The incidence of benign airway stenosis(BAS)is on the rise,and current treatment options are associated with a significant risk of restenosis.Therefore,there is an urgent need to explore new and effective prevention a...The incidence of benign airway stenosis(BAS)is on the rise,and current treatment options are associated with a significant risk of restenosis.Therefore,there is an urgent need to explore new and effective prevention and treatment methods.Animal models serve as essential tools for investigating disease mechanisms and assessing novel therapeutic strategies,and the scientific rigor of their construction and validation significantly impacts the reliability of research findings.This paper systematically reviews the research progress and evaluation systems of BAS animal models over the past decade,aiming to provide a robust foundation for the optimized construction of BAS models,intervention studies,and clinical translation.This effort is intended to facilitate the innovation and advancement in BAS prevention and treatment strategies.展开更多
Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based...Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.展开更多
Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may r...Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.展开更多
Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lack...Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lacks formal task definitions and corresponding benchmarks.To bridge this gap,we define the Automated Online Public Opinion Report Generation(OPOR-Gen)task and construct OPOR-Bench,an event-centric dataset with 463 crisis events across 108 countries(comprising 8.8 K news articles and 185 K tweets).To evaluate report quality,we propose OPOR-Eval,a novel agent-based framework that simulates human expert evaluation.Validation experiments show OPOR-Eval achieves a high Spearman’s correlation(ρ=0.70)with human judgments,though challenges in temporal reasoning persist.This work establishes an initial foundation for advancing automated public opinion reporting research.展开更多
LargeLanguageModels(LLMs)are increasingly appliedinthe fieldof code translation.However,existing evaluation methodologies suffer from two major limitations:(1)the high overlap between test data and pretraining corpora...LargeLanguageModels(LLMs)are increasingly appliedinthe fieldof code translation.However,existing evaluation methodologies suffer from two major limitations:(1)the high overlap between test data and pretraining corpora,which introduces significant bias in performance evaluation;and(2)mainstream metrics focus primarily on surface-level accuracy,failing to uncover the underlying factors that constrain model capabilities.To address these issues,this paper presents TCode(Translation-Oriented Code Evaluation benchmark)—a complexity-controllable,contamination-free benchmark dataset for code translation—alongside a dedicated static feature sensitivity evaluation framework.The dataset is carefully designed to control complexity along multiple dimensions—including syntactic nesting and expression intricacy—enabling both broad coverage and fine-grained differentiation of sample difficulty.This design supports precise evaluation of model capabilities across a wide spectrum of translation challenges.The proposed evaluation framework introduces a correlation-driven analysis mechanism based on static program features,enabling predictive modeling of translation success from two perspectives:Code Form Complexity(e.g.,code length and character density)and Semantic Modeling Complexity(e.g.,syntactic depth,control-flow nesting,and type system complexity).Empirical evaluations across representative LLMs—including Qwen2.5-72B and Llama3.3-70B—demonstrate that even state-of-the-art models achieve over 80% compilation success on simple samples,but their accuracy drops sharply below 40% on complex cases.Further correlation analysis indicates that Semantic Modeling Complexity alone is correlated with up to 60% of the variance in translation success,with static program features exhibiting nonlinear threshold effects that highlight clear capability boundaries.This study departs fromthe traditional accuracy-centric evaluation paradigm and,for the first time,systematically characterizes the capabilities of large languagemodels in translation tasks through the lens of programstatic features.The findings provide actionable insights for model refinement and training strategy development.展开更多
Although previous studies have demonstrated that transcranial focused ultrasound stimulation protects the ischemic brain,clear criteria for the stimulation time window and intensity are lacking.Electrical impedance to...Although previous studies have demonstrated that transcranial focused ultrasound stimulation protects the ischemic brain,clear criteria for the stimulation time window and intensity are lacking.Electrical impedance tomography enables real-time monitoring of changes in cerebral blood perfusion within the ischemic brain,but investigating the feasibility of using this method to assess post-stroke rehabilitation in vivo remains critical.In this study,ischemic stroke was induced in rats through middle cerebral artery occlusion surgery.Transcranial focused ultrasound stimulation was used to treat the rat model of ischemia,and electrical impedance tomography was used to measure impedance during both the acute stage of ischemia and the rehabilitation stage following the stimulation.Electrical impedance tomography results indicated that cerebral impedance increased after the onset of ischemia and decreased following transcranial focused ultrasound stimulation.Furthermore,the stimulation promoted motor function recovery,reduced cerebral infarction volume in the rat model of ischemic stroke,and induced the expression of brain-derived neurotrophic factor in the ischemic brain.Our results also revealed a significant correlation between the impedance of the ischemic brain post-intervention and improvements in behavioral scores and infarct volume.This study shows that daily administration of transcranial focused ultrasound stimulation for 20 minutes to the ischemic hemisphere 24 hours after cerebral ischemia enhanced motor recovery in a rat model of ischemia.Additionally,our findings indicate that electrical impedance tomography can serve as a valuable tool for quantitatively evaluating rehabilitation after ischemic stroke in vivo.These findings suggest the feasibility of using impedance data collected via electrical impedance tomography to clinically assess the effects of rehabilitatory interventions for patients with ischemic stroke.展开更多
We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpr...We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpreting these parameters is crucial for effectively exploring and developing oil and gas.However,with the increasing complexity of geological conditions in this industry,there is a growing demand for improved accuracy in reservoir parameter prediction,leading to higher costs associated with manual interpretation.The conventional logging interpretation methods rely on empirical relationships between logging data and reservoir parameters,which suffer from low interpretation efficiency,intense subjectivity,and suitability for ideal conditions.The application of artificial intelligence in the interpretation of logging data provides a new solution to the problems existing in traditional methods.It is expected to improve the accuracy and efficiency of the interpretation.If large and high-quality datasets exist,data-driven models can reveal relationships of arbitrary complexity.Nevertheless,constructing sufficiently large logging datasets with reliable labels remains challenging,making it difficult to apply data-driven models effectively in logging data interpretation.Furthermore,data-driven models often act as“black boxes”without explaining their predictions or ensuring compliance with primary physical constraints.This paper proposes a machine learning method with strong physical constraints by integrating mechanism and data-driven models.Prior knowledge of logging data interpretation is embedded into machine learning regarding network structure,loss function,and optimization algorithm.We employ the Physically Informed Auto-Encoder(PIAE)to predict porosity and water saturation,which can be trained without labeled reservoir parameters using self-supervised learning techniques.This approach effectively achieves automated interpretation and facilitates generalization across diverse datasets.展开更多
