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
Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinct...Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations.However,they often neglect the complex contextual dependencies among image patches,resulting in incomplete local representations and limited segmentation accuracy.To address these issues,we propose the Context Patch Fusion with Class Token Enhancement(CPF-CTE)framework,which exploits contextual relations among patches to enrich feature repre-sentations and improve segmentation.At its core,the Contextual-Fusion Bidirectional Long Short-Term Memory(CF-BiLSTM)module captures spatial dependencies between patches and enables bidirectional information flow,yield-ing a more comprehensive understanding of spatial correlations.This strengthens feature learning and segmentation robustness.Moreover,we introduce learnable class tokens that dynamically encode and refine class-specific semantics,enhancing discriminative capability.By effectively integrating spatial and semantic cues,CPF-CTE produces richer and more accurate representations of image content.Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate that CPF-CTE consistently surpasses prior WSSS methods.展开更多
Weakly supervised semantic segmentation(WSSS)is a tricky task,which only provides category information for segmentation prediction.Thus,the key stage of WSSS is to generate the pseudo labels.For convolutional neural n...Weakly supervised semantic segmentation(WSSS)is a tricky task,which only provides category information for segmentation prediction.Thus,the key stage of WSSS is to generate the pseudo labels.For convolutional neural network(CNN)based methods,in which class activation mapping(CAM)is proposed to obtain the pseudo labels,and only concentrates on the most discriminative parts.Recently,transformer-based methods utilize attention map from the multi-headed self-attention(MHSA)module to predict pseudo labels,which usually contain obvious background noise and incoherent object area.To solve the above problems,we use the Conformer as our backbone,which is a parallel network based on convolutional neural network(CNN)and Transformer.The two branches generate pseudo labels and refine them independently,and can effectively combine the advantages of CNN and Transformer.However,the parallel structure is not close enough in the information communication.Thus,parallel structure can result in poor details about pseudo labels,and the background noise still exists.To alleviate this problem,we propose enhancing convolution CAM(ECCAM)model,which have three improved modules based on enhancing convolution,including deeper stem(DStem),convolutional feed-forward network(CFFN)and feature coupling unit with convolution(FCUConv).The ECCAM could make Conformer have tighter interaction between CNN and Transformer branches.After experimental verification,the improved modules we propose can help the network perceive more local information from images,making the final segmentation results more refined.Compared with similar architecture,our modules greatly improve the semantic segmentation performance and achieve70.2%mean intersection over union(mIoU)on the PASCAL VOC 2012 dataset.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
In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can...In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.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
Background Evidence on the effects of different exercise interventions on cognitive function is insufficient.Aims To evaluate the feasibility and effects of remotely supervised aerobic exercise(AE)and resistance exerc...Background Evidence on the effects of different exercise interventions on cognitive function is insufficient.Aims To evaluate the feasibility and effects of remotely supervised aerobic exercise(AE)and resistance exercise(RE)interventions in older adults with mild cognitive impairment(MCI).Methods This study is a 6-month pilot three-arm randomised controlled trial.Eligible participants(n=108)were recruited and randomised to the AE group,RE group or control(CON)group with a 1:1:1 ratio.Interventions were delivered at home with remote supervision.We evaluated participants’global cognition,memory,executive function,attention,physical activity levels,physical performance and muscle strength of limbs at baseline,3 months(T1)and 6 months(T2)after randomisation.A linear mixed-effects model was adopted for data analyses after controlling for covariates.Tukey’s method was used for adjusting for multiple comparisons.Sensitivity analyses were performed after excluding individuals with low compliance rates.Results 15(13.89%)participants dropped out.The median compliance rates in the AE group and RE group were 67.31%and 93.27%,respectively.After adjusting for covariates,the scores of the Alzheimer’s Disease Assessment Scale-Cognitive subscale in the AE group decreased by 2.04(95%confidence interval(CI)−3.41 to−0.67,t=−2.94,p=0.004)and 1.53(95%CI−2.88 to−0.17,t=−2.22,p=0.028)points more than those in the CON group at T1 and T2,respectively.The effects of AE were still significant at T1(estimate=−1.70,95%CI−3.20 to−0.21,t=−2.69,p=0.021),but lost statistical significance at T2 after adjusting for multiple comparisons.As for executive function,the Stroop time interference in the RE group decreased by 11.76 s(95%CI−21.62 to−1.90,t=−2.81,p=0.015)more than that in the AE group at T2 after Tukey’s adjustment.No other significant effects on cognitive functions were found.Conclusions Both remotely supervised AE and RE programmes are feasible in older adults with MCI.AE has positive effects on global cognition,and RE improves executive function.展开更多
