The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness dimin...The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.展开更多
Objective To develop QingNangTCM,a specialized large language model(LLM)tailored for expert-level traditional Chinese medicine(TCM)question-answering and clinical reasoning,addressing the scarcity of domain-specific c...Objective To develop QingNangTCM,a specialized large language model(LLM)tailored for expert-level traditional Chinese medicine(TCM)question-answering and clinical reasoning,addressing the scarcity of domain-specific corpora and specialized alignment.Methods We constructed QnTCM_Dataset,a corpus of 100000 entries,by integrating data from ShenNong_TCM_Dataset and SymMap v2.0,and synthesizing additional samples via retrieval-augmented generation(RAG)and persona-driven generation.The dataset comprehensively covers diagnostic inquiries,prescriptions,and herbal knowledge.Utilizing P-Tuning v2,we fine-tuned the GLM-4-9B-Chat backbone to develop QingNangTCM.A multidimensional evaluation framework,assessing accuracy,coverage,consistency,safety,professionalism,and fluency,was established using metrics such as bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),metric for evaluation of translation with explicit ordering(METEOR),and LLM-as-a-Judge with expert review.Qualitative analysis was conducted across four simulated clinical scenarios:symptom analysis,disease treatment,herb inquiry,and failure cases.Baseline models included GLM-4-9BChat,DeepSeek-V2,HuatuoGPT-II(7B),and GLM-4-9B-Chat(freeze-tuning).Results QingNangTCM achieved the highest scores in BLEU-1/2/3/4(0.425/0.298/0.137/0.064),ROUGE-1/2(0.368/0.157),and METEOR(0.218),demonstrating a balanced and superior normalized performance profile of 0.900 across the dimensions of accuracy,coverage,and consistency.Although its ROUGE-L score(0.299)was lower than that of HuatuoGPT-II(7B)(0.351),it significantly outperformed domain-specific models in expert-validated win rates for professionalism(86%)and safety(73%).Qualitative analysis confirmed that the model strictly adheres to the“symptom-syndrome-pathogenesis-treatment”reasoning chain,though occasional misclassifications and hallucinations persisted when dealing with rare medicinal materials and uncommon syndromes.展开更多
The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in S...The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.展开更多
Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in speci...Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader deployment.Parameter-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational efficiency.Among these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA variants.Despite these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains underexplored.This study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM architectures.Our investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do so.These insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized LLMs.Moreover,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller one.This study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM fine-tuning in resource-constrained environments.展开更多
Configuring computational fluid dynamics(CFD)simulations typically demands extensive domain expertise,limiting broader access.Although large language models(LLMs)have advanced scientific computing,their use in automat...Configuring computational fluid dynamics(CFD)simulations typically demands extensive domain expertise,limiting broader access.Although large language models(LLMs)have advanced scientific computing,their use in automating CFD workflows is underdeveloped.We introduce a novel approach centered on domain-specific LLM adaptation.By fine-tuning Qwen2.5-7B-Instruct on NL2FOAM,our custom dataset of 28,716 natural language-to-OpenFOAM configuration pairs with chain-of-thought(CoT)annotations enables direct translation from natural language descriptions to executable CFD setups.A multi-agent system orchestrates the process,autonomously verifying inputs,generating configurations,running simulations,and correcting errors.Evaluation on a benchmark of 21 diverse flow cases demonstrates state-of-the-art performance,achieving 88.7%solution accuracy and 82.6%first-attempt success rate.This significantly outperforms larger general-purpose models such as Qwen2.5-72B-Instruct,DeepSeek-R1,and Llama3.3-70B-Instruct,while also requiring fewer correction iterations and maintaining high computational efficiency.The results highlight the critical role of domain-specific adaptation in deploying LLM assistants for complex engineering workflows.Our code and fine-tuned model have been deposited at https://github.com/YYgroup/AutoCFD.展开更多
A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehens...A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.展开更多
In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance o...In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance of two advanced models,the Large Language Model(LLM)LLaMA model and NLP BERT model,in the context of airline review sentiment analysis.Through fine-tuning,domain adaptation,and the application of few-shot learning,the study addresses the subtleties of sentiment expressions in airline-related text data.Employing predictive modeling and comparative analysis,the research evaluates the effectiveness of Large Language Model Meta AI(LLaMA)and Bidirectional Encoder Representations from Transformers(BERT)in capturing sentiment intricacies.Fine-tuning,including domain adaptation,enhances the models'performance in sentiment classification tasks.Additionally,the study explores the potential of few-shot learning to improve model generalization using minimal annotated data for targeted sentiment analysis.By conducting experiments on a diverse airline review dataset,the research quantifies the impact of fine-tuning,domain adaptation,and few-shot learning on model performance,providing valuable insights for industries aiming to predict recommendations and enhance customer satisfaction through a deeper understanding of sentiment in user-generated content(UGC).This research contributes to refining sentiment analysis models,ultimately fostering improved customer satisfaction in the airline industry.展开更多
