security maintenance.Multi-objective spatial collaborative optimization is a powerful method f...Rapid urbanization in China has led to spatial antagonism between urban development and farmland protection and ecological security maintenance.Multi-objective spatial collaborative optimization is a powerful method for achieving sustainable regional development.Previous studies on multi-objective spatial optimization do not involve spatial corrections to simulation results based on the natural endowment of space resources.This study proposes an Ecological Security-Food Security-Urban Sustainable Development(ES-FS-USD)spatial optimization framework.This framework combines the non-dominated sorting genetic algorithm II(NSGA-II)and patch-generating land use simulation(PLUS)model with an ecological protection importance evaluation,comprehensive agricultural productivity evaluation,and urban sustainable development potential assessment and optimizes the territorial space in the Yangtze River Delta(YRD)region in 2035.The proposed sustainable development(SD)scenario can effectively reduce the destruction of landscape patterns of various land-use types while considering both ecological and economic benefits.The simulation results were further revised by evaluating the land-use suitability of the YRD region.According to the revised spatial pattern for the YRD in 2035,the farmland area accounts for 43.59%of the total YRD,which is 5.35%less than that in 2010.Forest,grassland,and water area account for 40.46%of the total YRD—an increase of 1.42%compared with the case in 2010.Construction land accounts for 14.72%of the total YRD—an increase of 2.77%compared with the case in 2010.The ES-FS-USD spatial optimization framework ensures that spatial optimization outcomes are aligned with the natural endowments of land resources,thereby promoting the sustainable use of land resources,improving the ability of spatial management,and providing valuable insights for decision makers.展开更多
In this paper,we investigate the uniqueness of meromorphic functions and their derivatives in the unit disc and consider the relations between the Borel points and the shared-values of meromorphic functions in an angu...In this paper,we investigate the uniqueness of meromorphic functions and their derivatives in the unit disc and consider the relations between the Borel points and the shared-values of meromorphic functions in an angular domain by Nevanlinna value distribution theory.An admissible meromorphic function with orde or precise order has Borel point and shares IM common values with its derivative in an angular domain of the unit disc,then the meromorphic function and its derivative are unique.The obtained results improve and generalize some existing results and enrich the uniqueness theory of meromorphic functions.展开更多
The rapid growth of mobile and Internet of Things(IoT)applications in dense urban environments places stringent demands on future Beyond 5G(B5G)or Beyond 6G(B6G)networks,which must ensure high Quality of Service(QoS)w...The rapid growth of mobile and Internet of Things(IoT)applications in dense urban environments places stringent demands on future Beyond 5G(B5G)or Beyond 6G(B6G)networks,which must ensure high Quality of Service(QoS)while maintaining cost-efficiency and sustainable deployment.Traditional strategies struggle with complex 3D propagation,building penetration loss,and the balance between coverage and infrastructure cost.To address this challenge,this study presents the first application of a Global-best Guided Quantum-inspired Tabu Search with Quantum-Not Gate(GQTS-QNG)framework for 3D base-station deployment optimization.The problem is formulated as a multi-objective model that simultaneously maximizes coverage and minimizes deployment cost.A binary-to-decimal encodingmechanism is designed to represent discrete placement coordinates and base station types,leveraging a quantum-inspired method to efficiently search and refine solutions within challenging combinatorial environments.Global-best guidance and tabu memory are integrated to strengthen convergence stability and avoid revisiting previously explored solutions.Simulation results across user densities ranging from 1000 to 10,000 show that GQTS-QNG consistently finds deployment configurations achieving full coverage while reducing deployment cost compared with the state-of-the-art algorithms under equal iteration times.Additionally,our method generates welldistributed and structured Pareto fronts,offering diverse planning options that allow operators to flexibly balance cost and performance requirements.These findings demonstrate that GQTS-QNG is a scalable and efficient algorithm for sustainable 3D cellular network deployment in B5G/6G urban scenarios.展开更多