Existing weakly supervised semantic segmentation(WSSS)methods based on image-level labels always rely on class activation maps(CAMs),which measure the relationships between features and classifiers.However,CAMs only f...Existing weakly supervised semantic segmentation(WSSS)methods based on image-level labels always rely on class activation maps(CAMs),which measure the relationships between features and classifiers.However,CAMs only focus on the most discriminative regions of images,resulting in their poor coverage performance.We attribute this to the deficiency in the recognition ability of a single classifier and the negative impacts caused by magnitudes during the CAMs normalisation process.To address the aforementioned issues,we propose to construct selective multiple classifiers(SMC).During the training process,we extract multiple prototypes for each class and store them in the corresponding memory bank.These prototypes are divided into foreground and background prototypes,with the former used to identify foreground objects and the latter aimed at preventing the false activation of background pixels.As for the inference stage,multiple prototypes are adaptively selected from the memory bank for each image as SMC.Subsequently,CAMs are generated by measuring the angle between SMC and features.We enhance the recognition ability of classifiers by adaptively constructing multiple classifiers for each image,while only relying on angle measurement to generate CAMs can alleviate the suppression phenomenon caused by magnitudes.Furthermore,SMC can be integrated into other WSSS approaches to help generate better CAMs.Extensive experiments conducted on standard WSSS benchmarks such as PASCAL VOC 2012 and MS COCO 2014 demonstrate the superiority of our proposed method.展开更多
Background Zonal application maps are designed to represent field variability using key variables that can be translated into tailored management practices.For cotton,zonal maps for crop growth regulator(CGR)applicati...Background Zonal application maps are designed to represent field variability using key variables that can be translated into tailored management practices.For cotton,zonal maps for crop growth regulator(CGR)applications under variable-rate(VR)strategies are commonly based exclusively on vegetation indices(VIs)variability.However,VIs often saturate in dense crop vegetation areas,limiting their effectiveness in distinguishing variability in crop growth.This study aimed to compare unsupervised framework(UF)and supervised framework(SUF)approaches for generat-ing zonal application maps for CGR under VR conditions.During 2022-2023 agricultural seasons,an UF was employed to generate zonal maps based on locally collected field data on plant height of cotton,satellite imagery,soil texture,and phenology data.Subsequently,a SUF(based on historical data between 2020-2021 to 2022-2023 agricultural seasons)was developed to predict plant height using remote sensing and phenology data,aiming to replicate same zonal maps but without relying on direct field measurements of plant height.Both approaches were tested in three fields and on two different dates per field.Results The predictive model for plant height of SUF performed well,as indicated by the model metrics.However,when comparing zonal application maps for specific field-date combinations,the predicted plant height exhibited lower variability compared with field measurements.This led to variable compatibility between SUF maps,which utilized the model predictions,and the UF maps,which were based on the real field data.Fields characterized by much pronounced soil texture variability yielded the highest compatibility between the zonal application maps produced by both SUF and UF approaches.This was predominantly due to the greater consistency in estimating plant development patterns within these heterogeneous field environments.While VR application approach can facilitate product savings during the application operation,other key factors must be considered.These include the availability of specialized machinery required for this type of applications,as well as the inherent operational costs associated with applying a single CGR product which differs from the typical uniform rate applications that often integrate multi-ple inputs.Conclusion Predictive modeling shows promise for assisting in the creation of zonal application maps for VR of CGR applications.However,the degree of agreement with the actual variability in crop growth found in the field should be evaluated on a field-by-field basis.The SUF approach,which is based on plant heigh prediction,demonstrated potential for supporting the development of zonal application maps for VR of CGR applications.However,the degree to which this approach aligns itself with the actual variability in crop growth observed in the field may vary,necessi-tating field-by-field evaluation.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
