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
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
End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods th...End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods that perform full fine-tuning of pretrained video models often incur substantial computational costs,which become particularly pronounced when processing long video sequences.Moreover,the need for precise temporal boundary annotations makes data labeling extremely expensive.In low-resource settings where annotated samples are scarce,direct fine-tuning tends to cause overfitting.To address these challenges,we introduce Dynamic LowRank Adapter(DyLoRA),a lightweight fine-tuning framework tailored specifically for the TAD task.Built upon the Low-Rank Adaptation(LoRA)architecture,DyLoRA adapts only the key layers of the pretrained model via low-rank decomposition,reducing the number of trainable parameters to less than 5%of full fine-tuning methods.This significantly lowers memory consumption and mitigates overfitting in low-resource settings.Notably,DyLoRA enhances the temporal modeling capability of pretrained models by optimizing temporal dimension weights,thereby alleviating the representation misalignment of temporal features.Experimental results demonstrate that DyLoRA-TAD achieves impressive performance,with 73.9%mAP on THUMOS14,39.52%on ActivityNet-1.3,and 28.2%on Charades,substantially surpassing the best traditional feature-based methods.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
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
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 this paper,an adaptive cubic regularisation algorithm based on affine scaling methods(ARCBASM)is proposed for solving nonlinear equality constrained programming with nonnegative constraints on variables.From the op...In this paper,an adaptive cubic regularisation algorithm based on affine scaling methods(ARCBASM)is proposed for solving nonlinear equality constrained programming with nonnegative constraints on variables.From the optimality conditions of the problem,we introduce appropriate affine matrix and construct an affine scaling ARC subproblem with linearized constraints.Composite step methods and reduced Hessian methods are applied to tackle the linearized constraints.As a result,a standard unconstrained ARC subproblem is deduced and its solution can supply sufficient decrease.The fraction to the boundary rule maintains the strict feasibility(for nonnegative constraints on variables)of every iteration point.Reflection techniques are employed to prevent the iterations from approaching zero too early.Under mild assumptions,global convergence of the algorithm is analysed.Preliminary numerical results are reported.展开更多
1.Introduction The field of exercise science is experiencing a renaissance,with recent research illuminating the molecular,cellular,and systemic effects of physical activity.This is largely due to the now unequivocal ...1.Introduction The field of exercise science is experiencing a renaissance,with recent research illuminating the molecular,cellular,and systemic effects of physical activity.This is largely due to the now unequivocal evidence that a lack of physical activity,not only has direct effects on the prevalence of non-contagious diseases(NCDs)but has profound additive effects of other risk factors for NCD such as obesity and hypertension.1 The articles in this special topic of Journal of Sport and Health Science(JSHS)are dedicated to research on Exercise biochemistry&metabolism.展开更多
Qingke,a staple crop grown on the high-altitude Tibetan Plateau,has evolved a metabolomic profile providing both environmental stress resilience and human nutrition.We review the hypothesis that the metabolites that c...Qingke,a staple crop grown on the high-altitude Tibetan Plateau,has evolved a metabolomic profile providing both environmental stress resilience and human nutrition.We review the hypothesis that the metabolites that confer cold and UV resistance on the crop also facilitate human adaptation to high-altitude stresses.Specifically,β-glucans regulate blood glucose primarily via short-chain fatty acids(SCFAs)produced through gut microbiota fermentation,which directly mediate glucose homeostasis.Phenolamides accumulate via the phenylpropanoid pathway,with chalcone isomerase(CHI)serving as a key enzyme in flavonoid biosynthesis and enhancing UV-B resistance.Under low temperatures,β-glucans improve frost tolerance by modulating osmotic balance and inhibiting ice-nucleating proteins,while lipids maintain membrane fluidity to sustain cellular function during cold stress.Importantly,we explore the hypothesis that these same metabolites,upon consumption,may facilitate human adaptation to high-altitude stresses.This hypothesis is supported by preliminary epidemiological associations between Qingke consumption and favorable health outcomes in high-altitude populations,as well as established bioactivities of the implicated metabolites in vitro and in animal models.However,direct causal evidence in humans and a comprehensive understanding of the underlying molecular mechanisms remain key knowledge gaps that warrant future investigation.Qingke as a unique resource at the interface of agricultural resilience and human nutrition.Understanding its metabolic blueprint will inform the development of functional foods and climate-resilient crops.展开更多