Small RNAs(sRNAs)are important non-coding RNAs that usually play crucial roles in gene expression at the post-transcriptional level.The sRNAs have mostly been investigated in model microorganisms such as Escherichia c...Small RNAs(sRNAs)are important non-coding RNAs that usually play crucial roles in gene expression at the post-transcriptional level.The sRNAs have mostly been investigated in model microorganisms such as Escherichia coli and some pathogens.Nevertheless,microbial sRNAs from extreme environments such as the polar regions and deep sea have recently been discovered and analyzed for their unique roles in stress response,metabolic regulation and adaptation to extreme environments.These sRNAs fine-tune gene expression during oxidative and radiation stress,and modulate temperature and osmotic pressure responses.Representative sRNAs and their functions in thermophilic,psychrophilic,halophilic and radiation-tolerant bacteria are summarized in this review.Despite challenges in sample collection,RNA isolation,and functional annotation,the study of sRNAs in extreme environments provides opportunities for discovering novel regulatory mechanisms,applying them to biotechnology,and advancing our understanding of evolutionary adaptations.Looking ahead,high-throughput sequencing,synthetic biology,and multi-omics integration will bring new breakthroughs in discovering novel sRNAs and their functions and regulatory mechanisms.Such advancements are poised to enable comprehensive characterization of sRNA-mediated regulatory networks in extremophiles and unlock their biotechnological potential through mechanism-driven applications.展开更多
This study investigates the effects of ocean boundaries on modal shapes in very-low-frequency(VLF,1–10 Hz)sound propagation through the deep ocean.Utilizing a normal mode solution formulated in terms of parabolic cyl...This study investigates the effects of ocean boundaries on modal shapes in very-low-frequency(VLF,1–10 Hz)sound propagation through the deep ocean.Utilizing a normal mode solution formulated in terms of parabolic cylinder functions(PCF),we demonstrate that boundary interactions induce a phase change reduction below-πat frequencies of several hertz.This reduction,in turn,forces a key transition in the solution,shifting the order of the PCF from integer to non-integer values.Analysis of the characteristic shape of the PCF versus its order reveals that these boundary-influenced modes exhibit an energy shift toward deeper regions and a weakened axial convergence of the underwater sound field.展开更多
This paper proposes a fast quality control strategy for P-wave receiver functions based on AlexNet and wiggle plots.Receiver functions are essential tools in seismology,particularly for analyzing seismic wave propagat...This paper proposes a fast quality control strategy for P-wave receiver functions based on AlexNet and wiggle plots.Receiver functions are essential tools in seismology,particularly for analyzing seismic wave propagation and subsurface structures,such as the crust and upper mantle.However,the quality control of receiver functions is often a tedious,time-consuming process.In this study,we transform the time series classification problem of receiver function quality control problem into an image classification task by plotting receiver functions as wiggle diagrams and using the deep learning model AlexNet for binary classification to distinguish between“good”and“bad”receiver functions.The model achieved an accuracy of 92.55%on the testing set and demonstrated strong generalization performance with an accuracy of 89.23%on receiver functions of another seismic network(Sichuan Provincial Permanent Seismic Network).While maintaining strong performance,the model is capable of processing approximately 32 receiver function wiggle plots per second on an NVIDIA GeForce RTX 4050.The results show that the proposed feature mapping strategy significantly improves the efficiency and accuracy of receiver function quality control,making it a valuable tool for practical applications.Future work will focus on expanding the dataset and optimizing model performance for broader seismic data applications.展开更多
Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning sc...Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning scenarios.In this work,we propose an Adaptive Meta-Loss Network(Adaptive-MLN)that learns to generate taskagnostic loss functions tailored to evolving classification problems.Unlike traditional methods that rely on static objectives,Adaptive-MLN treats the loss function itself as a trainable component,parameterized by a shallow neural network.To enable flexible,gradient-free optimization,we introduce a hybrid evolutionary approach that combines GeneticAlgorithms(GA)for global exploration and Evolution Strategies(ES)for local refinement.This co-evolutionary process dynamically adjusts the loss landscape,improvingmodel generalization without relying on analytic gradients or handcrafted heuristics.Experimental evaluations on synthetic tasks and the CIFAR-10 andMNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy,convergence,and adaptability.展开更多