The authors regret that there were errors in the affiliations and the funding declaration in the original published version.The affiliations a and b of the original manuscript are"School of Information Engineerin...The authors regret that there were errors in the affiliations and the funding declaration in the original published version.The affiliations a and b of the original manuscript are"School of Information Engineering,Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications,Nanchang University,Nanchang 330031,China",and"School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China",respectively.The order of the two affiliations are not correct.展开更多
The identifiability of users as they interact in the digital world is fundamentally linked to privacy and security issues.Identifiability can be divided into two:subjective identifiability,which is based on psychologi...The identifiability of users as they interact in the digital world is fundamentally linked to privacy and security issues.Identifiability can be divided into two:subjective identifiability,which is based on psychological perceptions(i.e.,mental space),and objective identifiability,which is based on social media data(i.e.,information space).This study constructs a prediction model for social media data identifiability of users based on a supervised machine learning technique.The findings,based on data from Weibo,a Chinese social media platform,indicate that the top seven features and values for predicting social media identifiability include blog pictures(0.21),blog location(0.14),birthdate(0.12),location(0.10),blog interaction(0.10),school(0.08),and interests and hobbies(0.07).The relationship between machine-predicted and self-reported identifiability was tested using data from 91 participants.Based on the degree of deviation between the two,users can be divided into four categories—normal,conservative,active,and atypical—which reflect their sensitivity to privacy concerns and preferences regarding information disclosure.This study provides insights into the development of privacy protection strategies based on social media data classification.展开更多
The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gaine...The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.展开更多
With the rapid urbanization and exponential population growth in China,two-wheeled vehicles have become a popular mode of transportation,particularly for short-distance travel.However,due to a lack of safety awareness...With the rapid urbanization and exponential population growth in China,two-wheeled vehicles have become a popular mode of transportation,particularly for short-distance travel.However,due to a lack of safety awareness,traffic violations by two-wheeled vehicle riders have become a widespread concern,contributing to urban traffic risks.Currently,significant human and material resources are being allocated to monitor and intercept non-compliant riders to ensure safe driving behavior.To enhance the safety,efficiency,and cost-effectiveness of traffic monitoring,automated detection systems based on image processing algorithms can be employed to identify traffic violations from eye-level video footage.In this study,we propose a robust detection algorithm specifically designed for two-wheeled vehicles,which serves as a fundamental step toward intelligent traffic monitoring.Our approach integrates a novel convolutional and attention mechanism to improve detection accuracy and efficiency.Additionally,we introduce a semi-supervised training strategy that leverages a large number of unlabeled images to enhance the model’s learning capability by extracting valuable background information.This method enables the model to generalize effectively to diverse urban environments and varying lighting conditions.We evaluate our proposed algorithm on a custom-built dataset,and experimental results demonstrate its superior performance,achieving an average precision(AP)of 95%and a recall(R)of 90.6%.Furthermore,the model maintains a computational efficiency of only 25.7 GFLOPs while achieving a high processing speed of 249 FPS,making it highly suitable for deployment on edge devices.Compared to existing detection methods,our approach significantly enhances the accuracy and robustness of two-wheeled vehicle identification while ensuring real-time performance.展开更多
Because methane is flammable and explosive,the detection process is time-consuming and dangerous,and it is difficult to obtain labeled data.In order to reduce the dependence on marker data when detecting methane conce...Because methane is flammable and explosive,the detection process is time-consuming and dangerous,and it is difficult to obtain labeled data.In order to reduce the dependence on marker data when detecting methane concentration using tunable diode laser absorption spectroscopy(TDLAS)technology,this paper designs a methane gas acquisition platform based on TDLAS and proposes a methane gas concentration detection model based on semi-supervised learning.Firstly,the methane gas is feature extracted,and then semi-supervised learning is introduced to select the optimal feature combination;subsequently,the traditional whale optimization algorithm is improved to optimize the parameters of the random forest to detect the methane gas concentration.The results show that the model is not only able to select the optimal feature combination under limited labeled data,but also has an accuracy of 94.25%,which is better than the traditional model,and is robust in terms of parameter optimization.展开更多