Starting from the foundational static traits underlying the growth and development of flue-cured tobacco, this research conducts a systematic examination of the phenomena and theoretical principles associated with env...Starting from the foundational static traits underlying the growth and development of flue-cured tobacco, this research conducts a systematic examination of the phenomena and theoretical principles associated with environment-driven adaptive changes during its cultivation. It was found that environmental variables-including temperature, light, and moisture-elicit directional shifts in static traits ( e.g. , chemical composition, morphological architecture, and leaf tissue structure) toward enhanced environmental adaptation, characterized by graduality, juvenility, similarity, and correlativity. Upon alterations in ambient conditions, flue-cured tobacco modulates its static traits through integrated physical, chemical, and biological-genetic mechanisms, aiming to optimize resource utilization, mitigate environmental constraints, and preserve internal homeostasis alongside metabolic balance. The investigation further reveals that the adaptive scope of flue-cured tobacco to field environments is malleable and can be extended and elevated via adaptive conditioning commencing at the juvenile stage. In addition, the adaptive alignment between static traits and environmental parameters exerts a substantial impact on the plant s growth dynamics, yield performance, and quality attributes. Beyond its relevance to flue-cured tobacco, the proposed theory offers a meaningful framework for elucidating the pervasive adaptive strategies employed by plants and broader biological systems in response to environmental contingencies.展开更多
In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mec...In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mechanisms during aggregation,it is difficult to conduct effective backdoor attacks.In addition,existing backdoor attack methods are faced with challenges,such as low backdoor accuracy,poor ability to evade anomaly detection,and unstable model training.To address these challenges,a method called adaptive simulation backdoor attack(ASBA)is proposed.Specifically,ASBA improves the stability of model training by manipulating the local training process and using an adaptive mechanism,the ability of the malicious model to evade anomaly detection by combing large simulation training and clipping,and the backdoor accuracy by introducing a stimulus model to amplify the impact of the backdoor in the global model.Extensive comparative experiments under five advanced defense scenarios show that ASBA can effectively evade anomaly detection and achieve high backdoor accuracy in the global model.Furthermore,it exhibits excellent stability and effectiveness after multiple rounds of attacks,outperforming state-of-the-art backdoor attack methods.展开更多
The rapidly evolving cybersecurity threat landscape exposes a critical flaw in traditional educational programs where static curricula cannot adapt swiftly to novel attack vectors.This creates a significant gap betwee...The rapidly evolving cybersecurity threat landscape exposes a critical flaw in traditional educational programs where static curricula cannot adapt swiftly to novel attack vectors.This creates a significant gap between theoretical knowledge and the practical defensive capabilities needed in the field.To address this,we propose TeachSecure-CTI,a novel framework for adaptive cybersecurity curriculumgeneration that integrates real-time Cyber Threat Intelligence(CTI)with AI-driven personalization.Our framework employs a layered architecture featuring a CTI ingestion and clusteringmodule,natural language processing for semantic concept extraction,and a reinforcement learning agent for adaptive content sequencing.Bydynamically aligning learningmaterialswithboththe evolving threat environment and individual learner profiles,TeachSecure-CTI ensures content remains current,relevant,and tailored.A 12-week study with 150 students across three institutions demonstrated that the framework improves learning gains by 34%,significantly exceeding the 12%–21%reported in recent literature.The system achieved 84.8%personalization accuracy,85.9%recognition accuracy for MITRE ATT&CK tactics,and a 31%faster competency development rate compared to static curricula.These findings have implications beyond academia,extending to workforce development,cyber range training,and certification programs.By bridging the gap between dynamic threats and static educational materials,TeachSecure-CTI offers an empirically validated,scalable solution for cultivating cybersecurity professionals capable of responding to modern threats.展开更多