In the era of the Internet of Things,distributed computing alleviates the problem of insufficient terminal computing power by integrating idle resources of heterogeneous devices.However,the imbalance between task exec...In the era of the Internet of Things,distributed computing alleviates the problem of insufficient terminal computing power by integrating idle resources of heterogeneous devices.However,the imbalance between task execution delay and node energy consumption,and the scheduling and adaptation challenges brought about by device heterogeneity,urgently need to be addressed.To tackle this problem,this paper constructs a multi-objective real-time task scheduling model that considers task real-time performance,execution delay,system energy consumption,and node interests.The model aims to minimize the delay upper bound and total energy consumption while maximizing system satisfaction.A real-time task scheduling algorithm based on bilateral matching game is proposed.By designing a bidirectional preference mechanism between tasks and computing nodes,combined with a multi-round stable matching strategy,accurate matching between tasks and nodes is achieved.Simulation results show that compared with the baseline scheme,the proposed algorithm significantly reduces the total execution cost,effectively balances the task execution delay and the energy consumption of compute nodes,and takes into account the interests of each network compute node.展开更多
This study compares the relative efficacy of the continuation task and the model-as-feedbackwriting (MAFW) task in EFL writing development. Ninety intermediate-level Chinese EFL learnerswere randomly assigned to a con...This study compares the relative efficacy of the continuation task and the model-as-feedbackwriting (MAFW) task in EFL writing development. Ninety intermediate-level Chinese EFL learnerswere randomly assigned to a continuation group, a MAFW group, and a control group, each with30 learners. A pretest and a posttest were used to gauge L2 writing development. Results showedthat the continuation task outperformed the MAFW task not only in enhancing the overall qualityof L2 writing, but also in promoting the quality of three components of L2 writing, namely, content,organization, and language. The finding has important implications for L2 writing teaching andlearning.展开更多
With the widespread deployment of assembly robots in smart manufacturing,efficiently offloading tasks and allocating resources in highly dynamic industrial environments has become a critical challenge for Mobile Edge ...With the widespread deployment of assembly robots in smart manufacturing,efficiently offloading tasks and allocating resources in highly dynamic industrial environments has become a critical challenge for Mobile Edge Computing(MEC).To address this challenge,this paper constructs a cloud-edge-end collaborative MEC system that enables assembly robots to offload complex workflow tasks via multiple paths(horizontal,vertical,and hybrid collaboration).Tomitigate uncertainties arising frommobility,the location predictionmodule is employed.This enables proactive channel-quality estimation,providing forward-looking insights for offloading decisions.Furthermore,we propose a fairness-aware joint optimization framework.Utilizing an improved Multi-Agent Deep Reinforcement Learning(MADRL)algorithm whose reward function incorporates total system cost,positional reliability,and timeout penalties,the framework aims to balance resource distribution among assembly robots while maximizing system utility.Simulation results demonstrate that the proposed framework outperforms traditional offloading strategies.By integrating predictive mobility management with fairness-aware optimization,the framework offers a robust solution for dynamic industrial MEC environments.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
The iterative continuation task(ICT)requires English as a foreign language(EFL)learners to read a segment and write a continuation that aligns with the preceding segment of an English novel with successive turns,offer...The iterative continuation task(ICT)requires English as a foreign language(EFL)learners to read a segment and write a continuation that aligns with the preceding segment of an English novel with successive turns,offering exposure to diverse grammatical structures and opportunities for contextualized usage.Given the importance of integrating technology into second language(L2)writing and the critical role that grammar plays in L2 writing development,automated written corrective feedback provided by Grammarly has gained significant attention.This study investigates the impact of Grammarly on grammar learning strategies,grammar grit,and grammar competence among EFL college students engaged in ICT.This study employed a mixed-methods sequential exploratory design;56 participants were divided into an experimental group(n=28),receiving Grammarly feedback for ICT,and a control group(n=28),completing ICT without Grammarly feedback.Quantitative results revealed that both groups showed improvements in L2 grammar learning strategies,grit and competence.For the experimental group,significant differences were observed across all variables of L2 grammar learning strategies,grit,and competence between pre-and post-tests.For the control group,significant differences were only observed in the affective dimension of grammar learning strategies,Consistency of Interest(COI)of grammar grit,and grammar competence.However,the control group presented a significantly higher improvement in grammar competence.Qualitative analysis showed both positive and negative perceptions of Grammarly.The pedagogical implications of integrating Grammarly and ICT for L2 grammar development are discussed.展开更多
In scenarios where ground-based cloud computing infrastructure is unavailable,unmanned aerial vehicles(UAVs)act as mobile edge computing(MEC)servers to provide on-demand computation services for ground terminals.To ad...In scenarios where ground-based cloud computing infrastructure is unavailable,unmanned aerial vehicles(UAVs)act as mobile edge computing(MEC)servers to provide on-demand computation services for ground terminals.To address the challenge of jointly optimizing task scheduling and UAV trajectory under limited resources and high mobility of UAVs,this paper presents PER-MATD3,a multi-agent deep reinforcement learning algorithm with prioritized experience replay(PER)into the Centralized Training with Decentralized Execution(CTDE)framework.Specifically,PER-MATD3 enables each agent to learn a decentralized policy using only local observations during execution,while leveraging a shared replay buffer with prioritized sampling and centralized critic during training to accelerate convergence and improve sample efficiency.Simulation results show that PER-MATD3 reduces average task latency by up to 23%,improves energy efficiency by 21%,and enhances service coverage compared to state-of-the-art baselines,demonstrating its effectiveness and practicality in scenarios without terrestrial networks.展开更多