Objectives This study aimed to analyse the benefits of a gamified clinical supervision strategy during hospital-based training,particularly regarding the development of critical and reflective thinking among undergrad...Objectives This study aimed to analyse the benefits of a gamified clinical supervision strategy during hospital-based training,particularly regarding the development of critical and reflective thinking among undergraduate nursing students.Methods From April to July 2023,second-year nursing students who undertaking a nine-week clinical placement in a cardiology ward in northern Portugal were selected.Following a two-week diagnostic phase,students participated in a six-week gamified supervision programme comprising weekly 60-min sessions:infection-control decision-making;technical-procedural reasoning;guided emotional and ethical reflection;and clinical reasoning quiz on cardiology topics.Students completed weekly Structured Reflection Guide entries;supervisors recorded structured field notes after each session;and,after the intervention,students answered a post-intervention questionnaire and participated in focus groups.Qualitative data(reflections,field notes,open-ended questionnaire items,and focus-group transcripts)were analyzed using Bardin’s content analysis;quantitative questionnaire items were summarized descriptively.Results All seven students completed the six gamified sessions and submitted weekly reflection entries.Five students(71.4%)completed the questionnaire.Across data sources,students reported that gamified activities supported knowledge consolidation,teamwork,and clinical reasoning.Questionnaire data showed that all respondents(n=5,100%)strongly agreed that gamification enhanced their learning and should be maintained in clinical training.Reflections and focus groups revealed recurring themes related to emotional expression,sense of belonging,and difficulties using structured reflection tools,particularly in terms of comprehension and timing.Conclusion The gamified supervision strategy integrated into clinical training provided structured opportunities for practical engagement,collaborative work,and guided reflection.These findings suggest that gamification may support the development of reflective and critical-thinking processes in authentic clinical environments.展开更多
Objectives This study aimed to explore and clarify the concept of reflective supervision as a professional self-care strategy to create a positive Intensive Care Unit(ICU)practice environment.Methods Walker and Avant...Objectives This study aimed to explore and clarify the concept of reflective supervision as a professional self-care strategy to create a positive Intensive Care Unit(ICU)practice environment.Methods Walker and Avant’s eight-step concept analysis approach was utilized to identify and define the attributes,antecedents,and consequences of reflective supervision in the ICU.An extensive literature search was conducted across various databases,including Google Scholar,CINAHL,PubMed.Articles published from 2005 to 2025 were identified.We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)2020 statement to indicate the included articles and extract related data based on relevance.Results Forty articles were included in the analysis.The identified attributes included the supervisor-supervisee relationship,effective communication,teamwork,collaborations,reflection,competencies,feedback,continuous support,and autonomous choice.The identified antecedents included participation,supportive supervision,flexibility,open-door policy,training,and motivation.Consequences impacting the success of reflective supervision were identified as promotion of resiliency,autonomy,work-life balance,self-awareness,increased self-esteem,professional development,critical thinking,increased job satisfaction,and enhanced commitment.Conclusions Reflective supervision is a complex professional self-care strategy that enhances ICU practice,by promoting nurses’well-being,self-awareness,therapeutic skills,and professional development.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.
文摘Weakly Supervised Semantic Segmentation(WSSS),which relies only on image-level labels,has attracted significant attention for its cost-effectiveness and scalability.Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations.However,they often neglect the complex contextual dependencies among image patches,resulting in incomplete local representations and limited segmentation accuracy.To address these issues,we propose the Context Patch Fusion with Class Token Enhancement(CPF-CTE)framework,which exploits contextual relations among patches to enrich feature repre-sentations and improve segmentation.At its core,the Contextual-Fusion Bidirectional Long Short-Term Memory(CF-BiLSTM)module captures spatial dependencies between patches and enables bidirectional information flow,yield-ing a more comprehensive understanding of spatial correlations.This strengthens feature learning and segmentation robustness.Moreover,we introduce learnable class tokens that dynamically encode and refine class-specific semantics,enhancing discriminative capability.By effectively integrating spatial and semantic cues,CPF-CTE produces richer and more accurate representations of image content.Extensive experiments on PASCAL VOC 2012 and MS COCO 2014 validate that CPF-CTE consistently surpasses prior WSSS methods.