Zinc,an essential trace element,plays a pivotal role in maintaining animal health and physiological functions.This review comprehensively examines zinc metabolism—including absorption dynamics across species(poultry,...Zinc,an essential trace element,plays a pivotal role in maintaining animal health and physiological functions.This review comprehensively examines zinc metabolism—including absorption dynamics across species(poultry,ruminants,and non-ruminants),transport mechanisms,storage in tissues,e.g.,the liver,and excretion pathways—and its multifaceted effects on animal health.Zinc critically regulates aspects of growth and development,particularly bone formation,as its deficiency induces skeletal deformities in young animals.It modulates immune function through zinc finger proteins,influencing immune organ integrity,lymphocyte proliferation,and cytokine expression.Reproductive performance is significantly affected by zinc,with its deficiency causing impaired spermatogenesis;delayed sexual maturity in males;and reduced litter size,embryonic survival,and placental function in females.At the molecular level,zinc regulates the activity of enzymes(e.g.,SOD),signaling pathways(MAPK,NF-κB),and transcription factors(MTF-1,Sp1)to maintain homeostasis.Both zinc deficiency(due to dietary insufficiency,malabsorption,or physiological stress)and zinc excess(from environmental pollution or feed oversupplementation)adversely affect health,disrupting mineral balance,enzyme function,and gut microbiota.In animal production,inorganic(zinc oxide,zinc sulfate)and organic(zinc methionine)sources of zinc increase growth,immunity,and productivity,although sustainable strategies are needed to mitigate environmental risks.Future research should focus on novel zinc formulations,precision nutrition,and interactions with gut microbiota to optimize livestock health and sustainable husbandry.展开更多
文摘Mobile Cloud Computing(MCC)becomes an emerging computing paradigm,where Mobile Devices(MDs)are in the place for offloading task to the nearest resource-rich cloud servers.To promote the system’s performance,the MCC is performed.However,it holds with more overhead complexity in storage and energy,which degrades the network efficiency.Hence the scholar concentrates on decreasing the overhead issue by applying the task offloading process.The major issue in this mechanism is having most cost-effective communication among the devices.This research paper suggests a new optimization strategy for performing the offloading task in MCC.The developed hybrid approach offloads the task to the nearby server to enhance the performance of the MCC by finishing the task within the deadline.A new cost function is derived with the adoption of the average delay of tasks,the energy consumption level,battery lifetime,processing capabilities,storage capacity,response time,communication cost,etc for optimizing the task offloading.Thus,a new task offloading is optimized via a newly recommended hybrid optimizer with the adoption of Probability Condition of Satin Bowerbird Forensic Optimization(PCSBFO),which is developed with the combination of Satin Bowerbird Optimization(SBO)and Forensic-Based Investigation(FBI)to achieve optimal solutions.Additionally,the developed PCSBFO considers the multi-objective constraints such as average delay,energy consumption,and offloading expenditure for ensuring the quality of service,and satisfactory level of the end user in the MCC.This suggested lightweight paradigm addresses the difficulties and minimizes the efforts while developing,deploying,and managing to offload using optimization algorithms to help better available frameworks.Further,the creation of APAs is done to enable the mobile applications to extract maximum utility out of the volumes of available resources.The experiment results show that the suggested hybrid optimization-based task…
基金Supported by the National Basic Research Program of China(2012CB025904)Zhengzhou Shengda University of Economics,Business and Management(SD-YB2025085)。
文摘Gauss radial basis functions(GRBF)are frequently employed in data fitting and machine learning.Their linear independence property can theoretically guarantee the avoidance of data redundancy.In this paper,one of the main contributions is proving this property using linear algebra instead of profound knowledge.This makes it easy to read and understand this fundamental fact.The proof of linear independence of a set of Gauss functions relies on the constructing method for one-dimensional space and on the deducing method for higher dimensions.Additionally,under the condition of preserving the same moments between the original function and interpolating function,both the interpolating existence and uniqueness are proven for GRBF in one-dimensional space.The final work demonstrates the application of the GRBF method to locate lunar olivine.By combining preprocessed data using GRBF with the removing envelope curve method,a program is created to find the position of lunar olivine based on spectrum data,and the numerical experiment shows that it is an effective scheme.
基金supported by CARS(CARS-21),the CAMS Innovation Fund for Medical Sciences(2021-I2M-1-032)the Science and Technology Department of Xizang(XZ202401ZY0020)+2 种基金the Science and Technology Department of Sichuan Province(2023YFH0044,2023YFH0018)the Sichuan Province Science Foundation for Distinguished Young Scholars(2022JDJQ0006)the Doctoral Fund of Southwest University of Science and Technology(19ZX7117,21ZX7116).