Advanced technologies like Cyber-Physical Systems(CPS)and the Internet of Things(IoT)have supported modernizing and automating the transportation region through the introduction of Intelligent Transportation Systems(I...Advanced technologies like Cyber-Physical Systems(CPS)and the Internet of Things(IoT)have supported modernizing and automating the transportation region through the introduction of Intelligent Transportation Systems(ITS).Integrating CPS-ITS and IoT provides real-time Vehicle-to-Infrastructure(V2I)communication,supporting better traffic management,safety,and efficiency.These technological innovations generate complex problems that need to be addressed,uniquely about data routing and Task Scheduling(TS)in ITS.Attempts to solve those problems were primarily based on traditional and experimental methods,and the solutions were not so successful due to the dynamic nature of ITS.This is where the scope of Machine learning(ML)and Swarm Intelligence(SI)has significantly impacted dealing with these challenges;in this line,this research paper presents a novel method for TS and data routing in the CPS-ITS.This paper proposes using a cutting-edge ML algorithm for data transmission from CPS-ITS.This ML has Gated Linear Unit-approximated Reinforcement Learning(GLRL).Greedy Iterative-Particle Swarm Optimization(GI-PSO)has been recommended to develop the Particle Swarm Optimization(PSO)for TS.The primary objective of this study is to enhance the security and effectiveness of ITS systems that utilize CPS-ITS.This study trained and validated the models using a network simulation dataset of 50 nodes from numerous ITS environments.The experiments demonstrate that the proposed GLRL reduces End-toEnd Delay(EED)by 12%,enhances data size use from 83.6%to 88.6%,and achieves higher bandwidth allocation,particularly in high-demand scenarios such as multimedia data streams where adherence improved to 98.15%.Furthermore,the GLRL reduced Network Congestion(NC)by 5.5%,demonstrating its efficiency in managing complex traffic conditions across several environments.The model passed simulation tests in three different environments:urban(UE),suburban(SE),and rural(RE).It met the high bandwidth requirements,made task scheduling more efficient,and increased network throughput(NT).This proved that it was robust and flexible enough for scalable ITS applications.These innovations provide robust,scalable solutions for real-time traffic management,ultimately improving safety,reducing NC,and increasing overall NT.This study can affect ITS by developing it to be more responsive,safe,and effective and by creating a perfect method to set up UE,SE,and RE.展开更多
The cloud-fog computing paradigm has emerged as a novel hybrid computing model that integrates computational resources at both fog nodes and cloud servers to address the challenges posed by dynamic and heterogeneous c...The cloud-fog computing paradigm has emerged as a novel hybrid computing model that integrates computational resources at both fog nodes and cloud servers to address the challenges posed by dynamic and heterogeneous computing networks.Finding an optimal computational resource for task offloading and then executing efficiently is a critical issue to achieve a trade-off between energy consumption and transmission delay.In this network,the task processed at fog nodes reduces transmission delay.Still,it increases energy consumption,while routing tasks to the cloud server saves energy at the cost of higher communication delay.Moreover,the order in which offloaded tasks are executed affects the system’s efficiency.For instance,executing lower-priority tasks before higher-priority jobs can disturb the reliability and stability of the system.Therefore,an efficient strategy of optimal computation offloading and task scheduling is required for operational efficacy.In this paper,we introduced a multi-objective and enhanced version of Cheeta Optimizer(CO),namely(MoECO),to jointly optimize the computation offloading and task scheduling in cloud-fog networks to minimize two competing objectives,i.e.,energy consumption and communication delay.MoECO first assigns tasks to the optimal computational nodes and then the allocated tasks are scheduled for processing based on the task priority.The mathematical modelling of CO needs improvement in computation time and convergence speed.Therefore,MoECO is proposed to increase the search capability of agents by controlling the search strategy based on a leader’s location.The adaptive step length operator is adjusted to diversify the solution and thus improves the exploration phase,i.e.,global search strategy.Consequently,this prevents the algorithm from getting trapped in the local optimal solution.Moreover,the interaction factor during the exploitation phase is also adjusted based on the location of the prey instead of the adjacent Cheetah.This increases the exploitation capability of agents,i.e.,local search capability.Furthermore,MoECO employs a multi-objective Pareto-optimal front to simultaneously minimize designated objectives.Comprehensive simulations in MATLAB demonstrate that the proposed algorithm obtains multiple solutions via a Pareto-optimal front and achieves an efficient trade-off between optimization objectives compared to baseline methods.展开更多
In dynamic and uncertain reconnaissance missions,effective task assignment and path planning for multiple unmanned aerial vehicles(UAVs)present significant challenges.A stochastic multi-UAV reconnaissance scheduling p...In dynamic and uncertain reconnaissance missions,effective task assignment and path planning for multiple unmanned aerial vehicles(UAVs)present significant challenges.A stochastic multi-UAV reconnaissance scheduling problem is formulated as a combinatorial optimization task with nonlinear objectives and coupled constraints.To solve the non-deterministic polynomial(NP)-hard problem efficiently,a novel learning-enhanced pigeon-inspired optimization(L-PIO)algorithm is proposed.The algorithm integrates a Q-learning mechanism to dynamically regulate control parameters,enabling adaptive exploration–exploitation trade-offs across different optimization phases.Additionally,geometric abstraction techniques are employed to approximate complex reconnaissance regions using maximum inscribed rectangles and spiral path models,allowing for precise cost modeling of UAV paths.The formal objective function is developed to minimize global flight distance and completion time while maximizing reconnaissance priority and task coverage.A series of simulation experiments are conducted under three scenarios:static task allocation,dynamic task emergence,and UAV failure recovery.Comparative analysis with several updated algorithms demonstrates that L-PIO exhibits superior robustness,adaptability,and computational efficiency.The results verify the algorithm's effectiveness in addressing dynamic reconnaissance task planning in real-time multi-UAV applications.展开更多
