Android smartphones have become an integral part of our daily lives,becoming targets for ransomware attacks.Such attacks encrypt user information and ask for payment to recover it.Conventional detection mechanisms,suc...Android smartphones have become an integral part of our daily lives,becoming targets for ransomware attacks.Such attacks encrypt user information and ask for payment to recover it.Conventional detection mechanisms,such as signature-based and heuristic techniques,often fail to detect new and polymorphic ransomware samples.To address this challenge,we employed various ensemble classifiers,such as Random Forest,Gradient Boosting,Bagging,and AutoML models.We aimed to showcase how AutoML can automate processes such as model selection,feature engineering,and hyperparameter optimization,to minimize manual effort while ensuring or enhancing performance compared to traditional approaches.We used this framework to test it with a publicly available dataset from the Kaggle repository,which contains features for Android ransomware network traffic.The dataset comprises 392,024 flow records,divided into eleven groups.There are ten classes for various ransomware types,including SVpeng,PornDroid,Koler,WannaLocker,and Lockerpin.There is also a class for regular traffic.We applied a three-step procedure to select themost relevant features:filter,wrapper,and embeddedmethods.The Bagging classifier was highly accurate,correctly getting 99.84%of the time.The FLAML AutoML framework was evenmore accurate,correctly getting 99.85%of the time.This is indicative of howwellAutoML performs in improving things with minimal human assistance.Our findings indicate that AutoML is an efficient,scalable,and flexible method to discover Android ransomware,and it will facilitate the development of next-generation intrusion detection systems.展开更多
This study presents a physics-informed modelling framework that combines finite element method(FEM)simulations and supervised machine learning(ML)to predict the self-healing performance of microbial concrete.A FEniCS-...This study presents a physics-informed modelling framework that combines finite element method(FEM)simulations and supervised machine learning(ML)to predict the self-healing performance of microbial concrete.A FEniCS-based FEM platform resolves multiphysics phenomena including nutrient diffusion,microbial CaCO_(3) precipitation,and stiffness recovery.These simulations,together with experimental data,are used to train ML models(Random Forest yielding normalized RMSE≈0.10)capable of predicting performance over a wide range of design parameters.Feature importance analysis identifies curing temperature,calcium carbonate precipitation rate,crack width,bacterial strain,and encapsulation method as the most influential parameters.The coupled FEM-ML approach enables sensitivity analysis,design optimization,and prediction beyond the training dataset(consistently exceeding 90%healing efficiency).Experimental validation confirms model robustness in both crack closure and strength recovery.This FEM–ML pipeline thus offers a generalizable,interpretable,and scalable strategy for the design of intelligent,self-adaptive construction materials.展开更多
Efficient surface passivation is critical for achieving high-performance perovskite solar cells(PSCs),yet the discovery of optimal passivators remains a time-consuming,trial-and-error process.Here,we report a synergis...Efficient surface passivation is critical for achieving high-performance perovskite solar cells(PSCs),yet the discovery of optimal passivators remains a time-consuming,trial-and-error process.Here,we report a synergistic machine learning(ML)and density functional theory(DFT)approach that enables predictive and rapid identification of effective passivation materials.By training an XGBoost model(91.3%accuracy)with DFT-derived molecular descriptors and activity calculations,we identify 2-(4-aminophenyl)-3H-benzimidazol-5-amine(APBIA)as a promising passivator.Experimental validation demonstrates that APBIA effectively removes surface impurities and passivates defects within perovskite films,leading to a significant increase in power conversion efficiency(PCE)from 22.48%to 25.55%(certified as 25.02%).This ML-DFT framework provides a generalizable pathway for accelerating the development of advanced functional materials for photovoltaic applications.展开更多
Edge Machine Learning(EdgeML)and Tiny Machine Learning(TinyML)are fast-growing fields that bring machine learning to resource-constrained devices,allowing real-time data processing and decision-making at the network’...Edge Machine Learning(EdgeML)and Tiny Machine Learning(TinyML)are fast-growing fields that bring machine learning to resource-constrained devices,allowing real-time data processing and decision-making at the network’s edge.However,the complexity of model conversion techniques,diverse inference mechanisms,and varied learning strategies make designing and deploying these models challenging.Additionally,deploying TinyML models on resource-constrained hardware with specific software frameworks has broadened EdgeML’s applications across various sectors.These factors underscore the necessity for a comprehensive literature review,as current reviews do not systematically encompass the