文摘Saikosaponins are the major pharmacologically active components in Bupleurum genus and exhibit significant application potential in multiple fields such as immune regulation and anti-tumor activity.To elucidate the biosynthetic pathway of saikosaponins,we identified two cytochrome P450 monooxygenases,CYP716A41 and CYP716Y4,in Bupleurum chinense.These enzymes catalyze the C-28 oxidation and C-16 hydroxylation of oleanane-type triterpene skeletons,respectively.The catalytic efficiency of CYP716A41 from a southern B.chinense variety was significantly higher than that from a northern variety.Molecular docking and mutagenesis experiments revealed that amino acid residues at sites 9 and 35 may contribute to this difference in catalytic efficiency.Additionally,under cold stress,the expression levels of both CYP450 genes and the saikosaponin contents in the leaves of southern varieties were significantly higher compared to those in northern varieties.The variation in the catalytic efficiency of CYP716A41 and the differential expression of the two CYP450 genes under cold stress during winter are associated with the differences in saikosaponin biosynthesis in the leaves of southern and northern B.chinense varieties.This is consistent with the distinct medicinal usage practices observed between southern and northern China.
基金the Hebei Province Science and Technology Plan Project(19221909D)rincess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R308),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.
文摘Task scheduling in cloud computing is a multi-objective optimization problem,often involving conflicting objectives such as minimizing execution time,reducing operational cost,and maximizing resource utilization.However,traditional approaches frequently rely on single-objective optimization methods which are insufficient for capturing the complexity of such problems.To address this limitation,we introduce MDMOSA(Multi-objective Dwarf Mongoose Optimization with Simulated Annealing),a hybrid that integrates multi-objective optimization for efficient task scheduling in Infrastructure-as-a-Service(IaaS)cloud environments.MDMOSA harmonizes the exploration capabilities of the biologically inspired Dwarf Mongoose Optimization(DMO)with the exploitation strengths of Simulated Annealing(SA),achieving a balanced search process.The algorithm aims to optimize task allocation by reducing makespan and financial cost while improving system resource utilization.We evaluate MDMOSA through extensive simulations using the real-world Google Cloud Jobs(GoCJ)dataset within the CloudSim environment.Comparative analysis against benchmarked algorithms such as SMOACO,MOTSGWO,and MFPAGWO reveals that MDMOSA consistently achieves superior performance in terms of scheduling efficiency,cost-effectiveness,and scalability.These results confirm the potential of MDMOSA as a robust and adaptable solution for resource scheduling in dynamic and heterogeneous cloud computing infrastructures.
基金supported by the National Natural Science Foundation of China(No.12202295)the International(Regional)Cooperation and Exchange Projects of the National Natural Science Foundation of China(No.W2421002)+2 种基金the Sichuan Science and Technology Program(No.2025ZNSFSC0845)Zhejiang Provincial Natural Science Foundation of China(No.ZCLZ24A0201)the Fundamental Research Funds for the Provincial Universities of Zhejiang(No.GK249909299001-004)。
文摘Deployable Composite Thin-Walled Structures(DCTWS)are widely used in space applications due to their ability to compactly fold and self-deploy in orbit,enabled by cutouts.Cutout design is crucial for balancing structural rigidity and flexibility,ensuring material integrity during large deformations,and providing adequate load-bearing capacity and stability once deployed.Most research has focused on optimizing cutout size and shape,while topology optimization offers a broader design space.However,the anisotropic properties of woven composite laminates,complex failure criteria,and multi-performance optimization needs have limited the exploration of topology optimization in this field.This work derives the sensitivities of bending stiffness,critical buckling load,and the failure index of woven composite materials with respect to element density,and formulates both single-objective and multi-objective topology optimization models using a linear weighted aggregation approach.The developed method was integrated with the commercial finite element software ABAQUS via a Python script,allowing efficient application to cutout design in various DCTWS configurations to maximize bending stiffness and critical buckling load under material failure constraints.Optimization of a classical tubular hinge resulted in improvements of 107.7%in bending stiffness and 420.5%in critical buckling load compared to level-set topology optimization results reported in the literature,validating the effectiveness of the approach.To facilitate future research and encourage the broader adoption of topology optimization techniques in DCTWS design,the source code for this work is made publicly available via a Git Hub link:https://github.com/jinhao-ok1/Topo-for-DCTWS.git.