In recent years,fog computing has become an important environment for dealing with the Internet of Things.Fog computing was developed to handle large-scale big data by scheduling tasks via cloud computing.Task schedul...In recent years,fog computing has become an important environment for dealing with the Internet of Things.Fog computing was developed to handle large-scale big data by scheduling tasks via cloud computing.Task scheduling is crucial for efficiently handling IoT user requests,thereby improving system performance,cost,and energy consumption across nodes in cloud computing.With the large amount of data and user requests,achieving the optimal solution to the task scheduling problem is challenging,particularly in terms of cost and energy efficiency.In this paper,we develop novel strategies to save energy consumption across nodes in fog computing when users execute tasks through the least-cost paths.Task scheduling is developed using modified artificial ecosystem optimization(AEO),combined with negative swarm operators,Salp Swarm Algorithm(SSA),in order to competitively optimize their capabilities during the exploitation phase of the optimal search process.In addition,the proposed strategy,Enhancement Artificial Ecosystem Optimization Salp Swarm Algorithm(EAEOSSA),attempts to find the most suitable solution.The optimization that combines cost and energy for multi-objective task scheduling optimization problems.The backpack problem is also added to improve both cost and energy in the iFogSim implementation as well.A comparison was made between the proposed strategy and other strategies in terms of time,cost,energy,and productivity.Experimental results showed that the proposed strategy improved energy consumption,cost,and time over other algorithms.Simulation results demonstrate that the proposed algorithm increases the average cost,average energy consumption,and mean service time in most scenarios,with average reductions of up to 21.15%in cost and 25.8%in energy consumption.展开更多
The existing multi-objective wheel profile optimization methods mainly consist of three sub-modules:(1)wheel profile generation,(2)multi-body dynamics simulation,and(3)an optimization algorithm.For the first module,a ...The existing multi-objective wheel profile optimization methods mainly consist of three sub-modules:(1)wheel profile generation,(2)multi-body dynamics simulation,and(3)an optimization algorithm.For the first module,a comparably conservative rotary-scaling finetuning(RSFT)method,which introduces two design variables and an empirical formula,is proposed to fine-tune the traditional wheel profiles for improving their engineering applicability.For the second module,for the TRAXX locomotives serving on the Blankenburg–Rubeland line,an optimization function representing the relationship between the wheel profile and the wheel–rail wear number is established based on Kriging surrogate model(KSM).For the third module,a method combining the regression capability of KSM with the iterative computing power of particle swarm optimization(PSO)is proposed to quickly and reliably implement the task of optimizing wheel profiles.Finally,with the RSFT–KSM–PSO method,we propose two wear-resistant wheel profiles for the TRAXX locomotives serving on the Blankenburg–Rubeland line,namely S1002-S and S1002-M.The S1002-S profile minimizes the total wear number by 30%,while the S1002-M profile makes the wear distribution more uniform through a proper sacrifice of the tread wear number,and the total wear number is reduced by 21%.The quasi-static and hunting stability tests further demonstrate that the profile designed by the RSFT–KSM–PSO method is promising for practical engineering applications.展开更多
基金supported in part by the National Natural Science Foundation of China(NSFC)under Grant 62276109The authors extend their appreciation to the Deanship of Scientific Research at King Saud University for funding this work through the Research Group Project number(ORF-2025-585).
文摘The personalized fine-tuning of large languagemodels(LLMs)on edge devices is severely constrained by limited computation resources.Although split federated learning alleviates on-device burdens,its effectiveness diminishes in few-shot reasoning scenarios due to the low data efficiency of conventional supervised fine-tuning,which leads to excessive communication overhead.To address this,we propose Language-Empowered Split Fine-Tuning(LESFT),a framework that integrates split architectures with a contrastive-inspired fine-tuning paradigm.LESFT simultaneously learns frommultiple logically equivalent but linguistically diverse reasoning chains,providing richer supervisory signals and improving data efficiency.This process-oriented training allows more effective reasoning adaptation with fewer samples.Extensive experiments demonstrate that LESFT consistently outperforms strong baselines such as SplitLoRA in task accuracy.LESFT consistently outperforms strong baselines on GSM8K,CommonsenseQA,and AQUA_RAT,with the largest gains observed on Qwen2.5-3B.These results indicate that LESFT can effectively adapt large language models for reasoning tasks under the computational and communication constraints of edge environments.
基金Hebei Province Higher Education Scientific Research Project(QN2025367)Zhangjiakou City 2022 Municipal Science and Technology Plan Self-raised Fund Project(221105D)Hebei Province Education Science“14th Five-Year Plan”Project(2404224).
文摘Objective To develop QingNangTCM,a specialized large language model(LLM)tailored for expert-level traditional Chinese medicine(TCM)question-answering and clinical reasoning,addressing the scarcity of domain-specific corpora and specialized alignment.Methods We constructed QnTCM_Dataset,a corpus of 100000 entries,by integrating data from ShenNong_TCM_Dataset and SymMap v2.0,and synthesizing additional samples via retrieval-augmented generation(RAG)and persona-driven generation.The dataset comprehensively covers diagnostic inquiries,prescriptions,and herbal knowledge.Utilizing P-Tuning v2,we fine-tuned the GLM-4-9B-Chat backbone to develop QingNangTCM.A multidimensional evaluation framework,assessing accuracy,coverage,consistency,safety,professionalism,and fluency,was established using metrics such as bilingual evaluation understudy(BLEU),recall-oriented understudy for gisting evaluation(ROUGE),metric for evaluation of translation with explicit ordering(METEOR),and LLM-as-a-Judge with expert review.Qualitative analysis was conducted across four simulated clinical scenarios:symptom analysis,disease treatment,herb inquiry,and failure cases.Baseline models included GLM-4-9BChat,DeepSeek-V2,HuatuoGPT-II(7B),and GLM-4-9B-Chat(freeze-tuning).Results QingNangTCM achieved the highest scores in BLEU-1/2/3/4(0.425/0.298/0.137/0.064),ROUGE-1/2(0.368/0.157),and METEOR(0.218),demonstrating a balanced and superior normalized performance profile of 0.900 across the dimensions of accuracy,coverage,and consistency.Although its ROUGE-L score(0.299)was lower than that of HuatuoGPT-II(7B)(0.351),it significantly outperformed domain-specific models in expert-validated win rates for professionalism(86%)and safety(73%).Qualitative analysis confirmed that the model strictly adheres to the“symptom-syndrome-pathogenesis-treatment”reasoning chain,though occasional misclassifications and hallucinations persisted when dealing with rare medicinal materials and uncommon syndromes.