While reinforcement learning-based underwater acoustic adaptive modulation shows promise for enabling environment-adaptive communication as supported by extensive simulation-based research,its practical performance re...While reinforcement learning-based underwater acoustic adaptive modulation shows promise for enabling environment-adaptive communication as supported by extensive simulation-based research,its practical performance remains underexplored in field investigations.To evaluate the practical applicability of this emerging technique in adverse shallow sea channels,a field experiment was conducted using three communication modes:orthogonal frequency division multiplexing(OFDM),M-ary frequency-shift keying(MFSK),and direct sequence spread spectrum(DSSS)for reinforcement learning-driven adaptive modulation.Specifically,a Q-learning method is used to select the optimal modulation mode according to the channel quality quantified by signal-to-noise ratio,multipath spread length,and Doppler frequency offset.Experimental results demonstrate that the reinforcement learning-based adaptive modulation scheme outperformed fixed threshold detection in terms of total throughput and average bit error rate,surpassing conventional adaptive modulation strategies.展开更多
Rheumatoid arthritis(RA)patients face significant psychological challenges alongside physical symptoms,necessitating a comprehensive understanding of how psychological vulnerability and adaptation patterns evolve thro...Rheumatoid arthritis(RA)patients face significant psychological challenges alongside physical symptoms,necessitating a comprehensive understanding of how psychological vulnerability and adaptation patterns evolve throughout the disease course.This review examined 95 studies(2000-2025)from PubMed,Web of Science,and CNKI databases including longitudinal cohorts,randomized controlled trials,and mixed-methods research,to characterize the complex interplay between biological,psychological,and social factors affecting RA patients’mental health.Findings revealed three distinct vulnerability trajectories(45%persistently low,30%fluctuating improvement,25%persistently high)and four adaptation stages,with critical intervention periods occurring 3-6 months postdiagnosis and during disease flares.Multiple factors significantly influence psychological outcomes,including gender(females showing 1.8-fold increased risk),age(younger patients experiencing 42%higher vulnerability),pain intensity,inflammatory markers,and neuroendocrine dysregulation(48%showing cortisol rhythm disruption).Early psychological intervention(within 3 months of diagnosis)demonstrated robust benefits,reducing depression incidence by 42%with effects persisting 24-36 months,while different modalities showed complementary advantages:Cognitive behavioral therapy for depression(Cohen’s d=0.68),mindfulness for pain acceptance(38%improvement),and peer support for meaning reconstruction(25.6%increase).These findings underscore the importance of integrating routine psychological assessment into standard RA care,developing stage-appropriate interventions,and advancing research toward personalized biopsychosocial approaches that address the dynamic psychological dimensions of the disease.展开更多
In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic per...In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic performance evaluation persist.Traditional weighting methods,often based on pre-statistical class counting,tend to overemphasize certain classes while neglecting others,particularly rare sample categories.Approaches like focal loss and other rare-sample segmentation techniques introduce multiple hyperparameters that require manual tuning,leading to increased experimental costs due to their instability.This paper proposes a novel CAWASeg framework to address these limitations.Our approach leverages Grad-CAM technology to generate class activation maps,identifying key feature regions that the model focuses on during decision-making.We introduce a Comprehensive Segmentation Performance Score(CSPS)to dynamically evaluate model performance by converting these activation maps into pseudo mask and comparing them with Ground Truth.Additionally,we design two adaptive weights for each class:a Basic Weight(BW)and a Ratio Weight(RW),which the model adjusts during training based on real-time feedback.Extensive experiments on the COCO-Stuff,CityScapes,and ADE20k datasets demonstrate that our CAWASeg framework significantly improves segmentation performance for rare sample categories while enhancing overall segmentation accuracy.The proposed method offers a robust and efficient solution for addressing class imbalance in semantic segmentation tasks.展开更多
After billions of years of evolution,biological intelligence has converged on unrivalled energy efficiency and environmental adaptability.The human brain,for instance,is highly efficient in information transmission,co...After billions of years of evolution,biological intelligence has converged on unrivalled energy efficiency and environmental adaptability.The human brain,for instance,is highly efficient in information transmission,consuming only about 20 W onaverage in a resting state[1,2].A key to this efficiency is that biological signal transduction and processing rely significantly on multi-ions as the signal carriers.Inspired by this paradigm.展开更多