基金supported by the National Natural Science Foundation of China under Grant No.61972040the Science and Technology Research and Development Project funded by China Railway Material Trade Group Luban Company.
文摘In a wide range of engineering applications,complex constrained multi-objective optimization problems(CMOPs)present significant challenges,as the complexity of constraints often hampers algorithmic convergence and reduces population diversity.To address these challenges,we propose a novel algorithm named Constraint IntensityDriven Evolutionary Multitasking(CIDEMT),which employs a two-stage,tri-task framework to dynamically integrates problem structure and knowledge transfer.In the first stage,three cooperative tasks are designed to explore the Constrained Pareto Front(CPF),the Unconstrained Pareto Front(UPF),and theε-relaxed constraint boundary,respectively.A CPF-UPF relationship classifier is employed to construct a problem-type-aware evolutionary strategy pool.At the end of the first stage,each task selects strategies from this strategy pool based on the specific type of problem,thereby guiding the subsequent evolutionary process.In the second stage,while each task continues to evolve,aτ-driven knowledge transfer mechanism is introduced to selectively incorporate effective solutions across tasks.enhancing the convergence and feasibility of the main task.Extensive experiments conducted on 32 benchmark problems from three test suites(LIRCMOP,DASCMOP,and DOC)demonstrate that CIDEMT achieves the best Inverted Generational Distance(IGD)values on 24 problems and the best Hypervolume values(HV)on 22 problems.Furthermore,CIDEMT significantly outperforms six state-of-the-art constrained multi-objective evolutionary algorithms(CMOEAs).These results confirm CIDEMT’s superiority in promoting convergence,diversity,and robustness in solving complex CMOPs.
文摘Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.
基金supported by the National Research Foundation of Korea grant funded by the Korea government(RS-2023-00217116)。
文摘Federated learning is a distributed framework that trains a centralised model using data from multiple clients without transferring that data to a central server.Despite rapid progress,federated learning still faces several unsolved challenges.Specifically,communication costs and system heterogeneity,such as nonidentical data distribution,hinder federated learning's progress.Several approaches have recently emerged for federated learning involving heterogeneous clients with varying computational capabilities(namely,heterogeneous federated learning).However,heterogeneous federated learning faces two key challenges:optimising model size and determining client selection ratios.Moreover,efficiently aggregating local models from clients with diverse capabilities is crucial for addressing system heterogeneity and communication efficiency.This paper proposes an evolutionary multiobjective optimisation framework for heterogeneous federated learning(MOHFL)to address these issues.Our approach elegantly formulates and solves a biobjective optimisation problem that minimises communication cost and model error rate.The decision variables in this framework comprise model sizes and client selection ratios for each Q client cluster,yielding a total of 2×Q optimisation parameters to be tuned.We develop a partition-based strategy for MOHFL that segregates clients into clusters based on their communication and computation capabilities.Additionally,we implement an adaptive model sizing mechanism that dynamically assigns appropriate subnetwork architectures to clients based on their computational constraints.We also propose a unified aggregation framework to combine models of varying sizes from heterogeneous clients effectively.Extensive experiments on multiple datasets demonstrate the effectiveness and superiority of our proposed method compared to existing approaches.
基金supported by the NSFC(11561001)the Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region(NJYT18-A14)+4 种基金the NSF of Inner Mongolia(2022MS01004,2020MS01011)the Higher School Foundation of Inner Mongolia(NJZY20200)the Program for Key Laboratory Construction of Chifeng University(CFXYZD202004)the Research and Innovation Team of Complex Analysis and Nonlinear Dynamic Systems of Chifeng University(cfxykycxtd202005)the Youth Science Foundation of Chifeng University(cfxyqn202133).
文摘In recent years,researchers have extensively investigated the Hankel determinant,which consists of coefficients appearing in a holomorphic function’s Taylor-Maclaurin series.Hankel matrices are widely used in Markov processes,non-stationary signals,and other mathematical disciplines.The aim of the current research article is to first improve the bounds of coefficient-related problems by employing the well-known Carathéodory function.The problems that we are going to improve were obtained by Tang et al.The sharp estimates of the most difficult problem of geometric function theory known as the third-order Hankel determinant are also contributed here.Zalcman and Fekete-Szegöinequalities are also studied here for the defined family of holomorphic functions.