The emergence of Medical Large Language Models has significantly transformed healthcare.Medical Large Language Models(Med-LLMs)serve as transformative tools that enhance clinical practice through applications in decis...The emergence of Medical Large Language Models has significantly transformed healthcare.Medical Large Language Models(Med-LLMs)serve as transformative tools that enhance clinical practice through applications in decision support,documentation,and diagnostics.This evaluation examines the performance of leading Med-LLMs,including GPT-4Med,Med-PaLM,MEDITRON,PubMedGPT,and MedAlpaca,across diverse medical datasets.It provides graphical comparisons of their effectiveness in distinct healthcare domains.The study introduces a domain-specific categorization system that aligns these models with optimal applications in clinical decision-making,documentation,drug discovery,research,patient interaction,and public health.The paper addresses deployment challenges of Medical-LLMs,emphasizing trustworthiness and explainability as essential requirements for healthcare AI.It presents current evaluation techniques that improve model transparency in high-stakes medical contexts and analyzes regulatory frameworks using benchmarking datasets such asMedQA,MedMCQA,PubMedQA,and MIMIC.By identifying ongoing challenges in biasmitigation,reliability,and ethical compliance,thiswork serves as a resource for selecting appropriate Med-LLMs and outlines future directions in the field.This analysis offers a roadmap for developing Med-LLMs that balance technological innovation with the trust and transparency required for clinical integration,a perspective often overlooked in existing literature.展开更多
Cobalt phosphide has been successfully used as a catalyst in the production of ammonia from nitric acid.Substituting appropriate atoms is expected to further improve its catalytic performance.Owing to the diversity of...Cobalt phosphide has been successfully used as a catalyst in the production of ammonia from nitric acid.Substituting appropriate atoms is expected to further improve its catalytic performance.Owing to the diversity of substituting elements,substitution sites,adsorption sites,and adsorption configurations,extensive time-consuming simulation calculations are required for the high-throughput screening method.Additionally,multi-objective attributes should be considered simultaneously in catalytic design.To tackle this challenge,this paper suggests a multi-objective cobalt phosphide catalytic material design method based on surrogate models.And the effectiveness of the proposed method was validated through comparative experiments.The proposed method led to the discovery of fifteen promising cobalt phosphide catalyst configurations.This study provides a new avenue for expediting the design of catalyst,with the potential for application in other systems.展开更多
An acute skin injury model using continuous tape tearing was established,and studies the application of this model in the evaluation of soothing effects through instrument evaluation.30 healthy adult subjects were sel...An acute skin injury model using continuous tape tearing was established,and studies the application of this model in the evaluation of soothing effects through instrument evaluation.30 healthy adult subjects were selected as the research subjects,and an acute skin model was established on the forearm flexion side of the subjects.The skin color a^(*)value and transdermal water loss rate(TEWL)value of the blank and experimental groups were tested using instruments.The results showed that at 15 and 30 minutes after using the sample,the growth values of a^(*)value and TEWL value in the experimental group were significantly lower than those in the blank group(P<0.05),the acute skin lesion model can effectively evaluate the soothing effect of cosmetics.展开更多
In the context of advancing towards dual carbon goals,numerous factories are actively engaging in energy efficiency upgrades and transformations.To accurately pinpoint energy efficiency bottlenecks within factories an...In the context of advancing towards dual carbon goals,numerous factories are actively engaging in energy efficiency upgrades and transformations.To accurately pinpoint energy efficiency bottlenecks within factories and prioritize renovation sequences,it is crucial to conduct comprehensive evaluations of the energy performance across various workshops.Therefore,this paper proposes an evaluation model for workshop energy efficiency based on the drive-state-response(DSR)framework combined with the fuzzy BORDA method.Firstly,an in-depth analysis of the relationships between different energy efficiency indicators was conducted.Based on the DSR model,evaluation criteria were selected from three dimensions-drive factors,state characteristics,and response measures-to establish a robust energy efficiency indicator system.Secondly,three distinct assessment techniques were selected:Grey Relational Analysis(GRA),Entropy Weight Method(EWM),and Technique for Order Preference by Similarity to Ideal Solution(TOPSIS)forming a diversified set of evaluation methods.Subsequently,by introducing the fuzzy BORDA method,a comprehensive energy efficiency evaluation model was developed,aimed at quantitatively ranking the energy performance status of each workshop.Using a real-world factory as a case study,applying our proposed evaluationmodel yielded detailed scores and rankings for each workshop.Furthermore,post hoc testing was performed using the Spearman correlation coefficient,revealing a statistic value of 10.209,which validates the effectiveness and reliability of the proposed evaluation model.This model not only assists in identifying underperforming workshops within the factory but also provides solid data support and a decision-making basis for future energy efficiency optimization strategies.展开更多
Hydrocracking is one of the most important petroleum refining processes that converts heavy oils into gases,naphtha,diesel,and other products through cracking reactions.Multi-objective optimization algorithms can help...Hydrocracking is one of the most important petroleum refining processes that converts heavy oils into gases,naphtha,diesel,and other products through cracking reactions.Multi-objective optimization algorithms can help refining enterprises determine the optimal operating parameters to maximize product quality while ensuring product yield,or to increase product yield while reducing energy consumption.This paper presents a multi-objective optimization scheme for hydrocracking based on an improved SPEA2-PE algorithm,which combines path evolution operator and adaptive step strategy to accelerate the convergence speed and improve the computational accuracy of the algorithm.The reactor model used in this article is simulated based on a twenty-five lumped kinetic model.Through model and test function verification,the proposed optimization scheme exhibits significant advantages in the multiobjective optimization process of hydrocracking.展开更多