基金the research project LaTe4PoliticES(PID2022-138099OB-I00)funded by MCIN/AEI/10.13039/501100011033 and the European Fund for Regional Development(ERDF)-a way to make Europe.Tomás Bernal-Beltrán is supported by University of Murcia through the predoctoral programme.
文摘The malicious dissemination of hate speech via compromised accounts,automated bot networks and malware-driven social media campaigns has become a growing cybersecurity concern.Automatically detecting such content in Spanish is challenging due to linguistic complexity and the scarcity of annotated resources.In this paper,we compare two predominant AI-based approaches for the forensic detection of malicious hate speech:(1)finetuning encoder-only models that have been trained in Spanish and(2)In-Context Learning techniques(Zero-and Few-Shot Learning)with large-scale language models.Our approach goes beyond binary classification,proposing a comprehensive,multidimensional evaluation that labels each text by:(1)type of speech,(2)recipient,(3)level of intensity(ordinal)and(4)targeted group(multi-label).Performance is evaluated using an annotated Spanish corpus,standard metrics such as precision,recall and F1-score and stability-oriented metrics to evaluate the stability of the transition from zero-shot to few-shot prompting(Zero-to-Few Shot Retention and Zero-to-Few Shot Gain)are applied.The results indicate that fine-tuned encoder-only models(notably MarIA and BETO variants)consistently deliver the strongest and most reliable performance:in our experiments their macro F1-scores lie roughly in the range of approximately 46%–66%depending on the task.Zero-shot approaches are much less stable and typically yield substantially lower performance(observed F1-scores range approximately 0%–39%),often producing invalid outputs in practice.Few-shot prompting(e.g.,Qwen 38B,Mistral 7B)generally improves stability and recall relative to pure zero-shot,bringing F1-scores into a moderate range of approximately 20%–51%but still falling short of fully fine-tuned models.These findings highlight the importance of supervised adaptation and discuss the potential of both paradigms as components in AI-powered cybersecurity and malware forensics systems designed to identify and mitigate coordinated online hate campaigns.
基金supported by the National Key R&D Program of China(No.2021YFB0301200)National Natural Science Foundation of China(No.62025208).
文摘Large-scale Language Models(LLMs)have achieved significant breakthroughs in Natural Language Processing(NLP),driven by the pre-training and fine-tuning paradigm.While this approach allows models to specialize in specific tasks with reduced training costs,the substantial memory requirements during fine-tuning present a barrier to broader deployment.Parameter-Efficient Fine-Tuning(PEFT)techniques,such as Low-Rank Adaptation(LoRA),and parameter quantization methods have emerged as solutions to address these challenges by optimizing memory usage and computational efficiency.Among these,QLoRA,which combines PEFT and quantization,has demonstrated notable success in reducing memory footprints during fine-tuning,prompting the development of various QLoRA variants.Despite these advancements,the quantitative impact of key variables on the fine-tuning performance of quantized LLMs remains underexplored.This study presents a comprehensive analysis of these key variables,focusing on their influence across different layer types and depths within LLM architectures.Our investigation uncovers several critical findings:(1)Larger layers,such as MLP layers,can maintain performance despite reductions in adapter rank,while smaller layers,like self-attention layers,aremore sensitive to such changes;(2)The effectiveness of balancing factors depends more on specific values rather than layer type or depth;(3)In quantization-aware fine-tuning,larger layers can effectively utilize smaller adapters,whereas smaller layers struggle to do so.These insights suggest that layer type is a more significant determinant of fine-tuning success than layer depth when optimizing quantized LLMs.Moreover,for the same discount of trainable parameters,reducing the trainable parameters in a larger layer is more effective in preserving fine-tuning accuracy than in a smaller one.This study provides valuable guidance for more efficient fine-tuning strategies and opens avenues for further research into optimizing LLM fine-tuning in resource-constrained environments.
基金supported by the National Natural Science Foundation of China(Grant Nos.52306126,22350710788,12432010,11988102,92270203)the Xplore Prize.
文摘Configuring computational fluid dynamics(CFD)simulations typically demands extensive domain expertise,limiting broader access.Although large language models(LLMs)have advanced scientific computing,their use in automating CFD workflows is underdeveloped.We introduce a novel approach centered on domain-specific LLM adaptation.By fine-tuning Qwen2.5-7B-Instruct on NL2FOAM,our custom dataset of 28,716 natural language-to-OpenFOAM configuration pairs with chain-of-thought(CoT)annotations enables direct translation from natural language descriptions to executable CFD setups.A multi-agent system orchestrates the process,autonomously verifying inputs,generating configurations,running simulations,and correcting errors.Evaluation on a benchmark of 21 diverse flow cases demonstrates state-of-the-art performance,achieving 88.7%solution accuracy and 82.6%first-attempt success rate.This significantly outperforms larger general-purpose models such as Qwen2.5-72B-Instruct,DeepSeek-R1,and Llama3.3-70B-Instruct,while also requiring fewer correction iterations and maintaining high computational efficiency.The results highlight the critical role of domain-specific adaptation in deploying LLM assistants for complex engineering workflows.Our code and fine-tuned model have been deposited at https://github.com/YYgroup/AutoCFD.