文摘Weakly supervised semantic segmentation(WSSS)is a tricky task,which only provides category information for segmentation prediction.Thus,the key stage of WSSS is to generate the pseudo labels.For convolutional neural network(CNN)based methods,in which class activation mapping(CAM)is proposed to obtain the pseudo labels,and only concentrates on the most discriminative parts.Recently,transformer-based methods utilize attention map from the multi-headed self-attention(MHSA)module to predict pseudo labels,which usually contain obvious background noise and incoherent object area.To solve the above problems,we use the Conformer as our backbone,which is a parallel network based on convolutional neural network(CNN)and Transformer.The two branches generate pseudo labels and refine them independently,and can effectively combine the advantages of CNN and Transformer.However,the parallel structure is not close enough in the information communication.Thus,parallel structure can result in poor details about pseudo labels,and the background noise still exists.To alleviate this problem,we propose enhancing convolution CAM(ECCAM)model,which have three improved modules based on enhancing convolution,including deeper stem(DStem),convolutional feed-forward network(CFFN)and feature coupling unit with convolution(FCUConv).The ECCAM could make Conformer have tighter interaction between CNN and Transformer branches.After experimental verification,the improved modules we propose can help the network perceive more local information from images,making the final segmentation results more refined.Compared with similar architecture,our modules greatly improve the semantic segmentation performance and achieve70.2%mean intersection over union(mIoU)on the PASCAL VOC 2012 dataset.
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In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.
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funded by the National Natural Science Foundation of China(81871854,72374014)the National Key R&D Program of China(2020YFC2008804)+1 种基金the Shanghai Jiao Tong University Young Talent Cultivation Program in Liberal Arts(2024QN041)the Shanghai Jiao Tong University School of Medicine:Nursing Development Program(SJTUHLXK2024).
文摘Background Evidence on the effects of different exercise interventions on cognitive function is insufficient.Aims To evaluate the feasibility and effects of remotely supervised aerobic exercise(AE)and resistance exercise(RE)interventions in older adults with mild cognitive impairment(MCI).Methods This study is a 6-month pilot three-arm randomised controlled trial.Eligible participants(n=108)were recruited and randomised to the AE group,RE group or control(CON)group with a 1:1:1 ratio.Interventions were delivered at home with remote supervision.We evaluated participants’global cognition,memory,executive function,attention,physical activity levels,physical performance and muscle strength of limbs at baseline,3 months(T1)and 6 months(T2)after randomisation.A linear mixed-effects model was adopted for data analyses after controlling for covariates.Tukey’s method was used for adjusting for multiple comparisons.Sensitivity analyses were performed after excluding individuals with low compliance rates.Results 15(13.89%)participants dropped out.The median compliance rates in the AE group and RE group were 67.31%and 93.27%,respectively.After adjusting for covariates,the scores of the Alzheimer’s Disease Assessment Scale-Cognitive subscale in the AE group decreased by 2.04(95%confidence interval(CI)−3.41 to−0.67,t=−2.94,p=0.004)and 1.53(95%CI−2.88 to−0.17,t=−2.22,p=0.028)points more than those in the CON group at T1 and T2,respectively.The effects of AE were still significant at T1(estimate=−1.70,95%CI−3.20 to−0.21,t=−2.69,p=0.021),but lost statistical significance at T2 after adjusting for multiple comparisons.As for executive function,the Stroop time interference in the RE group decreased by 11.76 s(95%CI−21.62 to−1.90,t=−2.81,p=0.015)more than that in the AE group at T2 after Tukey’s adjustment.No other significant effects on cognitive functions were found.Conclusions Both remotely supervised AE and RE programmes are feasible in older adults with MCI.AE has positive effects on global cognition,and RE improves executive function.