This study proposes a multi-objective optimization framework for electric winches in fiber-reinforced plastic(FRP)fishing vessels to address critical limitations of conventional designs,including excessive weight,mate...This study proposes a multi-objective optimization framework for electric winches in fiber-reinforced plastic(FRP)fishing vessels to address critical limitations of conventional designs,including excessive weight,material inefficiency,and performance redundancy.By integrating surrogate modeling techniques with a multi-objective genetic algorithm(MOGA),we have developed a systematic approach that encompasses parametric modeling,finite element analysis under extreme operational conditions,and multi-fidelity performance evaluation.Through a 10-t electric winch case study,the methodology’s effectiveness is demonstrated via parametric characterization of structural integrity,stiffness behavior,and mass distribution.The comparative analysis identified optimal surrogate models for predicting key performance metrics,which enabled the construction of a robust multi-objective optimization model.The MOGA-derived Pareto solutions produced a design configuration achieving 7.86%mass reduction,2.01%safety factor improvement,and 23.97%deformation mitigation.Verification analysis confirmed the optimization scheme’s reliability in balancing conflicting design requirements.This research establishes a generalized framework for marine deck machinery modernization,particularly addressing the structural compatibility challenges in FRP vessel retrofitting.The proposed methodology demonstrates significant potential for facilitating sustainable upgrades of fishing vessel equipment through systematic performance optimization.展开更多
Objectives:Valid estimation of energy expenditure remains a challenge,particularly when using ankle-and thighworn devices.The Move 4 is a research-grade accelerometer previously tested for predicting metabolic equival...Objectives:Valid estimation of energy expenditure remains a challenge,particularly when using ankle-and thighworn devices.The Move 4 is a research-grade accelerometer previously tested for predicting metabolic equivalents(METs)when worn at the waist or wrist.This study aimed to calibrate and evaluate regression models to estimate METs from Move 4 data when worn at the ankle and thigh.Methods:Participants completed walking and jogging tasks under laboratory conditions while wearing Move 4 sensors and with indirect calorimetry as a reference measure.Models were calibrated using study 1(n=160)and evaluated in an independent dataset(study 2;n=15).Performance was assessed using mean absolute error(MAE),root mean square error(RMSE),and Bland-Altman analyses.Results:The MET models demonstrated strong agreement across both locations and datasets.For the thigh position,the MAE ranged from 0.60 METs(walking)to 1.38 METs(jogging),with RMSE of 0.82 and 1.70 in the evaluation data.Calibration metrics were comparable(jogging:MAE=1.24,RMSE=1.63).The ankle models showed similar accuracy,with MAEs of 0.66(walking)and 1.39(jogging),and RMSEs of 0.85 and 1.67,respectively.Systematic bias remained low(mean differences between−0.34 and−0.01 METs).Conclusions:This study provides the first calibration and evaluation for estimating METs from ankle-and thigh-worn Move 4 accelerometers.The model indicated accurate,highresolution MET estimation for walking and jogging.Future work should expand independent performance evaluations,including diverse activities such as static activities,and diverse samples under free-living conditions.展开更多
With the rapid development of generative artificial intelligence technologies,represented by large language models,university-level computer science education is undergoing a critical transition-from knowledge-based i...With the rapid development of generative artificial intelligence technologies,represented by large language models,university-level computer science education is undergoing a critical transition-from knowledge-based instruction to competency-oriented teaching.A postgraduate student competency evaluation model can serve as a framework to organize and guide both teaching and research activities at the postgraduate level.A number of relevant research efforts have already been conducted in this area.Graduate education plays a vital role not only as a continuation and enhancement of undergraduate education but also as essential preparation for future research endeavors.An analysis of the acceptance of competency evaluation models refers to the assessment of how various stakeholders perceive the importance of different components within the model.Investigating the degree of acceptance among diverse groups-such as current undergraduate students,current postgraduate students,graduates with less than three years of work experience,and those with more than three years of work experience-can offer valuable insights for improving and optimizing postgraduate education and training practices.展开更多
With the widespread application of Internet of Things(IoT)technology,the processing of massive realtime streaming data poses significant challenges to the computational and data-processing capabilities of systems.Alth...With the widespread application of Internet of Things(IoT)technology,the processing of massive realtime streaming data poses significant challenges to the computational and data-processing capabilities of systems.Although distributed streaming data processing frameworks such asApache Flink andApache Spark Streaming provide solutions,meeting stringent response time requirements while ensuring high throughput and resource utilization remains an urgent problem.To address this,the study proposes a formal modeling approach based on Performance Evaluation Process Algebra(PEPA),which abstracts the core components and interactions of cloud-based distributed streaming data processing systems.Additionally,a generic service flow generation algorithmis introduced,enabling the automatic extraction of service flows fromthe PEPAmodel and the computation of key performance metrics,including response time,throughput,and resource utilization.The novelty of this work lies in the integration of PEPA-based formal modeling with the service flow generation algorithm,bridging the gap between formal modeling and practical performance evaluation for IoT systems.Simulation experiments demonstrate that optimizing the execution efficiency of components can significantly improve system performance.For instance,increasing the task execution rate from 10 to 100 improves system performance by 9.53%,while further increasing it to 200 results in a 21.58%improvement.However,diminishing returns are observed when the execution rate reaches 500,with only a 0.42%gain.Similarly,increasing the number of TaskManagers from 10 to 20 improves response time by 18.49%,but the improvement slows to 6.06% when increasing from 20 to 50,highlighting the importance of co-optimizing component efficiency and resource management to achieve substantial performance gains.This study provides a systematic framework for analyzing and optimizing the performance of IoT systems for large-scale real-time streaming data processing.The proposed approach not only identifies performance bottlenecks but also offers insights into improving system efficiency under different configurations and workloads.展开更多