most recent findings on these topics.Consequently,it provides a comprehensive overview of state-of-the-art techniques in model conversion,inference mechanisms,learning strategies within EdgeML,and deploying these models on resource-constrained edge devices using TinyML.It identifies 90 research articles published between 2018 and 2025,categorizing them into two main areas:(1)model conversion,inference,and learning strategies in EdgeML and(2)deploying TinyML models on resource-constrained hardware using specific software frameworks.In the first category,the synthesis of selected research articles compares and critically reviews various model conversion techniques,inference mechanisms,and learning strategies.In the second category,the synthesis identifies and elaborates on major development boards,software frameworks,sensors,and algorithms used in various applications across six major sectors.As a result,this article provides valuable insights for researchers,practitioners,and developers.It assists them in choosing suitable model conversion techniques,inference mechanisms,learning strategies,hardware development boards,software frameworks,sensors,and algorithms tailored to their specific needs and applications across various sectors.展开更多
Together,the heart and lung sound comprise the thoracic cavity sound,which provides informative details that reflect patient conditions,particularly heart failure(HF)patients.However,due to the limitations of human he...Together,the heart and lung sound comprise the thoracic cavity sound,which provides informative details that reflect patient conditions,particularly heart failure(HF)patients.However,due to the limitations of human hearing,a limited amount of information can be auscultated from thoracic cavity sounds.With the aid of artificial intelligence–machine learning,these features can be analyzed and aid in the care of HF patients.Machine learning of thoracic cavity sound data involves sound data pre-processing by denoising,resampling,segmentation,and normalization.Afterwards,the most crucial step is feature extraction and se-lection where relevant features are selected to train the model.The next step is classification and model performance evaluation.This review summarizes the currently available studies that utilized different machine learning models,different feature extraction and selection methods,and different classifiers to generate the desired output.Most studies have analyzed the heart sound component of thoracic cavity sound to distinguish between normal and HF patients.Additionally,some studies have aimed to classify HF patients based on thoracic cavity sounds in their entirety,while others have focused on risk strati-fication and prognostic evaluation of HF patients using thoracic cavity sounds.Overall,the results from these studies demonstrate a promisingly high level of accuracy.Therefore,future prospective studies should incorporate these machine learning models to expedite their integration into daily clinical practice for managing HF patients.展开更多
The advanced driver assistance system(ADAS)primarily serves to assist drivers in monitoring the speed of the car and helps them make the right decision,which leads to fewer fatal accidents and ensures higher safety.In...The advanced driver assistance system(ADAS)primarily serves to assist drivers in monitoring the speed of the car and helps them make the right decision,which leads to fewer fatal accidents and ensures higher safety.In the artificial Intelligence domain,machine learning(ML)was developed to make inferences with a degree of accuracy similar to that of humans;however,enormous amounts of data are required.Machine learning enhances the accuracy of the decisions taken by ADAS,by evaluating all the data received from various vehicle sensors.This study summarizes all the critical algorithms used in ADAS technologies and presents the evolution of ADAS technology.Initially,ADAS technology is introduced,along with its evolution,to understand the objectives of developing this technology.Subsequently,the critical algorithms used in ADAS technology,which include face detection,head-pose estimation,gaze estimation,and link detection are discussed.A further discussion follows on the impact of ML on each algorithm in different environments,leading to increased accuracy at the expense of additional computing,to increase efficiency.The aim of this study was to evaluate all the methods with or without ML for each algorithm.展开更多
Machine learning(ML)has been increasingly adopted to solve engineering problems with performance gauged by accuracy,efficiency,and security.Notably,blockchain technology(BT)has been added to ML when security is a part...Machine learning(ML)has been increasingly adopted to solve engineering problems with performance gauged by accuracy,efficiency,and security.Notably,blockchain technology(BT)has been added to ML when security is a particular concern.Nevertheless,there is a research gap that prevailing solutions focus primarily on data security using blockchain but ignore computational security,making the traditional ML process vulnerable to off-chain risks.Therefore,the research objective is to develop a novel ML on blockchain(MLOB)framework to ensure both the data and computational process security.The