基金supported by the National Natural Science Foundation of China(Grants 62176097,61433007)Fundamental Research Funds for the Central Universities(Grant 2019kfyXKJC024)the 111 Project on Computational Intelligence and Intelligent Control(Grant B18024).
文摘Existing weakly supervised semantic segmentation(WSSS)methods based on image-level labels always rely on class activation maps(CAMs),which measure the relationships between features and classifiers.However,CAMs only focus on the most discriminative regions of images,resulting in their poor coverage performance.We attribute this to the deficiency in the recognition ability of a single classifier and the negative impacts caused by magnitudes during the CAMs normalisation process.To address the aforementioned issues,we propose to construct selective multiple classifiers(SMC).During the training process,we extract multiple prototypes for each class and store them in the corresponding memory bank.These prototypes are divided into foreground and background prototypes,with the former used to identify foreground objects and the latter aimed at preventing the false activation of background pixels.As for the inference stage,multiple prototypes are adaptively selected from the memory bank for each image as SMC.Subsequently,CAMs are generated by measuring the angle between SMC and features.We enhance the recognition ability of classifiers by adaptively constructing multiple classifiers for each image,while only relying on angle measurement to generate CAMs can alleviate the suppression phenomenon caused by magnitudes.Furthermore,SMC can be integrated into other WSSS approaches to help generate better CAMs.Extensive experiments conducted on standard WSSS benchmarks such as PASCAL VOC 2012 and MS COCO 2014 demonstrate the superiority of our proposed method.
文摘Background Zonal application maps are designed to represent field variability using key variables that can be translated into tailored management practices.For cotton,zonal maps for crop growth regulator(CGR)applications under variable-rate(VR)strategies are commonly based exclusively on vegetation indices(VIs)variability.However,VIs often saturate in dense crop vegetation areas,limiting their effectiveness in distinguishing variability in crop growth.This study aimed to compare unsupervised framework(UF)and supervised framework(SUF)approaches for generat-ing zonal application maps for CGR under VR conditions.During 2022-2023 agricultural seasons,an UF was employed to generate zonal maps based on locally collected field data on plant height of cotton,satellite imagery,soil texture,and phenology data.Subsequently,a SUF(based on historical data between 2020-2021 to 2022-2023 agricultural seasons)was developed to predict plant height using remote sensing and phenology data,aiming to replicate same zonal maps but without relying on direct field measurements of plant height.Both approaches were tested in three fields and on two different dates per field.Results The predictive model for plant height of SUF performed well,as indicated by the model metrics.However,when comparing zonal application maps for specific field-date combinations,the predicted plant height exhibited lower variability compared with field measurements.This led to variable compatibility between SUF maps,which utilized the model predictions,and the UF maps,which were based on the real field data.Fields characterized by much pronounced soil texture variability yielded the highest compatibility between the zonal application maps produced by both SUF and UF approaches.This was predominantly due to the greater consistency in estimating plant development patterns within these heterogeneous field environments.While VR application approach can facilitate product savings during the application operation,other key factors must be considered.These include the availability of specialized machinery required for this type of applications,as well as the inherent operational costs associated with applying a single CGR product which differs from the typical uniform rate applications that often integrate multi-ple inputs.Conclusion Predictive modeling shows promise for assisting in the creation of zonal application maps for VR of CGR applications.However,the degree of agreement with the actual variability in crop growth found in the field should be evaluated on a field-by-field basis.The SUF approach,which is based on plant heigh prediction,demonstrated potential for supporting the development of zonal application maps for VR of CGR applications.However,the degree to which this approach aligns itself with the actual variability in crop growth observed in the field may vary,necessi-tating field-by-field evaluation.
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.
文摘The authors regret that there were errors in the affiliations and the funding declaration in the original published version.The affiliations a and b of the original manuscript are"School of Information Engineering,Jiangxi Provincial Key Laboratory of Advanced Signal Processing and Intelligent Communications,Nanchang University,Nanchang 330031,China",and"School of Internet of Things Engineering,Jiangnan University,Wuxi 214122,China",respectively.The order of the two affiliations are not correct.
基金supported by the National Social Science Funds of China(Grant No.21BSH050)Major Project of National Social Science Funds of China(Grant No.20&ZD013).