The average stiffness performance indices throughout the workspace are commonly used as global stiffness performance indices to evaluate the overall stiffness performance of parallel mechanisms,which involves an analy...The average stiffness performance indices throughout the workspace are commonly used as global stiffness performance indices to evaluate the overall stiffness performance of parallel mechanisms,which involves an analysis of the stiffness performance of numerous discrete points in the workspace.This necessitates time-consuming and inefficient calculation,which is particularly pronounced in the optimization design stage of the mechanism,where the variations in the global stiffness performance indices versus various dimensional and structural parameters need to be analyzed.This paper presents a semi-analytical approach for stiffness modeling of the novel(R(RPS&RP))&2-UPS parallel mechanism(referred to as the Trifree mechanism)and proposes“local”stiffness performance indices as alternatives to global indices.Drawing on the screw theory,the Cartesian stiffness matrix of the Trifree mechanism is formulated explicitly by considering the compliances of all elastic elements and the over-constraint characteristics inherent in the mechanism.Based on the spherical motion pattern of the Trifree mechanism,four special reference configurations are extracted within the workspace.This yields“local”stiffness performance indices capable of accurately evaluating the overall stiffness performance of the mechanism and effectively improving the computational efficiency.The variations in global and“local”stiffness performance indices versus key design parameters are investigated.Furthermore,the proposed indices are applied to the Tricept and Trimule mechanisms.The results demonstrate that the proposed indices exhibit excellent computational accuracy and efficiency in evaluating the overall stiffness performance of these spherical parallel mechanisms.Moreover,the stiffness performance of the novel parallel mechanism investigated in this study closely resembles that of the well-known Tricept and Trimule mechanisms.This research proposes a semi-analytic stiffness model of the Trifree mechanism and“local”stiffness performance indices to evaluate the overall stiffness performance,thereby substantially improving the computational efficiency without sacrificing accuracy.展开更多
The rapid and increasing growth in the volume and number of cyber threats from malware is not a real danger;the real threat lies in the obfuscation of these cyberattacks,as they constantly change their behavior,making...The rapid and increasing growth in the volume and number of cyber threats from malware is not a real danger;the real threat lies in the obfuscation of these cyberattacks,as they constantly change their behavior,making detection more difficult.Numerous researchers and developers have devoted considerable attention to this topic;however,the research field has not yet been fully saturated with high-quality studies that address these problems.For this reason,this paper presents a novel multi-objective Markov-enhanced adaptive whale optimization(MOMEAWO)cybersecurity model to improve the classification of binary and multi-class malware threats through the proposed MOMEAWO approach.The proposed MOMEAWO cybersecurity model aims to provide an innovative solution for analyzing,detecting,and classifying the behavior of obfuscated malware within their respective families.The proposed model includes three classification types:Binary classification and multi-class classification(e.g.,four families and 16 malware families).To evaluate the performance of this model,we used a recently published dataset called the Canadian Institute for Cybersecurity Malware Memory Analysis(CIC-MalMem-2022)that contains balanced data.The results show near-perfect accuracy in binary classification and high accuracy in multi-class classification compared with related work using the same dataset.展开更多
The rapid development of evolutionary deep learning has led to the emergence of various Neural Architecture Search(NAS)algorithms designed to optimize neural network structures.However,these algorithms often face sign...The rapid development of evolutionary deep learning has led to the emergence of various Neural Architecture Search(NAS)algorithms designed to optimize neural network structures.However,these algorithms often face significant computational costs due to the time-consuming process of training neural networks and evaluating their performance.Traditional NAS approaches,which rely on exhaustive evaluations and large training datasets,are inefficient for solving complex image classification tasks within limited time frames.To address these challenges,this paper proposes a novel NAS algorithm that integrates a hierarchical evaluation strategy based on Surrogate models,specifically using supernet to pre-trainweights and randomforests as performance predictors.This hierarchical framework combines rapid Surrogate model evaluations with traditional,precise evaluations to balance the trade-off between performance accuracy and computational efficiency.The algorithm significantly reduces the time required for model evaluation by predicting the fitness of candidate architectures using a random forest Surrogate model,thus alleviating the need for full training cycles for each architecture.The proposed method also incorporates evolutionary operations such as mutation and crossover to refine the search process and improve the accuracy of the resulting architectures.Experimental evaluations on the CIFAR-10 and CIFAR-100 datasets demonstrate that the proposed hierarchical evaluation strategy reduces the search time and costs compared to traditional methods,while achieving comparable or even superior model performance.The results suggest that this approach can efficiently handle resourceconstrained tasks,providing a promising solution for accelerating the NAS process without compromising the quality of the generated architectures.展开更多
Offline policy evaluation,evaluating and selecting complex policies for decision-making by only using offline datasets is important in reinforcement learning.At present,the model-based offline policy evaluation(MBOPE)...Offline policy evaluation,evaluating and selecting complex policies for decision-making by only using offline datasets is important in reinforcement learning.At present,the model-based offline policy evaluation(MBOPE)is widely welcomed because of its easy to implement and good performance.MBOPE directly approximates the unknown value of a given policy using the Monte Carlo method given the estimated transition and reward functions of the environment.Usually,multiple models are trained,and then one of them is selected to be used.However,a challenge remains in selecting an appropriate model from those trained for further use.The authors first analyse the upper bound of the difference between the approximated value and the unknown true value.Theoretical results show that this difference is related to the trajectories generated by the given policy on the learnt model and the prediction error of the transition and reward functions at these generated data points.Based on the theoretical results,a new criterion is proposed to tell which trained model is better suited for evaluating the given policy.At last,the effectiveness of the proposed criterion is demonstrated on both benchmark and synthetic offline datasets.展开更多
基金National Natural Science Foundation of China,Grant/Award Number:82000102 and 82270112。
文摘The incidence of benign airway stenosis(BAS)is on the rise,and current treatment options are associated with a significant risk of restenosis.Therefore,there is an urgent need to explore new and effective prevention and treatment methods.Animal models serve as essential tools for investigating disease mechanisms and assessing novel therapeutic strategies,and the scientific rigor of their construction and validation significantly impacts the reliability of research findings.This paper systematically reviews the research progress and evaluation systems of BAS animal models over the past decade,aiming to provide a robust foundation for the optimized construction of BAS models,intervention studies,and clinical translation.This effort is intended to facilitate the innovation and advancement in BAS prevention and treatment strategies.