基金supported by Key Science and Technology Program of Henan Province,China(Grant Nos.242102210147,242102210027)Fujian Province Young and Middle aged Teacher Education Research Project(Science and Technology Category)(No.JZ240101)(Corresponding author:Dong Yuan).
文摘Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrained onboard devices to nearby Roadside Unit(RSU),thereby achieving lower delay and energy consumption.However,due to the limited storage capacity and energy budget of RSUs,it is challenging to meet the demands of the highly dynamic Internet of Vehicles(IoV)environment.Therefore,determining reasonable service caching and computation offloading strategies is crucial.To address this,this paper proposes a joint service caching scheme for cloud-edge collaborative IoV computation offloading.By modeling the dynamic optimization problem using Markov Decision Processes(MDP),the scheme jointly optimizes task delay,energy consumption,load balancing,and privacy entropy to achieve better quality of service.Additionally,a dynamic adaptive multi-objective deep reinforcement learning algorithm is proposed.Each Double Deep Q-Network(DDQN)agent obtains rewards for different objectives based on distinct reward functions and dynamically updates the objective weights by learning the value changes between objectives using Radial Basis Function Networks(RBFN),thereby efficiently approximating the Pareto-optimal decisions for multiple objectives.Extensive experiments demonstrate that the proposed algorithm can better coordinate the three-tier computing resources of cloud,edge,and vehicles.Compared to existing algorithms,the proposed method reduces task delay and energy consumption by 10.64%and 5.1%,respectively.
基金supported by the National Natural Science Foundation of China(No.62173107).
文摘Spaceborne antennas are essential for remote sensing,deep-space communication,and Earth observation,yet their trajectory planning is complicated by nonlinear base-manipulator coupling and antenna flexibility.To address these challenges,this paper proposes a multi-objective trajectory optimization framework.The system dynamics capture both nonlinear rigid-flexible coupling and antenna deformation through a reduced-order formulation.To enhance discretization efficiency,a predictive-terminal hp-adaptive pseudospectral method is employed,assigning collocation density based on task-phase characteristics:finer resolution is applied to dynamic segments requiring higher accuracy,especially near the terminal phase.This enables efficient transcription of the continuous-time problem into a Nonlinear Programming Problem(NLP).The resulting NLP is then solved using a multi-objective optimization strategy based on the nondominated sorting genetic algorithm II,which explores trade-offs among antenna pointing accuracy,energy consumption,and structural vibration.Numerical results demonstrate that the proposed method achieves a reduction of approximately 14.0% in control energy and 41.8%in peak actuation compared to a GPOPS-II baseline,while significantly enhancing vibration suppression.The resulting Pareto front reveals structured trade-offs and clustered solutions,offering robust and diverse options for precision,low-disturbance mission planning.
基金National Natural Science Foundation of China,No.42301470,No.52270185,No.42171389Capacity Building Program of Local Colleges and Universities in Shanghai,No.21010503300。
文摘Rapid urbanization in China has led to spatial antagonism between urban development and farmland protection and ecological security maintenance.Multi-objective spatial collaborative optimization is a powerful method for achieving sustainable regional development.Previous studies on multi-objective spatial optimization do not involve spatial corrections to simulation results based on the natural endowment of space resources.This study proposes an Ecological Security-Food Security-Urban Sustainable Development(ES-FS-USD)spatial optimization framework.This framework combines the non-dominated sorting genetic algorithm II(NSGA-II)and patch-generating land use simulation(PLUS)model with an ecological protection importance evaluation,comprehensive agricultural productivity evaluation,and urban sustainable development potential assessment and optimizes the territorial space in the Yangtze River Delta(YRD)region in 2035.The proposed sustainable development(SD)scenario can effectively reduce the destruction of landscape patterns of various land-use types while considering both ecological and economic benefits.The simulation results were further revised by evaluating the land-use suitability of the YRD region.According to the revised spatial pattern for the YRD in 2035,the farmland area accounts for 43.59%of the total YRD,which is 5.35%less than that in 2010.Forest,grassland,and water area account for 40.46%of the total YRD—an increase of 1.42%compared with the case in 2010.Construction land accounts for 14.72%of the total YRD—an increase of 2.77%compared with the case in 2010.The ES-FS-USD spatial optimization framework ensures that spatial optimization outcomes are aligned with the natural endowments of land resources,thereby promoting the sustainable use of land resources,improving the ability of spatial management,and providing valuable insights for decision makers.