The present study investigates the quest for a fully distributed Nash equilibrium(NE) in networked non-cooperative games, with particular emphasis on actuator limitations. Existing distributed NE seeking approaches of...The present study investigates the quest for a fully distributed Nash equilibrium(NE) in networked non-cooperative games, with particular emphasis on actuator limitations. Existing distributed NE seeking approaches often overlook practical input constraints or rely on centralized information. To address these issues, a novel edge-based double-layer adaptive control framework is proposed. Specifically, adaptive scaling parameters are embedded into the edge weights of the communication graph, enabling a fully distributed scheme that avoids dependence on centralized or global knowledge. Every participant modifies its strategy by exclusively utilizing local information and communicating with its neighbors to iteratively approach the NE. By incorporating damping terms into the design of the adaptive parameters, the proposed approach effectively suppresses unbounded parameter growth and consequently guarantees the boundedness of the adaptive gains. In addition, to account for actuator saturation, the proposed distributed NE seeking approach incorporates a saturation function, which ensures that control inputs do not exceed allowable ranges. A rigorous Lyapunov-based analysis guarantees the convergence and boundedness of all system variables. Finally, the presentation of simulation results aims to validate the efficacy and theoretical soundness of the proposed approach.展开更多
Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional ...Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.展开更多
To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervis...To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.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 Natural Science Foundation of China(Grant No.62266054)the Major Science and Technology Project of Yunnan Province(Grant No.202402AD080002)the Scientific Research Fund of the Yunnan Provincial Department of Education(Grant No.2025Y0302).
文摘End-to-end Temporal Action Detection(TAD)has achieved remarkable progress in recent years,driven by innovations in model architectures and the emergence of Video Foundation Models(VFMs).However,existing TAD methods that perform full fine-tuning of pretrained video models often incur substantial computational costs,which become particularly pronounced when processing long video sequences.Moreover,the need for precise temporal boundary annotations makes data labeling extremely expensive.In low-resource settings where annotated samples are scarce,direct fine-tuning tends to cause overfitting.To address these challenges,we introduce Dynamic LowRank Adapter(DyLoRA),a lightweight fine-tuning framework tailored specifically for the TAD task.Built upon the Low-Rank Adaptation(LoRA)architecture,DyLoRA adapts only the key layers of the pretrained model via low-rank decomposition,reducing the number of trainable parameters to less than 5%of full fine-tuning methods.This significantly lowers memory consumption and mitigates overfitting in low-resource settings.Notably,DyLoRA enhances the temporal modeling capability of pretrained models by optimizing temporal dimension weights,thereby alleviating the representation misalignment of temporal features.Experimental results demonstrate that DyLoRA-TAD achieves impressive performance,with 73.9%mAP on THUMOS14,39.52%on ActivityNet-1.3,and 28.2%on Charades,substantially surpassing the best traditional feature-based methods.
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.
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 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.
基金Supported by the National Natural Science Foundation of China(12071133)Natural Science Foundation of Henan Province(252300421993)Key Scientific Research Project of Higher Education Institutions in Henan Province(25B110005)。
文摘In this paper,an adaptive cubic regularisation algorithm based on affine scaling methods(ARCBASM)is proposed for solving nonlinear equality constrained programming with nonnegative constraints on variables.From the optimality conditions of the problem,we introduce appropriate affine matrix and construct an affine scaling ARC subproblem with linearized constraints.Composite step methods and reduced Hessian methods are applied to tackle the linearized constraints.As a result,a standard unconstrained ARC subproblem is deduced and its solution can supply sufficient decrease.The fraction to the boundary rule maintains the strict feasibility(for nonnegative constraints on variables)of every iteration point.Reflection techniques are employed to prevent the iterations from approaching zero too early.Under mild assumptions,global convergence of the algorithm is analysed.Preliminary numerical results are reported.