基金the Hebei Province Science and Technology Plan Project(19221909D)rincess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R308),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Autonomous connected vehicles(ACV)involve advanced control strategies to effectively balance safety,efficiency,energy consumption,and passenger comfort.This research introduces a deep reinforcement learning(DRL)-based car-following(CF)framework employing the Deep Deterministic Policy Gradient(DDPG)algorithm,which integrates a multi-objective reward function that balances the four goals while maintaining safe policy learning.Utilizing real-world driving data from the highD dataset,the proposed model learns adaptive speed control policies suitable for dynamic traffic scenarios.The performance of the DRL-based model is evaluated against a traditional model predictive control-adaptive cruise control(MPC-ACC)controller.Results show that theDRLmodel significantly enhances safety,achieving zero collisions and a higher average time-to-collision(TTC)of 8.45 s,compared to 5.67 s for MPC and 6.12 s for human drivers.For efficiency,the model demonstrates 89.2% headway compliance and maintains speed tracking errors below 1.2 m/s in 90% of cases.In terms of energy optimization,the proposed approach reduces fuel consumption by 5.4% relative to MPC.Additionally,it enhances passenger comfort by lowering jerk values by 65%,achieving 0.12 m/s3 vs.0.34 m/s3 for human drivers.A multi-objective reward function is integrated to ensure stable policy convergence while simultaneously balancing the four key performance metrics.Moreover,the findings underscore the potential of DRL in advancing autonomous vehicle control,offering a robust and sustainable solution for safer,more efficient,and more comfortable transportation systems.
文摘Community detection is one of the most fundamental applications in understanding the structure of complicated networks.Furthermore,it is an important approach to identifying closely linked clusters of nodes that may represent underlying patterns and relationships.Networking structures are highly sensitive in social networks,requiring advanced techniques to accurately identify the structure of these communities.Most conventional algorithms for detecting communities perform inadequately with complicated networks.In addition,they miss out on accurately identifying clusters.Since single-objective optimization cannot always generate accurate and comprehensive results,as multi-objective optimization can.Therefore,we utilized two objective functions that enable strong connections between communities and weak connections between them.In this study,we utilized the intra function,which has proven effective in state-of-the-art research studies.We proposed a new inter-function that has demonstrated its effectiveness by making the objective of detecting external connections between communities is to make them more distinct and sparse.Furthermore,we proposed a Multi-Objective community strength enhancement algorithm(MOCSE).The proposed algorithm is based on the framework of the Multi-Objective Evolutionary Algorithm with Decomposition(MOEA/D),integrated with a new heuristic mutation strategy,community strength enhancement(CSE).The results demonstrate that the model is effective in accurately identifying community structures while also being computationally efficient.The performance measures used to evaluate the MOEA/D algorithm in our work are normalized mutual information(NMI)and modularity(Q).It was tested using five state-of-the-art algorithms on social networks,comprising real datasets(Zachary,Dolphin,Football,Krebs,SFI,Jazz,and Netscience),as well as twenty synthetic datasets.These results provide the robustness and practical value of the proposed algorithm in multi-objective community identification.
基金supported by the Fundamental Research Funds for the Central Universities(No.CUC25SG013)the Foundation of Key Laboratory of Education Informatization for Nationalities(Yunnan Normal University),Ministry of Education(No.EIN2024C006).
文摘Online Public Opinion Reports consolidate news and social media for timely crisis management by governments and enterprises.While large language models(LLMs)enable automated report generation,this specific domain lacks formal task definitions and corresponding benchmarks.To bridge this gap,we define the Automated Online Public Opinion Report Generation(OPOR-Gen)task and construct OPOR-Bench,an event-centric dataset with 463 crisis events across 108 countries(comprising 8.8 K news articles and 185 K tweets).To evaluate report quality,we propose OPOR-Eval,a novel agent-based framework that simulates human expert evaluation.Validation experiments show OPOR-Eval achieves a high Spearman’s correlation(ρ=0.70)with human judgments,though challenges in temporal reasoning persist.This work establishes an initial foundation for advancing automated public opinion reporting research.
文摘LargeLanguageModels(LLMs)are increasingly appliedinthe fieldof code translation.However,existing evaluation methodologies suffer from two major limitations:(1)the high overlap between test data and pretraining corpora,which introduces significant bias in performance evaluation;and(2)mainstream metrics focus primarily on surface-level accuracy,failing to uncover the underlying factors that constrain model capabilities.To address these issues,this paper presents TCode(Translation-Oriented Code Evaluation benchmark)—a complexity-controllable,contamination-free benchmark dataset for code translation—alongside a dedicated static feature sensitivity evaluation framework.The dataset is carefully designed to control complexity along multiple dimensions—including syntactic nesting and expression intricacy—enabling both broad coverage and fine-grained differentiation of sample difficulty.This design supports precise evaluation of model capabilities across a wide spectrum of translation challenges.The proposed evaluation framework introduces a correlation-driven analysis mechanism based on static program features,enabling predictive modeling of translation success from two perspectives:Code Form Complexity(e.g.,code length and character density)and Semantic Modeling Complexity(e.g.,syntactic depth,control-flow nesting,and type system complexity).Empirical evaluations across representative LLMs—including Qwen2.5-72B and Llama3.3-70B—demonstrate that even state-of-the-art models achieve over 80% compilation success on simple samples,but their accuracy drops sharply below 40% on complex cases.Further correlation analysis indicates that Semantic Modeling Complexity alone is correlated with up to 60% of the variance in translation success,with static program features exhibiting nonlinear threshold effects that highlight clear capability boundaries.This study departs fromthe traditional accuracy-centric evaluation paradigm and,for the first time,systematically characterizes the capabilities of large languagemodels in translation tasks through the lens of programstatic features.The findings provide actionable insights for model refinement and training strategy development.
基金supported by the Fundamental Research Funds for the Central Universities,Nos.G2021KY05107,G2021KY05101the National Natural Science Foundation of China,Nos.32071316,32211530049+1 种基金the Natural Science Foundation of Shaanxi Province,No.2022-JM482the Education and Teaching Reform Funds for the Central Universities,No.23GZ230102(all to LL and HH).