文摘In this paper,we investigate the uniqueness of meromorphic functions and their derivatives in the unit disc and consider the relations between the Borel points and the shared-values of meromorphic functions in an angular domain by Nevanlinna value distribution theory.An admissible meromorphic function with orde or precise order has Borel point and shares IM common values with its derivative in an angular domain of the unit disc,then the meromorphic function and its derivative are unique.The obtained results improve and generalize some existing results and enrich the uniqueness theory of meromorphic functions.
基金supported by the National Science and Technology Council,Taiwan,under Grants 113-2221-E-260-014-MY2 and 114-2119-M-033-001.
文摘The rapid growth of mobile and Internet of Things(IoT)applications in dense urban environments places stringent demands on future Beyond 5G(B5G)or Beyond 6G(B6G)networks,which must ensure high Quality of Service(QoS)while maintaining cost-efficiency and sustainable deployment.Traditional strategies struggle with complex 3D propagation,building penetration loss,and the balance between coverage and infrastructure cost.To address this challenge,this study presents the first application of a Global-best Guided Quantum-inspired Tabu Search with Quantum-Not Gate(GQTS-QNG)framework for 3D base-station deployment optimization.The problem is formulated as a multi-objective model that simultaneously maximizes coverage and minimizes deployment cost.A binary-to-decimal encodingmechanism is designed to represent discrete placement coordinates and base station types,leveraging a quantum-inspired method to efficiently search and refine solutions within challenging combinatorial environments.Global-best guidance and tabu memory are integrated to strengthen convergence stability and avoid revisiting previously explored solutions.Simulation results across user densities ranging from 1000 to 10,000 show that GQTS-QNG consistently finds deployment configurations achieving full coverage while reducing deployment cost compared with the state-of-the-art algorithms under equal iteration times.Additionally,our method generates welldistributed and structured Pareto fronts,offering diverse planning options that allow operators to flexibly balance cost and performance requirements.These findings demonstrate that GQTS-QNG is a scalable and efficient algorithm for sustainable 3D cellular network deployment in B5G/6G urban scenarios.
基金supported by the National Natural Science Foundation of China(Grant nos.42476264,41976224).
文摘Small RNAs(sRNAs)are important non-coding RNAs that usually play crucial roles in gene expression at the post-transcriptional level.The sRNAs have mostly been investigated in model microorganisms such as Escherichia coli and some pathogens.Nevertheless,microbial sRNAs from extreme environments such as the polar regions and deep sea have recently been discovered and analyzed for their unique roles in stress response,metabolic regulation and adaptation to extreme environments.These sRNAs fine-tune gene expression during oxidative and radiation stress,and modulate temperature and osmotic pressure responses.Representative sRNAs and their functions in thermophilic,psychrophilic,halophilic and radiation-tolerant bacteria are summarized in this review.Despite challenges in sample collection,RNA isolation,and functional annotation,the study of sRNAs in extreme environments provides opportunities for discovering novel regulatory mechanisms,applying them to biotechnology,and advancing our understanding of evolutionary adaptations.Looking ahead,high-throughput sequencing,synthetic biology,and multi-omics integration will bring new breakthroughs in discovering novel sRNAs and their functions and regulatory mechanisms.Such advancements are poised to enable comprehensive characterization of sRNA-mediated regulatory networks in extremophiles and unlock their biotechnological potential through mechanism-driven applications.
基金Project supported by the National Natural Science Foundation of China(Grant No.12204128)。
文摘This study investigates the effects of ocean boundaries on modal shapes in very-low-frequency(VLF,1–10 Hz)sound propagation through the deep ocean.Utilizing a normal mode solution formulated in terms of parabolic cylinder functions(PCF),we demonstrate that boundary interactions induce a phase change reduction below-πat frequencies of several hertz.This reduction,in turn,forces a key transition in the solution,shifting the order of the PCF from integer to non-integer values.Analysis of the characteristic shape of the PCF versus its order reveals that these boundary-influenced modes exhibit an energy shift toward deeper regions and a weakened axial convergence of the underwater sound field.