文摘The identifiability of users as they interact in the digital world is fundamentally linked to privacy and security issues.Identifiability can be divided into two:subjective identifiability,which is based on psychological perceptions(i.e.,mental space),and objective identifiability,which is based on social media data(i.e.,information space).This study constructs a prediction model for social media data identifiability of users based on a supervised machine learning technique.The findings,based on data from Weibo,a Chinese social media platform,indicate that the top seven features and values for predicting social media identifiability include blog pictures(0.21),blog location(0.14),birthdate(0.12),location(0.10),blog interaction(0.10),school(0.08),and interests and hobbies(0.07).The relationship between machine-predicted and self-reported identifiability was tested using data from 91 participants.Based on the degree of deviation between the two,users can be divided into four categories—normal,conservative,active,and atypical—which reflect their sensitivity to privacy concerns and preferences regarding information disclosure.This study provides insights into the development of privacy protection strategies based on social media data classification.
基金funding from the following sources:National Natural Science Foundation of China(U1904119)Research Programs of Henan Science and Technology Department(232102210054)+3 种基金Chongqing Natural Science Foundation(CSTB2023NSCQ-MSX0070)Henan Province Key Research and Development Project(231111212000)Aviation Science Foundation(20230001055002)supported by Henan Center for Outstanding Overseas Scientists(GZS2022011).
文摘The primary challenge in weakly supervised semantic segmentation is effectively leveraging weak annotations while minimizing the performance gap compared to fully supervised methods.End-to-end model designs have gained significant attention for improving training efficiency.Most current algorithms rely on Convolutional Neural Networks(CNNs)for feature extraction.Although CNNs are proficient at capturing local features,they often struggle with global context,leading to incomplete and false Class Activation Mapping(CAM).To address these limitations,this work proposes a Contextual Prototype-Based End-to-End Weakly Supervised Semantic Segmentation(CPEWS)model,which improves feature extraction by utilizing the Vision Transformer(ViT).By incorporating its intermediate feature layers to preserve semantic information,this work introduces the Intermediate Supervised Module(ISM)to supervise the final layer’s output,reducing boundary ambiguity and mitigating issues related to incomplete activation.Additionally,the Contextual Prototype Module(CPM)generates class-specific prototypes,while the proposed Prototype Discrimination Loss and Superclass Suppression Loss guide the network’s training,(LPDL)(LSSL)effectively addressing false activation without the need for extra supervision.The CPEWS model proposed in this paper achieves state-of-the-art performance in end-to-end weakly supervised semantic segmentation without additional supervision.The validation set and test set Mean Intersection over Union(MIoU)of PASCAL VOC 2012 dataset achieved 69.8%and 72.6%,respectively.Compared with ToCo(pre trained weight ImageNet-1k),MIoU on the test set is 2.1%higher.In addition,MIoU reached 41.4%on the validation set of the MS COCO 2014 dataset.
基金supported by the Natural Science Foundation Project of Fujian Province,China(Grant No.2023J011439 and No.2019J01859).
文摘With the rapid urbanization and exponential population growth in China,two-wheeled vehicles have become a popular mode of transportation,particularly for short-distance travel.However,due to a lack of safety awareness,traffic violations by two-wheeled vehicle riders have become a widespread concern,contributing to urban traffic risks.Currently,significant human and material resources are being allocated to monitor and intercept non-compliant riders to ensure safe driving behavior.To enhance the safety,efficiency,and cost-effectiveness of traffic monitoring,automated detection systems based on image processing algorithms can be employed to identify traffic violations from eye-level video footage.In this study,we propose a robust detection algorithm specifically designed for two-wheeled vehicles,which serves as a fundamental step toward intelligent traffic monitoring.Our approach integrates a novel convolutional and attention mechanism to improve detection accuracy and efficiency.Additionally,we introduce a semi-supervised training strategy that leverages a large number of unlabeled images to enhance the model’s learning capability by extracting valuable background information.This method enables the model to generalize effectively to diverse urban environments and varying lighting conditions.We evaluate our proposed algorithm on a custom-built dataset,and experimental results demonstrate its superior performance,achieving an average precision(AP)of 95%and a recall(R)of 90.6%.Furthermore,the model maintains a computational efficiency of only 25.7 GFLOPs while achieving a high processing speed of 249 FPS,making it highly suitable for deployment on edge devices.Compared to existing detection methods,our approach significantly enhances the accuracy and robustness of two-wheeled vehicle identification while ensuring real-time performance.