文摘Although previous studies have demonstrated that transcranial focused ultrasound stimulation protects the ischemic brain,clear criteria for the stimulation time window and intensity are lacking.Electrical impedance tomography enables real-time monitoring of changes in cerebral blood perfusion within the ischemic brain,but investigating the feasibility of using this method to assess post-stroke rehabilitation in vivo remains critical.In this study,ischemic stroke was induced in rats through middle cerebral artery occlusion surgery.Transcranial focused ultrasound stimulation was used to treat the rat model of ischemia,and electrical impedance tomography was used to measure impedance during both the acute stage of ischemia and the rehabilitation stage following the stimulation.Electrical impedance tomography results indicated that cerebral impedance increased after the onset of ischemia and decreased following transcranial focused ultrasound stimulation.Furthermore,the stimulation promoted motor function recovery,reduced cerebral infarction volume in the rat model of ischemic stroke,and induced the expression of brain-derived neurotrophic factor in the ischemic brain.Our results also revealed a significant correlation between the impedance of the ischemic brain post-intervention and improvements in behavioral scores and infarct volume.This study shows that daily administration of transcranial focused ultrasound stimulation for 20 minutes to the ischemic hemisphere 24 hours after cerebral ischemia enhanced motor recovery in a rat model of ischemia.Additionally,our findings indicate that electrical impedance tomography can serve as a valuable tool for quantitatively evaluating rehabilitation after ischemic stroke in vivo.These findings suggest the feasibility of using impedance data collected via electrical impedance tomography to clinically assess the effects of rehabilitatory interventions for patients with ischemic stroke.
基金supported by National Key Research and Development Program (2019YFA0708301)National Natural Science Foundation of China (51974337)+2 种基金the Strategic Cooperation Projects of CNPC and CUPB (ZLZX2020-03)Science and Technology Innovation Fund of CNPC (2021DQ02-0403)Open Fund of Petroleum Exploration and Development Research Institute of CNPC (2022-KFKT-09)
文摘We propose an integrated method of data-driven and mechanism models for well logging formation evaluation,explicitly focusing on predicting reservoir parameters,such as porosity and water saturation.Accurately interpreting these parameters is crucial for effectively exploring and developing oil and gas.However,with the increasing complexity of geological conditions in this industry,there is a growing demand for improved accuracy in reservoir parameter prediction,leading to higher costs associated with manual interpretation.The conventional logging interpretation methods rely on empirical relationships between logging data and reservoir parameters,which suffer from low interpretation efficiency,intense subjectivity,and suitability for ideal conditions.The application of artificial intelligence in the interpretation of logging data provides a new solution to the problems existing in traditional methods.It is expected to improve the accuracy and efficiency of the interpretation.If large and high-quality datasets exist,data-driven models can reveal relationships of arbitrary complexity.Nevertheless,constructing sufficiently large logging datasets with reliable labels remains challenging,making it difficult to apply data-driven models effectively in logging data interpretation.Furthermore,data-driven models often act as“black boxes”without explaining their predictions or ensuring compliance with primary physical constraints.This paper proposes a machine learning method with strong physical constraints by integrating mechanism and data-driven models.Prior knowledge of logging data interpretation is embedded into machine learning regarding network structure,loss function,and optimization algorithm.We employ the Physically Informed Auto-Encoder(PIAE)to predict porosity and water saturation,which can be trained without labeled reservoir parameters using self-supervised learning techniques.This approach effectively achieves automated interpretation and facilitates generalization across diverse datasets.
文摘The emergence of Medical Large Language Models has significantly transformed healthcare.Medical Large Language Models(Med-LLMs)serve as transformative tools that enhance clinical practice through applications in decision support,documentation,and diagnostics.This evaluation examines the performance of leading Med-LLMs,including GPT-4Med,Med-PaLM,MEDITRON,PubMedGPT,and MedAlpaca,across diverse medical datasets.It provides graphical comparisons of their effectiveness in distinct healthcare domains.The study introduces a domain-specific categorization system that aligns these models with optimal applications in clinical decision-making,documentation,drug discovery,research,patient interaction,and public health.The paper addresses deployment challenges of Medical-LLMs,emphasizing trustworthiness and explainability as essential requirements for healthcare AI.It presents current evaluation techniques that improve model transparency in high-stakes medical contexts and analyzes regulatory frameworks using benchmarking datasets such asMedQA,MedMCQA,PubMedQA,and MIMIC.By identifying ongoing challenges in biasmitigation,reliability,and ethical compliance,thiswork serves as a resource for selecting appropriate Med-LLMs and outlines future directions in the field.This analysis offers a roadmap for developing Med-LLMs that balance technological innovation with the trust and transparency required for clinical integration,a perspective often overlooked in existing literature.
基金supported by the Jiangxi Provincial Natural Science Foundation(No.20224BAB212022)Science and Technology Project of Education Department of Jiangxi Province(No.GJJ211435)+3 种基金the National Key Research and Development Program of China(No.2021YFA1400204)the Project of China Postdoctoral Science Foundation(No.2022M712909)the Natural Science Foundation of China(No.21603109)the Henan Joint Fund of the National Natural Science Foundation of China(No.U1404216)。
文摘Cobalt phosphide has been successfully used as a catalyst in the production of ammonia from nitric acid.Substituting appropriate atoms is expected to further improve its catalytic performance.Owing to the diversity of substituting elements,substitution sites,adsorption sites,and adsorption configurations,extensive time-consuming simulation calculations are required for the high-throughput screening method.Additionally,multi-objective attributes should be considered simultaneously in catalytic design.To tackle this challenge,this paper suggests a multi-objective cobalt phosphide catalytic material design method based on surrogate models.And the effectiveness of the proposed method was validated through comparative experiments.The proposed method led to the discovery of fifteen promising cobalt phosphide catalyst configurations.This study provides a new avenue for expediting the design of catalyst,with the potential for application in other systems.
文摘An acute skin injury model using continuous tape tearing was established,and studies the application of this model in the evaluation of soothing effects through instrument evaluation.30 healthy adult subjects were selected as the research subjects,and an acute skin model was established on the forearm flexion side of the subjects.The skin color a^(*)value and transdermal water loss rate(TEWL)value of the blank and experimental groups were tested using instruments.The results showed that at 15 and 30 minutes after using the sample,the growth values of a^(*)value and TEWL value in the experimental group were significantly lower than those in the blank group(P<0.05),the acute skin lesion model can effectively evaluate the soothing effect of cosmetics.
基金funded by the National Social Science Fund of China(Grant No.23BGL234).