基金supported by the National Natural Science Foundation of China(No.42174071)the National Key Research and Development Program of China(No.2022YFF0800601)Sichuan Key Research and Development Program(No.2023YFS0433)。
文摘This paper proposes a fast quality control strategy for P-wave receiver functions based on AlexNet and wiggle plots.Receiver functions are essential tools in seismology,particularly for analyzing seismic wave propagation and subsurface structures,such as the crust and upper mantle.However,the quality control of receiver functions is often a tedious,time-consuming process.In this study,we transform the time series classification problem of receiver function quality control problem into an image classification task by plotting receiver functions as wiggle diagrams and using the deep learning model AlexNet for binary classification to distinguish between“good”and“bad”receiver functions.The model achieved an accuracy of 92.55%on the testing set and demonstrated strong generalization performance with an accuracy of 89.23%on receiver functions of another seismic network(Sichuan Provincial Permanent Seismic Network).While maintaining strong performance,the model is capable of processing approximately 32 receiver function wiggle plots per second on an NVIDIA GeForce RTX 4050.The results show that the proposed feature mapping strategy significantly improves the efficiency and accuracy of receiver function quality control,making it a valuable tool for practical applications.Future work will focus on expanding the dataset and optimizing model performance for broader seismic data applications.
基金supported by the National Natural Science Foundation of China(NSFC)under Grant number:82171965.
文摘Designing appropriate loss functions is critical to the success of supervised learning models.However,most conventional losses are fixed and manually designed,making them suboptimal for diverse and dynamic learning scenarios.In this work,we propose an Adaptive Meta-Loss Network(Adaptive-MLN)that learns to generate taskagnostic loss functions tailored to evolving classification problems.Unlike traditional methods that rely on static objectives,Adaptive-MLN treats the loss function itself as a trainable component,parameterized by a shallow neural network.To enable flexible,gradient-free optimization,we introduce a hybrid evolutionary approach that combines GeneticAlgorithms(GA)for global exploration and Evolution Strategies(ES)for local refinement.This co-evolutionary process dynamically adjusts the loss landscape,improvingmodel generalization without relying on analytic gradients or handcrafted heuristics.Experimental evaluations on synthetic tasks and the CIFAR-10 andMNIST datasets demonstrate that our approach consistently outperforms standard losses such as Cross-Entropy and Mean Squared Error in terms of accuracy,convergence,and adaptability.
基金supported by the Natural Science Foundation of Heilongjiang Province(LH2023C028)。
文摘Zinc,an essential trace element,plays a pivotal role in maintaining animal health and physiological functions.This review comprehensively examines zinc metabolism—including absorption dynamics across species(poultry,ruminants,and non-ruminants),transport mechanisms,storage in tissues,e.g.,the liver,and excretion pathways—and its multifaceted effects on animal health.Zinc critically regulates aspects of growth and development,particularly bone formation,as its deficiency induces skeletal deformities in young animals.It modulates immune function through zinc finger proteins,influencing immune organ integrity,lymphocyte proliferation,and cytokine expression.Reproductive performance is significantly affected by zinc,with its deficiency causing impaired spermatogenesis;delayed sexual maturity in males;and reduced litter size,embryonic survival,and placental function in females.At the molecular level,zinc regulates the activity of enzymes(e.g.,SOD),signaling pathways(MAPK,NF-κB),and transcription factors(MTF-1,Sp1)to maintain homeostasis.Both zinc deficiency(due to dietary insufficiency,malabsorption,or physiological stress)and zinc excess(from environmental pollution or feed oversupplementation)adversely affect health,disrupting mineral balance,enzyme function,and gut microbiota.In animal production,inorganic(zinc oxide,zinc sulfate)and organic(zinc methionine)sources of zinc increase growth,immunity,and productivity,although sustainable strategies are needed to mitigate environmental risks.Future research should focus on novel zinc formulations,precision nutrition,and interactions with gut microbiota to optimize livestock health and sustainable husbandry.