基金supported by the Ministry of Education Chunhui Program of China(No.HZKY20220304).
文摘Because methane is flammable and explosive,the detection process is time-consuming and dangerous,and it is difficult to obtain labeled data.In order to reduce the dependence on marker data when detecting methane concentration using tunable diode laser absorption spectroscopy(TDLAS)technology,this paper designs a methane gas acquisition platform based on TDLAS and proposes a methane gas concentration detection model based on semi-supervised learning.Firstly,the methane gas is feature extracted,and then semi-supervised learning is introduced to select the optimal feature combination;subsequently,the traditional whale optimization algorithm is improved to optimize the parameters of the random forest to detect the methane gas concentration.The results show that the model is not only able to select the optimal feature combination under limited labeled data,but also has an accuracy of 94.25%,which is better than the traditional model,and is robust in terms of parameter optimization.
文摘Objectives This study aimed to analyse the benefits of a gamified clinical supervision strategy during hospital-based training,particularly regarding the development of critical and reflective thinking among undergraduate nursing students.Methods From April to July 2023,second-year nursing students who undertaking a nine-week clinical placement in a cardiology ward in northern Portugal were selected.Following a two-week diagnostic phase,students participated in a six-week gamified supervision programme comprising weekly 60-min sessions:infection-control decision-making;technical-procedural reasoning;guided emotional and ethical reflection;and clinical reasoning quiz on cardiology topics.Students completed weekly Structured Reflection Guide entries;supervisors recorded structured field notes after each session;and,after the intervention,students answered a post-intervention questionnaire and participated in focus groups.Qualitative data(reflections,field notes,open-ended questionnaire items,and focus-group transcripts)were analyzed using Bardin’s content analysis;quantitative questionnaire items were summarized descriptively.Results All seven students completed the six gamified sessions and submitted weekly reflection entries.Five students(71.4%)completed the questionnaire.Across data sources,students reported that gamified activities supported knowledge consolidation,teamwork,and clinical reasoning.Questionnaire data showed that all respondents(n=5,100%)strongly agreed that gamification enhanced their learning and should be maintained in clinical training.Reflections and focus groups revealed recurring themes related to emotional expression,sense of belonging,and difficulties using structured reflection tools,particularly in terms of comprehension and timing.Conclusion The gamified supervision strategy integrated into clinical training provided structured opportunities for practical engagement,collaborative work,and guided reflection.These findings suggest that gamification may support the development of reflective and critical-thinking processes in authentic clinical environments.
文摘Objectives This study aimed to explore and clarify the concept of reflective supervision as a professional self-care strategy to create a positive Intensive Care Unit(ICU)practice environment.Methods Walker and Avant’s eight-step concept analysis approach was utilized to identify and define the attributes,antecedents,and consequences of reflective supervision in the ICU.An extensive literature search was conducted across various databases,including Google Scholar,CINAHL,PubMed.Articles published from 2005 to 2025 were identified.We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses(PRISMA)2020 statement to indicate the included articles and extract related data based on relevance.Results Forty articles were included in the analysis.The identified attributes included the supervisor-supervisee relationship,effective communication,teamwork,collaborations,reflection,competencies,feedback,continuous support,and autonomous choice.The identified antecedents included participation,supportive supervision,flexibility,open-door policy,training,and motivation.Consequences impacting the success of reflective supervision were identified as promotion of resiliency,autonomy,work-life balance,self-awareness,increased self-esteem,professional development,critical thinking,increased job satisfaction,and enhanced commitment.Conclusions Reflective supervision is a complex professional self-care strategy that enhances ICU practice,by promoting nurses’well-being,self-awareness,therapeutic skills,and professional development.