文摘1.Introduction The field of exercise science is experiencing a renaissance,with recent research illuminating the molecular,cellular,and systemic effects of physical activity.This is largely due to the now unequivocal evidence that a lack of physical activity,not only has direct effects on the prevalence of non-contagious diseases(NCDs)but has profound additive effects of other risk factors for NCD such as obesity and hypertension.1 The articles in this special topic of Journal of Sport and Health Science(JSHS)are dedicated to research on Exercise biochemistry&metabolism.
基金supported by the Financial Special Fund,grant number XZ202401JD0027National Barley Industry Technology System(CARS-05-01A-08)+3 种基金the Xizang Agri-Tech Innovation Project(XZNKY-2025-CXGC-T01)the Joint Funds of the National Natural Science Foundation of China(No.U20A2026)the Financial Special Fund,grant number(32401784,2017CZZX001/2,XZNKY-2018-C-021 and NYSTC202401)the China Agriculture Research System of Barley(CARS-05).
文摘Qingke,a staple crop grown on the high-altitude Tibetan Plateau,has evolved a metabolomic profile providing both environmental stress resilience and human nutrition.We review the hypothesis that the metabolites that confer cold and UV resistance on the crop also facilitate human adaptation to high-altitude stresses.Specifically,β-glucans regulate blood glucose primarily via short-chain fatty acids(SCFAs)produced through gut microbiota fermentation,which directly mediate glucose homeostasis.Phenolamides accumulate via the phenylpropanoid pathway,with chalcone isomerase(CHI)serving as a key enzyme in flavonoid biosynthesis and enhancing UV-B resistance.Under low temperatures,β-glucans improve frost tolerance by modulating osmotic balance and inhibiting ice-nucleating proteins,while lipids maintain membrane fluidity to sustain cellular function during cold stress.Importantly,we explore the hypothesis that these same metabolites,upon consumption,may facilitate human adaptation to high-altitude stresses.This hypothesis is supported by preliminary epidemiological associations between Qingke consumption and favorable health outcomes in high-altitude populations,as well as established bioactivities of the implicated metabolites in vitro and in animal models.However,direct causal evidence in humans and a comprehensive understanding of the underlying molecular mechanisms remain key knowledge gaps that warrant future investigation.Qingke as a unique resource at the interface of agricultural resilience and human nutrition.Understanding its metabolic blueprint will inform the development of functional foods and climate-resilient crops.
基金Supported by Changsha Tobacco Company Science and Technology Project(2020-2024A04).
文摘Starting from the foundational static traits underlying the growth and development of flue-cured tobacco, this research conducts a systematic examination of the phenomena and theoretical principles associated with environment-driven adaptive changes during its cultivation. It was found that environmental variables-including temperature, light, and moisture-elicit directional shifts in static traits ( e.g. , chemical composition, morphological architecture, and leaf tissue structure) toward enhanced environmental adaptation, characterized by graduality, juvenility, similarity, and correlativity. Upon alterations in ambient conditions, flue-cured tobacco modulates its static traits through integrated physical, chemical, and biological-genetic mechanisms, aiming to optimize resource utilization, mitigate environmental constraints, and preserve internal homeostasis alongside metabolic balance. The investigation further reveals that the adaptive scope of flue-cured tobacco to field environments is malleable and can be extended and elevated via adaptive conditioning commencing at the juvenile stage. In addition, the adaptive alignment between static traits and environmental parameters exerts a substantial impact on the plant s growth dynamics, yield performance, and quality attributes. Beyond its relevance to flue-cured tobacco, the proposed theory offers a meaningful framework for elucidating the pervasive adaptive strategies employed by plants and broader biological systems in response to environmental contingencies.