文摘In the context of advancing towards dual carbon goals,numerous factories are actively engaging in energy efficiency upgrades and transformations.To accurately pinpoint energy efficiency bottlenecks within factories and prioritize renovation sequences,it is crucial to conduct comprehensive evaluations of the energy performance across various workshops.Therefore,this paper proposes an evaluation model for workshop energy efficiency based on the drive-state-response(DSR)framework combined with the fuzzy BORDA method.Firstly,an in-depth analysis of the relationships between different energy efficiency indicators was conducted.Based on the DSR model,evaluation criteria were selected from three dimensions-drive factors,state characteristics,and response measures-to establish a robust energy efficiency indicator system.Secondly,three distinct assessment techniques were selected:Grey Relational Analysis(GRA),Entropy Weight Method(EWM),and Technique for Order Preference by Similarity to Ideal Solution(TOPSIS)forming a diversified set of evaluation methods.Subsequently,by introducing the fuzzy BORDA method,a comprehensive energy efficiency evaluation model was developed,aimed at quantitatively ranking the energy performance status of each workshop.Using a real-world factory as a case study,applying our proposed evaluationmodel yielded detailed scores and rankings for each workshop.Furthermore,post hoc testing was performed using the Spearman correlation coefficient,revealing a statistic value of 10.209,which validates the effectiveness and reliability of the proposed evaluation model.This model not only assists in identifying underperforming workshops within the factory but also provides solid data support and a decision-making basis for future energy efficiency optimization strategies.
基金supported by National Key Research and Development Program of China (2023YFB3307800)National Natural Science Foundation of China (Key Program: 62136003, 62373155)+1 种基金Major Science and Technology Project of Xinjiang (No. 2022A01006-4)the Fundamental Research Funds for the Central Universities。
文摘Hydrocracking is one of the most important petroleum refining processes that converts heavy oils into gases,naphtha,diesel,and other products through cracking reactions.Multi-objective optimization algorithms can help refining enterprises determine the optimal operating parameters to maximize product quality while ensuring product yield,or to increase product yield while reducing energy consumption.This paper presents a multi-objective optimization scheme for hydrocracking based on an improved SPEA2-PE algorithm,which combines path evolution operator and adaptive step strategy to accelerate the convergence speed and improve the computational accuracy of the algorithm.The reactor model used in this article is simulated based on a twenty-five lumped kinetic model.Through model and test function verification,the proposed optimization scheme exhibits significant advantages in the multiobjective optimization process of hydrocracking.
基金supported by the Basic Public Welfare Research Program of Zhejiang Province(No.LGN22E050005).
文摘This study proposes a multi-objective optimization framework for electric winches in fiber-reinforced plastic(FRP)fishing vessels to address critical limitations of conventional designs,including excessive weight,material inefficiency,and performance redundancy.By integrating surrogate modeling techniques with a multi-objective genetic algorithm(MOGA),we have developed a systematic approach that encompasses parametric modeling,finite element analysis under extreme operational conditions,and multi-fidelity performance evaluation.Through a 10-t electric winch case study,the methodology’s effectiveness is demonstrated via parametric characterization of structural integrity,stiffness behavior,and mass distribution.The comparative analysis identified optimal surrogate models for predicting key performance metrics,which enabled the construction of a robust multi-objective optimization model.The MOGA-derived Pareto solutions produced a design configuration achieving 7.86%mass reduction,2.01%safety factor improvement,and 23.97%deformation mitigation.Verification analysis confirmed the optimization scheme’s reliability in balancing conflicting design requirements.This research establishes a generalized framework for marine deck machinery modernization,particularly addressing the structural compatibility challenges in FRP vessel retrofitting.The proposed methodology demonstrates significant potential for facilitating sustainable upgrades of fishing vessel equipment through systematic performance optimization.
基金funded by the German Research Foundation[Grant Number:496846758].
文摘Objectives:Valid estimation of energy expenditure remains a challenge,particularly when using ankle-and thighworn devices.The Move 4 is a research-grade accelerometer previously tested for predicting metabolic equivalents(METs)when worn at the waist or wrist.This study aimed to calibrate and evaluate regression models to estimate METs from Move 4 data when worn at the ankle and thigh.Methods:Participants completed walking and jogging tasks under laboratory conditions while wearing Move 4 sensors and with indirect calorimetry as a reference measure.Models were calibrated using study 1(n=160)and evaluated in an independent dataset(study 2;n=15).Performance was assessed using mean absolute error(MAE),root mean square error(RMSE),and Bland-Altman analyses.Results:The MET models demonstrated strong agreement across both locations and datasets.For the thigh position,the MAE ranged from 0.60 METs(walking)to 1.38 METs(jogging),with RMSE of 0.82 and 1.70 in the evaluation data.Calibration metrics were comparable(jogging:MAE=1.24,RMSE=1.63).The ankle models showed similar accuracy,with MAEs of 0.66(walking)and 1.39(jogging),and RMSEs of 0.85 and 1.67,respectively.Systematic bias remained low(mean differences between−0.34 and−0.01 METs).Conclusions:This study provides the first calibration and evaluation for estimating METs from ankle-and thigh-worn Move 4 accelerometers.The model indicated accurate,highresolution MET estimation for walking and jogging.Future work should expand independent performance evaluations,including diverse activities such as static activities,and diverse samples under free-living conditions.
文摘With the rapid development of generative artificial intelligence technologies,represented by large language models,university-level computer science education is undergoing a critical transition-from knowledge-based instruction to competency-oriented teaching.A postgraduate student competency evaluation model can serve as a framework to organize and guide both teaching and research activities at the postgraduate level.A number of relevant research efforts have already been conducted in this area.Graduate education plays a vital role not only as a continuation and enhancement of undergraduate education but also as essential preparation for future research endeavors.An analysis of the acceptance of competency evaluation models refers to the assessment of how various stakeholders perceive the importance of different components within the model.Investigating the degree of acceptance among diverse groups-such as current undergraduate students,current postgraduate students,graduates with less than three years of work experience,and those with more than three years of work experience-can offer valuable insights for improving and optimizing postgraduate education and training practices.
基金funded by the Joint Project of Industry-University-Research of Jiangsu Province(Grant:BY20231146).