文摘A complete examination of Large Language Models’strengths,problems,and applications is needed due to their rising use across disciplines.Current studies frequently focus on single-use situations and lack a comprehensive understanding of LLM architectural performance,strengths,and weaknesses.This gap precludes finding the appropriate models for task-specific applications and limits awareness of emerging LLM optimization and deployment strategies.In this research,50 studies on 25+LLMs,including GPT-3,GPT-4,Claude 3.5,DeepKet,and hybrid multimodal frameworks like ContextDET and GeoRSCLIP,are thoroughly reviewed.We propose LLM application taxonomy by grouping techniques by task focus—healthcare,chemistry,sentiment analysis,agent-based simulations,and multimodal integration.Advanced methods like parameter-efficient tuning(LoRA),quantumenhanced embeddings(DeepKet),retrieval-augmented generation(RAG),and safety-focused models(GalaxyGPT)are evaluated for dataset requirements,computational efficiency,and performance measures.Frameworks for ethical issues,data limited hallucinations,and KDGI-enhanced fine-tuning like Woodpecker’s post-remedy corrections are highlighted.The investigation’s scope,mad,and methods are described,but the primary results are not.The work reveals that domain-specialized fine-tuned LLMs employing RAG and quantum-enhanced embeddings performbetter for context-heavy applications.In medical text normalization,ChatGPT-4 outperforms previous models,while two multimodal frameworks,GeoRSCLIP,increase remote sensing.Parameter-efficient tuning technologies like LoRA have minimal computing cost and similar performance,demonstrating the necessity for adaptive models in multiple domains.To discover the optimum domain-specific models,explain domain-specific fine-tuning,and present quantum andmultimodal LLMs to address scalability and cross-domain issues.The framework helps academics and practitioners identify,adapt,and innovate LLMs for different purposes.This work advances the field of efficient,interpretable,and ethical LLM application research.
文摘In the rapidly evolving landscape of natural language processing(NLP)and sentiment analysis,improving the accuracy and efficiency of sentiment classification models is crucial.This paper investigates the performance of two advanced models,the Large Language Model(LLM)LLaMA model and NLP BERT model,in the context of airline review sentiment analysis.Through fine-tuning,domain adaptation,and the application of few-shot learning,the study addresses the subtleties of sentiment expressions in airline-related text data.Employing predictive modeling and comparative analysis,the research evaluates the effectiveness of Large Language Model Meta AI(LLaMA)and Bidirectional Encoder Representations from Transformers(BERT)in capturing sentiment intricacies.Fine-tuning,including domain adaptation,enhances the models'performance in sentiment classification tasks.Additionally,the study explores the potential of few-shot learning to improve model generalization using minimal annotated data for targeted sentiment analysis.By conducting experiments on a diverse airline review dataset,the research quantifies the impact of fine-tuning,domain adaptation,and few-shot learning on model performance,providing valuable insights for industries aiming to predict recommendations and enhance customer satisfaction through a deeper understanding of sentiment in user-generated content(UGC).This research contributes to refining sentiment analysis models,ultimately fostering improved customer satisfaction in the airline industry.
基金Supported by the National Program on Key Basic Research Project(2020YFA0713600)the National Natural Science Foundation of China(62272214)。
文摘In the era of the Internet of Things,distributed computing alleviates the problem of insufficient terminal computing power by integrating idle resources of heterogeneous devices.However,the imbalance between task execution delay and node energy consumption,and the scheduling and adaptation challenges brought about by device heterogeneity,urgently need to be addressed.To tackle this problem,this paper constructs a multi-objective real-time task scheduling model that considers task real-time performance,execution delay,system energy consumption,and node interests.The model aims to minimize the delay upper bound and total energy consumption while maximizing system satisfaction.A real-time task scheduling algorithm based on bilateral matching game is proposed.By designing a bidirectional preference mechanism between tasks and computing nodes,combined with a multi-round stable matching strategy,accurate matching between tasks and nodes is achieved.Simulation results show that compared with the baseline scheme,the proposed algorithm significantly reduces the total execution cost,effectively balances the task execution delay and the energy consumption of compute nodes,and takes into account the interests of each network compute node.
文摘This study compares the relative efficacy of the continuation task and the model-as-feedbackwriting (MAFW) task in EFL writing development. Ninety intermediate-level Chinese EFL learnerswere randomly assigned to a continuation group, a MAFW group, and a control group, each with30 learners. A pretest and a posttest were used to gauge L2 writing development. Results showedthat the continuation task outperformed the MAFW task not only in enhancing the overall qualityof L2 writing, but also in promoting the quality of three components of L2 writing, namely, content,organization, and language. The finding has important implications for L2 writing teaching andlearning.
基金supported by the National Key R&D Program of China under Grant Nos.2024YFD2400200 and 2024YFD2400204supported in part by the Science and Technology Development Program for the Two Zones under Grant No.2023LQ02004.
文摘With the widespread deployment of assembly robots in smart manufacturing,efficiently offloading tasks and allocating resources in highly dynamic industrial environments has become a critical challenge for Mobile Edge Computing(MEC).To address this challenge,this paper constructs a cloud-edge-end collaborative MEC system that enables assembly robots to offload complex workflow tasks via multiple paths(horizontal,vertical,and hybrid collaboration).Tomitigate uncertainties arising frommobility,the location predictionmodule is employed.This enables proactive channel-quality estimation,providing forward-looking insights for offloading decisions.Furthermore,we propose a fairness-aware joint optimization framework.Utilizing an improved Multi-Agent Deep Reinforcement Learning(MADRL)algorithm whose reward function incorporates total system cost,positional reliability,and timeout penalties,the framework aims to balance resource distribution among assembly robots while maximizing system utility.Simulation results demonstrate that the proposed framework outperforms traditional offloading strategies.By integrating predictive mobility management with fairness-aware optimization,the framework offers a robust solution for dynamic industrial MEC environments.