文摘In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mechanisms during aggregation,it is difficult to conduct effective backdoor attacks.In addition,existing backdoor attack methods are faced with challenges,such as low backdoor accuracy,poor ability to evade anomaly detection,and unstable model training.To address these challenges,a method called adaptive simulation backdoor attack(ASBA)is proposed.Specifically,ASBA improves the stability of model training by manipulating the local training process and using an adaptive mechanism,the ability of the malicious model to evade anomaly detection by combing large simulation training and clipping,and the backdoor accuracy by introducing a stimulus model to amplify the impact of the backdoor in the global model.Extensive comparative experiments under five advanced defense scenarios show that ASBA can effectively evade anomaly detection and achieve high backdoor accuracy in the global model.Furthermore,it exhibits excellent stability and effectiveness after multiple rounds of attacks,outperforming state-of-the-art backdoor attack methods.
文摘The rapidly evolving cybersecurity threat landscape exposes a critical flaw in traditional educational programs where static curricula cannot adapt swiftly to novel attack vectors.This creates a significant gap between theoretical knowledge and the practical defensive capabilities needed in the field.To address this,we propose TeachSecure-CTI,a novel framework for adaptive cybersecurity curriculumgeneration that integrates real-time Cyber Threat Intelligence(CTI)with AI-driven personalization.Our framework employs a layered architecture featuring a CTI ingestion and clusteringmodule,natural language processing for semantic concept extraction,and a reinforcement learning agent for adaptive content sequencing.Bydynamically aligning learningmaterialswithboththe evolving threat environment and individual learner profiles,TeachSecure-CTI ensures content remains current,relevant,and tailored.A 12-week study with 150 students across three institutions demonstrated that the framework improves learning gains by 34%,significantly exceeding the 12%–21%reported in recent literature.The system achieved 84.8%personalization accuracy,85.9%recognition accuracy for MITRE ATT&CK tactics,and a 31%faster competency development rate compared to static curricula.These findings have implications beyond academia,extending to workforce development,cyber range training,and certification programs.By bridging the gap between dynamic threats and static educational materials,TeachSecure-CTI offers an empirically validated,scalable solution for cultivating cybersecurity professionals capable of responding to modern threats.
基金funding from the National Key Research and Development Program of China(No.2018YFE0110000)the National Natural Science Foundation of China(No.11274259,No.11574258)the Science and Technology Commission Foundation of Shanghai(21DZ1205500)in support of the present research.
文摘While reinforcement learning-based underwater acoustic adaptive modulation shows promise for enabling environment-adaptive communication as supported by extensive simulation-based research,its practical performance remains underexplored in field investigations.To evaluate the practical applicability of this emerging technique in adverse shallow sea channels,a field experiment was conducted using three communication modes:orthogonal frequency division multiplexing(OFDM),M-ary frequency-shift keying(MFSK),and direct sequence spread spectrum(DSSS)for reinforcement learning-driven adaptive modulation.Specifically,a Q-learning method is used to select the optimal modulation mode according to the channel quality quantified by signal-to-noise ratio,multipath spread length,and Doppler frequency offset.Experimental results demonstrate that the reinforcement learning-based adaptive modulation scheme outperformed fixed threshold detection in terms of total throughput and average bit error rate,surpassing conventional adaptive modulation strategies.
基金Supported by Chongqing Health Commission and Chongqing Science and Technology Bureau,No.2023MSXM182。
文摘Rheumatoid arthritis(RA)patients face significant psychological challenges alongside physical symptoms,necessitating a comprehensive understanding of how psychological vulnerability and adaptation patterns evolve throughout the disease course.This review examined 95 studies(2000-2025)from PubMed,Web of Science,and CNKI databases including longitudinal cohorts,randomized controlled trials,and mixed-methods research,to characterize the complex interplay between biological,psychological,and social factors affecting RA patients’mental health.Findings revealed three distinct vulnerability trajectories(45%persistently low,30%fluctuating improvement,25%persistently high)and four adaptation stages,with critical intervention periods occurring 3-6 months postdiagnosis and during disease flares.Multiple factors significantly influence psychological outcomes,including gender(females showing 1.8-fold increased risk),age(younger patients experiencing 42%higher vulnerability),pain intensity,inflammatory markers,and neuroendocrine dysregulation(48%showing cortisol rhythm disruption).Early psychological intervention(within 3 months of diagnosis)demonstrated robust benefits,reducing depression incidence by 42%with effects persisting 24-36 months,while different modalities showed complementary advantages:Cognitive behavioral therapy for depression(Cohen’s d=0.68),mindfulness for pain acceptance(38%improvement),and peer support for meaning reconstruction(25.6%increase).These findings underscore the importance of integrating routine psychological assessment into standard RA care,developing stage-appropriate interventions,and advancing research toward personalized biopsychosocial approaches that address the dynamic psychological dimensions of the disease.