central tenet is to place them both on the blockchain,execute them as blockchain smart contracts,and protect the execution records on-chain.The framework is established by developing a prototype and further calibrated using a case study of industrial inspection.It is shown that the MLOB framework,compared with existing ML and BT isolated solutions,is superior in terms of security(successfully defending against corruption on six designed attack scenario),maintaining accuracy(0.01%difference with baseline),albeit with a slightly compromised efficiency(0.231 second latency increased).The key finding is MLOB can significantly enhances the computational security of engineering computing without increasing computing power demands.This finding can alleviate concerns regarding the computational resource requirements of ML-BT integration.With proper adaption,the MLOB framework can inform various novel solutions to achieve computational security in broader engineering challenges.展开更多
Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face...Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face challenges,including high metal usage,high process costs,and low cyclohexene yield.This study utilizes existing literature data combined with machine learning methods to analyze the factors influencing benzene conversion,cyclohexene selectivity,and yield in the benzene hydrogenation to cyclohexene reaction.It constructs predictive models based on XGBoost and Random Forest algorithms.After analysis,it was found that reaction time,Ru content,and space velocity are key factors influencing cyclohexene yield,selectivity,and benzene conversion.Shapley Additive Explanations(SHAP)analysis and feature importance analysis further revealed the contribution of each variable to the reaction outcomes.Additionally,we randomly generated one million variable combinations using the Dirichlet distribution to attempt to predict high-yield catalyst formulations.This paper provides new insights into the application of machine learning in heterogeneous catalysis and offers some reference for further research.展开更多
The uplift resistance of the soil overlying shield tunnels significantly impacts their anti-floating stability.However,research on uplift resistance concerning special-shaped shield tunnels is limited.This study combi...The uplift resistance of the soil overlying shield tunnels significantly impacts their anti-floating stability.However,research on uplift resistance concerning special-shaped shield tunnels is limited.This study combines numerical simulation with machine learning techniques to explore this issue.It presents a summary of special-shaped tunnel geometries and introduces a shape coefficient.Through the finite element software,Plaxis3D,the study simulates six key parameters—shape coefficient,burial depth ratio,tunnel’s longest horizontal length,internal friction angle,cohesion,and soil submerged bulk density—that impact uplift resistance across different conditions.Employing XGBoost and ANN methods,the feature importance of each parameter was analyzed based on the numerical simulation results.The findings demonstrate that a tunnel shape more closely resembling a circle leads to reduced uplift resistance in the overlying soil,whereas other parameters exhibit the contrary effects.Furthermore,the study reveals a diminishing trend in the feature importance of buried depth ratio,internal friction angle,tunnel longest horizontal length,cohesion,soil submerged bulk density,and shape coefficient in influencing uplift resistance.展开更多
Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitiv...Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.展开更多
Split Learning(SL)has been promoted as a promising collaborative machine learning technique designed to address data privacy and resource efficiency.Specifically,neural networks are divided into client and server subn...Split Learning(SL)has been promoted as a promising collaborative machine learning technique designed to address data privacy and resource efficiency.Specifically,neural networks are divided into client and server subnetworks in order to mitigate the exposure of sensitive data and reduce the overhead on client devices,thereby making SL particularly suitable for resource-constrained devices.Although SL prevents the direct transmission of raw data,it does not alleviate entirely the risk of privacy breaches.In fact,the data intermediately transmitted to the server sub-model may include patterns or information that could reveal sensitive data.Moreover,achieving a balance between model utility and data privacy has emerged as a challenging problem.In this article,we propose a novel defense approach that combines:(i)Adversarial learning,and(ii)Network channel pruning.In particular,the proposed adversarial learning approach is specifically designed to reduce the risk of private data exposure while maintaining high performance for the utility task.On the other hand,the suggested channel pruning enables the model to adaptively adjust and reactivate pruned channels while conducting adversarial training.The integration of these two techniques reduces the informativeness of the intermediate data transmitted by the client sub-model,thereby enhancing its robustness against attribute inference attacks without adding significant computational overhead,making it wellsuited for IoT devices,mobile platforms,and Internet of Vehicles(IoV)scenarios.The proposed defense approach was evaluated using EfficientNet-B0,a widely adopted compact model,along with three benchmark datasets.The obtained results showcased its superior defense capability against attribute inference attacks compared to existing state-of-the-art methods.This research’s findings demonstrated the effectiveness of the proposed channel pruning-based adversarial training approach in achieving the intended compromise between utility and privacy within SL frameworks.In fact,the classification accuracy attained by the attackers witnessed a drastic decrease of 70%.展开更多
Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Re...Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.展开更多
Latest digital advancements have intensified the necessity for adaptive,data-driven and socially-centered learning ecosystems.This paper presents the formulation of a cross-platform,innovative,gamified and personalize...Latest digital advancements have intensified the necessity for adaptive,data-driven and socially-centered learning ecosystems.This paper presents the formulation of a cross-platform,innovative,gamified and personalized Learning Ecosystem,which integrates 3D/VR environments,as well as machine learning algorithms,and business intelligence frameworks to enhance learner-centered education and inferenced decision-making.This Learning System makes use of immersive,analytically assessed virtual learning spaces,therefore facilitating real-time monitoring of not just learning performance,but also overall engagement and behavioral patterns,via a comprehensive set of sustainability-oriented ESG-aligned Key Performance Indicators(KPIs).Machine learning models support predictive analysis,personalized feedback,and hybrid recommendation mechanisms,whilst dedicated dashboards translate complex educational data into actionable insights for all Use Cases of the System(Educational Institutions,Educators and Learners).Additionally,the presented Learning System introduces a structured Mentoring and Consulting Subsystem,thence reinforcing human-centered guidance alongside automated intelligence.The Platform’s modular architecture and simulation-centered evaluation approach actively support personalized,and continuously optimized learning pathways.Thence,it exemplifies a mature,adaptive Learning Ecosystem,supporting immersive technologies,analytics,and pedagogical support,hence,contributing to contemporary digital learning innovation and sociotechnical transformation in education.展开更多
Automated grading of dandruff severity is a clinically significant but challenging task due to the inherent ordinal nature of severity levels and the high prevalence of label noise from subjective expert annotations.S...Automated grading of dandruff severity is a clinically significant but challenging task due to the inherent ordinal nature of severity levels and the high prevalence of label noise from subjective expert annotations.Standard classification methods fail to address these dual challenges,limiting their real-world performance.In this paper,a novel,three-phase training framework is proposed that learns a robust ordinal classifier directly from noisy labels.The approach synergistically combines a rank-based ordinal regression backbone with a cooperative,semi-supervised learning strategy to dynamically partition the data into clean and noisy subsets.A hybrid training objective is then employed,applying a supervised ordinal loss to the clean set.The noisy set is simultaneously trained using a dualobjective that combines a semi-supervised ordinal loss with a parallel,label-agnostic contrastive loss.This design allows themodel to learn fromthe entire noisy subset while using contrastive learning to mitigate the risk of error propagation frompotentially corrupt supervision.Extensive experiments on a new,large-scale,multi-site clinical dataset validate our approach.Themethod achieves state-of-the-art performance with 80.71%accuracy and a 76.86%F1-score,significantly outperforming existing approaches,including a 2.26%improvement over the strongest baseline method.This work provides not only a robust solution for a practical medical imaging problem but also a generalizable framework for other tasks plagued by noisy ordinal labels.展开更多
Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Tr...Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Training(AT)enables NIDS agents to discover and prevent newattack paths by exposing them to competing examples,thereby increasing detection accuracy,reducing False Positives(FPs),and enhancing network security.To develop robust decision-making capabilities for real-world network disruptions and hostile activity,NIDS agents are trained in adversarial scenarios to monitor the current state and notify management of any abnormal or malicious activity.The accuracy and timeliness of the IDS were crucial to the network’s availability and reliability at this time.This paper analyzes ARL applications in NIDS,revealing State-of-The-Art(SoTA)methodology,issues,and future research prospects.This includes Reinforcement Machine Learning(RML)-based NIDS,which enables an agent to interact with the environment to achieve a goal,andDeep Reinforcement Learning(DRL)-based NIDS,which can solve complex decision-making problems.Additionally,this survey study addresses cybersecurity adversarial circumstances and their importance for ARL and NIDS.Architectural design,RL algorithms,feature representation,and training methodologies are examined in the ARL-NIDS study.This comprehensive study evaluates ARL for intelligent NIDS research,benefiting cybersecurity researchers,practitioners,and policymakers.The report promotes cybersecurity defense research and innovation.展开更多