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.
文摘The iterative continuation task(ICT)requires English as a foreign language(EFL)learners to read a segment and write a continuation that aligns with the preceding segment of an English novel with successive turns,offering exposure to diverse grammatical structures and opportunities for contextualized usage.Given the importance of integrating technology into second language(L2)writing and the critical role that grammar plays in L2 writing development,automated written corrective feedback provided by Grammarly has gained significant attention.This study investigates the impact of Grammarly on grammar learning strategies,grammar grit,and grammar competence among EFL college students engaged in ICT.This study employed a mixed-methods sequential exploratory design;56 participants were divided into an experimental group(n=28),receiving Grammarly feedback for ICT,and a control group(n=28),completing ICT without Grammarly feedback.Quantitative results revealed that both groups showed improvements in L2 grammar learning strategies,grit and competence.For the experimental group,significant differences were observed across all variables of L2 grammar learning strategies,grit,and competence between pre-and post-tests.For the control group,significant differences were only observed in the affective dimension of grammar learning strategies,Consistency of Interest(COI)of grammar grit,and grammar competence.However,the control group presented a significantly higher improvement in grammar competence.Qualitative analysis showed both positive and negative perceptions of Grammarly.The pedagogical implications of integrating Grammarly and ICT for L2 grammar development are discussed.
基金supported by the National Natural Science Foundation of China under Grant No.61701100.
文摘In scenarios where ground-based cloud computing infrastructure is unavailable,unmanned aerial vehicles(UAVs)act as mobile edge computing(MEC)servers to provide on-demand computation services for ground terminals.To address the challenge of jointly optimizing task scheduling and UAV trajectory under limited resources and high mobility of UAVs,this paper presents PER-MATD3,a multi-agent deep reinforcement learning algorithm with prioritized experience replay(PER)into the Centralized Training with Decentralized Execution(CTDE)framework.Specifically,PER-MATD3 enables each agent to learn a decentralized policy using only local observations during execution,while leveraging a shared replay buffer with prioritized sampling and centralized critic during training to accelerate convergence and improve sample efficiency.Simulation results show that PER-MATD3 reduces average task latency by up to 23%,improves energy efficiency by 21%,and enhances service coverage compared to state-of-the-art baselines,demonstrating its effectiveness and practicality in scenarios without terrestrial networks.
基金funded by Taif University,Taif,Saudi Arabia,project number(TU-DSPP-2024-17)。
文摘Advanced technologies like Cyber-Physical Systems(CPS)and the Internet of Things(IoT)have supported modernizing and automating the transportation region through the introduction of Intelligent Transportation Systems(ITS).Integrating CPS-ITS and IoT provides real-time Vehicle-to-Infrastructure(V2I)communication,supporting better traffic management,safety,and efficiency.These technological innovations generate complex problems that need to be addressed,uniquely about data routing and Task Scheduling(TS)in ITS.Attempts to solve those problems were primarily based on traditional and experimental methods,and the solutions were not so successful due to the dynamic nature of ITS.This is where the scope of Machine learning(ML)and Swarm Intelligence(SI)has significantly impacted dealing with these challenges;in this line,this research paper presents a novel method for TS and data routing in the CPS-ITS.This paper proposes using a cutting-edge ML algorithm for data transmission from CPS-ITS.This ML has Gated Linear Unit-approximated Reinforcement Learning(GLRL).Greedy Iterative-Particle Swarm Optimization(GI-PSO)has been recommended to develop the Particle Swarm Optimization(PSO)for TS.The primary objective of this study is to enhance the security and effectiveness of ITS systems that utilize CPS-ITS.This study trained and validated the models using a network simulation dataset of 50 nodes from numerous ITS environments.The experiments demonstrate that the proposed GLRL reduces End-toEnd Delay(EED)by 12%,enhances data size use from 83.6%to 88.6%,and achieves higher bandwidth allocation,particularly in high-demand scenarios such as multimedia data streams where adherence improved to 98.15%.Furthermore,the GLRL reduced Network Congestion(NC)by 5.5%,demonstrating its efficiency in managing complex traffic conditions across several environments.The model passed simulation tests in three different environments:urban(UE),suburban(SE),and rural(RE).It met the high bandwidth requirements,made task scheduling more efficient,and increased network throughput(NT).This proved that it was robust and flexible enough for scalable ITS applications.These innovations provide robust,scalable solutions for real-time traffic management,ultimately improving safety,reducing NC,and increasing overall NT.This study can affect ITS by developing it to be more responsive,safe,and effective and by creating a perfect method to set up UE,SE,and RE.