基金supported by the Funds for Central-Guided Local Science and Technology Development(Grant No.202407AC110005)Key Technologies for the Construction of a Whole-Process Intelligent Service System for Neuroendocrine Neoplasm.Supported by 2023 Opening Research Fund of Yunnan Key Laboratory of Digital Communications(YNJTKFB-20230686,YNKLDC-KFKT-202304).
文摘In image analysis,high-precision semantic segmentation predominantly relies on supervised learning.Despite significant advancements driven by deep learning techniques,challenges such as class imbalance and dynamic performance evaluation persist.Traditional weighting methods,often based on pre-statistical class counting,tend to overemphasize certain classes while neglecting others,particularly rare sample categories.Approaches like focal loss and other rare-sample segmentation techniques introduce multiple hyperparameters that require manual tuning,leading to increased experimental costs due to their instability.This paper proposes a novel CAWASeg framework to address these limitations.Our approach leverages Grad-CAM technology to generate class activation maps,identifying key feature regions that the model focuses on during decision-making.We introduce a Comprehensive Segmentation Performance Score(CSPS)to dynamically evaluate model performance by converting these activation maps into pseudo mask and comparing them with Ground Truth.Additionally,we design two adaptive weights for each class:a Basic Weight(BW)and a Ratio Weight(RW),which the model adjusts during training based on real-time feedback.Extensive experiments on the COCO-Stuff,CityScapes,and ADE20k datasets demonstrate that our CAWASeg framework significantly improves segmentation performance for rare sample categories while enhancing overall segmentation accuracy.The proposed method offers a robust and efficient solution for addressing class imbalance in semantic segmentation tasks.
文摘After billions of years of evolution,biological intelligence has converged on unrivalled energy efficiency and environmental adaptability.The human brain,for instance,is highly efficient in information transmission,consuming only about 20 W onaverage in a resting state[1,2].A key to this efficiency is that biological signal transduction and processing rely significantly on multi-ions as the signal carriers.Inspired by this paradigm.
基金supported by the National Natural Science Foundation of China (Grant No.62173009)the National Key Research and Development Program of China (Grant No.2021ZD0112302)。
文摘The present study investigates the quest for a fully distributed Nash equilibrium(NE) in networked non-cooperative games, with particular emphasis on actuator limitations. Existing distributed NE seeking approaches often overlook practical input constraints or rely on centralized information. To address these issues, a novel edge-based double-layer adaptive control framework is proposed. Specifically, adaptive scaling parameters are embedded into the edge weights of the communication graph, enabling a fully distributed scheme that avoids dependence on centralized or global knowledge. Every participant modifies its strategy by exclusively utilizing local information and communicating with its neighbors to iteratively approach the NE. By incorporating damping terms into the design of the adaptive parameters, the proposed approach effectively suppresses unbounded parameter growth and consequently guarantees the boundedness of the adaptive gains. In addition, to account for actuator saturation, the proposed distributed NE seeking approach incorporates a saturation function, which ensures that control inputs do not exceed allowable ranges. A rigorous Lyapunov-based analysis guarantees the convergence and boundedness of all system variables. Finally, the presentation of simulation results aims to validate the efficacy and theoretical soundness of the proposed approach.