文摘With the widespread application of Internet of Things(IoT)technology,the processing of massive realtime streaming data poses significant challenges to the computational and data-processing capabilities of systems.Although distributed streaming data processing frameworks such asApache Flink andApache Spark Streaming provide solutions,meeting stringent response time requirements while ensuring high throughput and resource utilization remains an urgent problem.To address this,the study proposes a formal modeling approach based on Performance Evaluation Process Algebra(PEPA),which abstracts the core components and interactions of cloud-based distributed streaming data processing systems.Additionally,a generic service flow generation algorithmis introduced,enabling the automatic extraction of service flows fromthe PEPAmodel and the computation of key performance metrics,including response time,throughput,and resource utilization.The novelty of this work lies in the integration of PEPA-based formal modeling with the service flow generation algorithm,bridging the gap between formal modeling and practical performance evaluation for IoT systems.Simulation experiments demonstrate that optimizing the execution efficiency of components can significantly improve system performance.For instance,increasing the task execution rate from 10 to 100 improves system performance by 9.53%,while further increasing it to 200 results in a 21.58%improvement.However,diminishing returns are observed when the execution rate reaches 500,with only a 0.42%gain.Similarly,increasing the number of TaskManagers from 10 to 20 improves response time by 18.49%,but the improvement slows to 6.06% when increasing from 20 to 50,highlighting the importance of co-optimizing component efficiency and resource management to achieve substantial performance gains.This study provides a systematic framework for analyzing and optimizing the performance of IoT systems for large-scale real-time streaming data processing.The proposed approach not only identifies performance bottlenecks but also offers insights into improving system efficiency under different configurations and workloads.
基金Supported by National High-quality Development Project of China(Grant No.2340STCZB193).
文摘The average stiffness performance indices throughout the workspace are commonly used as global stiffness performance indices to evaluate the overall stiffness performance of parallel mechanisms,which involves an analysis of the stiffness performance of numerous discrete points in the workspace.This necessitates time-consuming and inefficient calculation,which is particularly pronounced in the optimization design stage of the mechanism,where the variations in the global stiffness performance indices versus various dimensional and structural parameters need to be analyzed.This paper presents a semi-analytical approach for stiffness modeling of the novel(R(RPS&RP))&2-UPS parallel mechanism(referred to as the Trifree mechanism)and proposes“local”stiffness performance indices as alternatives to global indices.Drawing on the screw theory,the Cartesian stiffness matrix of the Trifree mechanism is formulated explicitly by considering the compliances of all elastic elements and the over-constraint characteristics inherent in the mechanism.Based on the spherical motion pattern of the Trifree mechanism,four special reference configurations are extracted within the workspace.This yields“local”stiffness performance indices capable of accurately evaluating the overall stiffness performance of the mechanism and effectively improving the computational efficiency.The variations in global and“local”stiffness performance indices versus key design parameters are investigated.Furthermore,the proposed indices are applied to the Tricept and Trimule mechanisms.The results demonstrate that the proposed indices exhibit excellent computational accuracy and efficiency in evaluating the overall stiffness performance of these spherical parallel mechanisms.Moreover,the stiffness performance of the novel parallel mechanism investigated in this study closely resembles that of the well-known Tricept and Trimule mechanisms.This research proposes a semi-analytic stiffness model of the Trifree mechanism and“local”stiffness performance indices to evaluate the overall stiffness performance,thereby substantially improving the computational efficiency without sacrificing accuracy.
文摘The rapid and increasing growth in the volume and number of cyber threats from malware is not a real danger;the real threat lies in the obfuscation of these cyberattacks,as they constantly change their behavior,making detection more difficult.Numerous researchers and developers have devoted considerable attention to this topic;however,the research field has not yet been fully saturated with high-quality studies that address these problems.For this reason,this paper presents a novel multi-objective Markov-enhanced adaptive whale optimization(MOMEAWO)cybersecurity model to improve the classification of binary and multi-class malware threats through the proposed MOMEAWO approach.The proposed MOMEAWO cybersecurity model aims to provide an innovative solution for analyzing,detecting,and classifying the behavior of obfuscated malware within their respective families.The proposed model includes three classification types:Binary classification and multi-class classification(e.g.,four families and 16 malware families).To evaluate the performance of this model,we used a recently published dataset called the Canadian Institute for Cybersecurity Malware Memory Analysis(CIC-MalMem-2022)that contains balanced data.The results show near-perfect accuracy in binary classification and high accuracy in multi-class classification compared with related work using the same dataset.
文摘The rapid development of evolutionary deep learning has led to the emergence of various Neural Architecture Search(NAS)algorithms designed to optimize neural network structures.However,these algorithms often face significant computational costs due to the time-consuming process of training neural networks and evaluating their performance.Traditional NAS approaches,which rely on exhaustive evaluations and large training datasets,are inefficient for solving complex image classification tasks within limited time frames.To address these challenges,this paper proposes a novel NAS algorithm that integrates a hierarchical evaluation strategy based on Surrogate models,specifically using supernet to pre-trainweights and randomforests as performance predictors.This hierarchical framework combines rapid Surrogate model evaluations with traditional,precise evaluations to balance the trade-off between performance accuracy and computational efficiency.The algorithm significantly reduces the time required for model evaluation by predicting the fitness of candidate architectures using a random forest Surrogate model,thus alleviating the need for full training cycles for each architecture.The proposed method also incorporates evolutionary operations such as mutation and crossover to refine the search process and improve the accuracy of the resulting architectures.Experimental evaluations on the CIFAR-10 and CIFAR-100 datasets demonstrate that the proposed hierarchical evaluation strategy reduces the search time and costs compared to traditional methods,while achieving comparable or even superior model performance.The results suggest that this approach can efficiently handle resourceconstrained tasks,providing a promising solution for accelerating the NAS process without compromising the quality of the generated architectures.
文摘Offline policy evaluation,evaluating and selecting complex policies for decision-making by only using offline datasets is important in reinforcement learning.At present,the model-based offline policy evaluation(MBOPE)is widely welcomed because of its easy to implement and good performance.MBOPE directly approximates the unknown value of a given policy using the Monte Carlo method given the estimated transition and reward functions of the environment.Usually,multiple models are trained,and then one of them is selected to be used.However,a challenge remains in selecting an appropriate model from those trained for further use.The authors first analyse the upper bound of the difference between the approximated value and the unknown true value.Theoretical results show that this difference is related to the trajectories generated by the given policy on the learnt model and the prediction error of the transition and reward functions at these generated data points.Based on the theoretical results,a new criterion is proposed to tell which trained model is better suited for evaluating the given policy.At last,the effectiveness of the proposed criterion is demonstrated on both benchmark and synthetic offline datasets.