基金appreciation to the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R384)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The cloud-fog computing paradigm has emerged as a novel hybrid computing model that integrates computational resources at both fog nodes and cloud servers to address the challenges posed by dynamic and heterogeneous computing networks.Finding an optimal computational resource for task offloading and then executing efficiently is a critical issue to achieve a trade-off between energy consumption and transmission delay.In this network,the task processed at fog nodes reduces transmission delay.Still,it increases energy consumption,while routing tasks to the cloud server saves energy at the cost of higher communication delay.Moreover,the order in which offloaded tasks are executed affects the system’s efficiency.For instance,executing lower-priority tasks before higher-priority jobs can disturb the reliability and stability of the system.Therefore,an efficient strategy of optimal computation offloading and task scheduling is required for operational efficacy.In this paper,we introduced a multi-objective and enhanced version of Cheeta Optimizer(CO),namely(MoECO),to jointly optimize the computation offloading and task scheduling in cloud-fog networks to minimize two competing objectives,i.e.,energy consumption and communication delay.MoECO first assigns tasks to the optimal computational nodes and then the allocated tasks are scheduled for processing based on the task priority.The mathematical modelling of CO needs improvement in computation time and convergence speed.Therefore,MoECO is proposed to increase the search capability of agents by controlling the search strategy based on a leader’s location.The adaptive step length operator is adjusted to diversify the solution and thus improves the exploration phase,i.e.,global search strategy.Consequently,this prevents the algorithm from getting trapped in the local optimal solution.Moreover,the interaction factor during the exploitation phase is also adjusted based on the location of the prey instead of the adjacent Cheetah.This increases the exploitation capability of agents,i.e.,local search capability.Furthermore,MoECO employs a multi-objective Pareto-optimal front to simultaneously minimize designated objectives.Comprehensive simulations in MATLAB demonstrate that the proposed algorithm obtains multiple solutions via a Pareto-optimal front and achieves an efficient trade-off between optimization objectives compared to baseline methods.
基金supported by the National Natural Science Foundation of China(Nos.T2121003,U24B20156)Open Fund of the National Key Laboratory of Helicopter Aeromechanics(No.2024-ZSJ-LB-02-06)。
文摘In dynamic and uncertain reconnaissance missions,effective task assignment and path planning for multiple unmanned aerial vehicles(UAVs)present significant challenges.A stochastic multi-UAV reconnaissance scheduling problem is formulated as a combinatorial optimization task with nonlinear objectives and coupled constraints.To solve the non-deterministic polynomial(NP)-hard problem efficiently,a novel learning-enhanced pigeon-inspired optimization(L-PIO)algorithm is proposed.The algorithm integrates a Q-learning mechanism to dynamically regulate control parameters,enabling adaptive exploration–exploitation trade-offs across different optimization phases.Additionally,geometric abstraction techniques are employed to approximate complex reconnaissance regions using maximum inscribed rectangles and spiral path models,allowing for precise cost modeling of UAV paths.The formal objective function is developed to minimize global flight distance and completion time while maximizing reconnaissance priority and task coverage.A series of simulation experiments are conducted under three scenarios:static task allocation,dynamic task emergence,and UAV failure recovery.Comparative analysis with several updated algorithms demonstrates that L-PIO exhibits superior robustness,adaptability,and computational efficiency.The results verify the algorithm's effectiveness in addressing dynamic reconnaissance task planning in real-time multi-UAV applications.
基金supported and funded by theDeanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University(IMSIU)(grant number IMSIU-DDRSP2503).
文摘In recent years,fog computing has become an important environment for dealing with the Internet of Things.Fog computing was developed to handle large-scale big data by scheduling tasks via cloud computing.Task scheduling is crucial for efficiently handling IoT user requests,thereby improving system performance,cost,and energy consumption across nodes in cloud computing.With the large amount of data and user requests,achieving the optimal solution to the task scheduling problem is challenging,particularly in terms of cost and energy efficiency.In this paper,we develop novel strategies to save energy consumption across nodes in fog computing when users execute tasks through the least-cost paths.Task scheduling is developed using modified artificial ecosystem optimization(AEO),combined with negative swarm operators,Salp Swarm Algorithm(SSA),in order to competitively optimize their capabilities during the exploitation phase of the optimal search process.In addition,the proposed strategy,Enhancement Artificial Ecosystem Optimization Salp Swarm Algorithm(EAEOSSA),attempts to find the most suitable solution.The optimization that combines cost and energy for multi-objective task scheduling optimization problems.The backpack problem is also added to improve both cost and energy in the iFogSim implementation as well.A comparison was made between the proposed strategy and other strategies in terms of time,cost,energy,and productivity.Experimental results showed that the proposed strategy improved energy consumption,cost,and time over other algorithms.Simulation results demonstrate that the proposed algorithm increases the average cost,average energy consumption,and mean service time in most scenarios,with average reductions of up to 21.15%in cost and 25.8%in energy consumption.
基金the Assets4Rail Project which is funded by the Shift2Rail Joint Undertaking under the EU’s H2020 program(Grant No.826250)the Open Research Fund of State Key Laboratory of Traction Power of Southwest Jiaotong University(Grant No.TPL2011)+1 种基金part of the experiment data concerning the railway line is supported by the DynoTRAIN Project,funded by European Commission(Grant No.234079)The first author is also supported by the China Scholarship Council(Grant No.201707000113).
文摘The existing multi-objective wheel profile optimization methods mainly consist of three sub-modules:(1)wheel profile generation,(2)multi-body dynamics simulation,and(3)an optimization algorithm.For the first module,a comparably conservative rotary-scaling finetuning(RSFT)method,which introduces two design variables and an empirical formula,is proposed to fine-tune the traditional wheel profiles for improving their engineering applicability.For the second module,for the TRAXX locomotives serving on the Blankenburg–Rubeland line,an optimization function representing the relationship between the wheel profile and the wheel–rail wear number is established based on Kriging surrogate model(KSM).For the third module,a method combining the regression capability of KSM with the iterative computing power of particle swarm optimization(PSO)is proposed to quickly and reliably implement the task of optimizing wheel profiles.Finally,with the RSFT–KSM–PSO method,we propose two wear-resistant wheel profiles for the TRAXX locomotives serving on the Blankenburg–Rubeland line,namely S1002-S and S1002-M.The S1002-S profile minimizes the total wear number by 30%,while the S1002-M profile makes the wear distribution more uniform through a proper sacrifice of the tread wear number,and the total wear number is reduced by 21%.The quasi-static and hunting stability tests further demonstrate that the profile designed by the RSFT–KSM–PSO method is promising for practical engineering applications.