基金supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(MSIT)(No.RS-2024-00406320)the Institute of Information&Communica-tions Technology Planning&Evaluation(IITP)-Innovative Human Resource Development for Local Intellectualization Program Grant funded by the Korea government(MSIT)(IITP-2026-RS-2023-00259678).
文摘Domain adaptation aims to reduce the distribution gap between the training data(source domain)and the target data.This enables effective predictions even for domains not seen during training.However,most conventional domain adaptation methods assume a single source domain,making them less suitable for modern deep learning settings that rely on diverse and large-scale datasets.To address this limitation,recent research has focused on Multi-Source Domain Adaptation(MSDA),which aims to learn effectively from multiple source domains.In this paper,we propose Efficient Domain Transition for Multi-source(EDTM),a novel and efficient framework designed to tackle two major challenges in existing MSDA approaches:(1)integrating knowledge across different source domains and(2)aligning label distributions between source and target domains.EDTM leverages an ensemble-based classifier expert mechanism to enhance the contribution of source domains that are more similar to the target domain.To further stabilize the learning process and improve performance,we incorporate imitation learning into the training of the target model.In addition,Maximum Classifier Discrepancy(MCD)is employed to align class-wise label distributions between the source and target domains.Experiments were conducted using Digits-Five,one of the most representative benchmark datasets for MSDA.The results show that EDTM consistently outperforms existing methods in terms of average classification accuracy.Notably,EDTM achieved significantly higher performance on target domains such as Modified National Institute of Standards and Technolog with blended background images(MNIST-M)and Street View House Numbers(SVHN)datasets,demonstrating enhanced generalization compared to baseline approaches.Furthermore,an ablation study analyzing the contribution of each loss component validated the effectiveness of the framework,highlighting the importance of each module in achieving optimal performance.
基金supported by the National Natural Science Foundation of China Funded Project(Project Name:Research on Robust Adaptive Allocation Mechanism of Human Machine Co-Driving System Based on NMS Features,Project Approval Number:52172381).
文摘To address the issue of scarce labeled samples and operational condition variations that degrade the accuracy of fault diagnosis models in variable-condition gearbox fault diagnosis,this paper proposes a semi-supervised masked contrastive learning and domain adaptation(SSMCL-DA)method for gearbox fault diagnosis under variable conditions.Initially,during the unsupervised pre-training phase,a dual signal augmentation strategy is devised,which simultaneously applies random masking in the time domain and random scaling in the frequency domain to unlabeled samples,thereby constructing more challenging positive sample pairs to guide the encoder in learning intrinsic features robust to condition variations.Subsequently,a ConvNeXt-Transformer hybrid architecture is employed,integrating the superior local detail modeling capacity of ConvNeXt with the robust global perception capability of Transformer to enhance feature extraction in complex scenarios.Thereafter,a contrastive learning model is constructed with the optimization objective of maximizing feature similarity across different masked instances of the same sample,enabling the extraction of consistent features from multiple masked perspectives and reducing reliance on labeled data.In the final supervised fine-tuning phase,a multi-scale attention mechanism is incorporated for feature rectification,and a domain adaptation module combining Local Maximum Mean Discrepancy(LMMD)with adversarial learning is proposed.This module embodies a dual mechanism:LMMD facilitates fine-grained class-conditional alignment,compelling features of identical fault classes to converge across varying conditions,while the domain discriminator utilizes adversarial training to guide the feature extractor toward learning domain-invariant features.Working in concert,they markedly diminish feature distribution discrepancies induced by changes in load,rotational speed,and other factors,thereby boosting the model’s adaptability to cross-condition scenarios.Experimental evaluations on the WT planetary gearbox dataset and the Case Western Reserve University(CWRU)bearing dataset demonstrate that the SSMCL-DA model effectively identifies multiple fault classes in gearboxes,with diagnostic performance substantially surpassing that of conventional methods.Under cross-condition scenarios,the model attains fault diagnosis accuracies of 99.21%for the WT planetary gearbox and 99.86%for the bearings,respectively.Furthermore,the model exhibits stable generalization capability in cross-device settings.