As urbanization continues to accelerate,the challenges associated with managing transportation in metropolitan areas become increasingly complex.The surge in population density contributes to traffic congestion,impact...As urbanization continues to accelerate,the challenges associated with managing transportation in metropolitan areas become increasingly complex.The surge in population density contributes to traffic congestion,impacting travel experiences and posing safety risks.Smart urban transportation management emerges as a strategic solution,conceptualized here as a multidimensional big data problem.The success of this strategy hinges on the effective collection of information from diverse,extensive,and heterogeneous data sources,necessitating the implementation of full⁃stack Information and Communication Technology(ICT)solutions.The main idea of the work is to investigate the current technologies of Intelligent Transportation Systems(ITS)and enhance the safety of urban transportation systems.Machine learning models,trained on historical data,can predict traffic congestion,allowing for the implementation of preventive measures.Deep learning architectures,with their ability to handle complex data representations,further refine traffic predictions,contributing to more accurate and dynamic transportation management.The background of this research underscores the challenges posed by traffic congestion in metropolitan areas and emphasizes the need for advanced technological solutions.By integrating GPS and GIS technologies with machine learning algorithms,this work aims to pay attention to the development of intelligent transportation systems that not only address current challenges but also pave the way for future advancements in urban transportation management.展开更多
基金supported through theOngoing Research Funding Program(ORF-2025-498),King Saud University,Riyadh,Saudi Arabia.
文摘Android smartphones have become an integral part of our daily lives,becoming targets for ransomware attacks.Such attacks encrypt user information and ask for payment to recover it.Conventional detection mechanisms,such as signature-based and heuristic techniques,often fail to detect new and polymorphic ransomware samples.To address this challenge,we employed various ensemble classifiers,such as Random Forest,Gradient Boosting,Bagging,and AutoML models.We aimed to showcase how AutoML can automate processes such as model selection,feature engineering,and hyperparameter optimization,to minimize manual effort while ensuring or enhancing performance compared to traditional approaches.We used this framework to test it with a publicly available dataset from the Kaggle repository,which contains features for Android ransomware network traffic.The dataset comprises 392,024 flow records,divided into eleven groups.There are ten classes for various ransomware types,including SVpeng,PornDroid,Koler,WannaLocker,and Lockerpin.There is also a class for regular traffic.We applied a three-step procedure to select themost relevant features:filter,wrapper,and embeddedmethods.The Bagging classifier was highly accurate,correctly getting 99.84%of the time.The FLAML AutoML framework was evenmore accurate,correctly getting 99.85%of the time.This is indicative of howwellAutoML performs in improving things with minimal human assistance.Our findings indicate that AutoML is an efficient,scalable,and flexible method to discover Android ransomware,and it will facilitate the development of next-generation intrusion detection systems.
基金funding from the European Union’s Horizon 2020 Research and Innovation Programme under the Marie Skłodowska-Curie Grant Agreement No.945478(SASPRO2)supported by the ReBuilt project:Circular and Digital Renewal of Central Europe Construction and Building Sector CE0100390 ReBuiltthe Slovak Research and Development Agency under APVV-23-0383 and the Slovak Grant Agency VEGA No.2/0080/24.
文摘This study presents a physics-informed modelling framework that combines finite element method(FEM)simulations and supervised machine learning(ML)to predict the self-healing performance of microbial concrete.A FEniCS-based FEM platform resolves multiphysics phenomena including nutrient diffusion,microbial CaCO_(3) precipitation,and stiffness recovery.These simulations,together with experimental data,are used to train ML models(Random Forest yielding normalized RMSE≈0.10)capable of predicting performance over a wide range of design parameters.Feature importance analysis identifies curing temperature,calcium carbonate precipitation rate,crack width,bacterial strain,and encapsulation method as the most influential parameters.The coupled FEM-ML approach enables sensitivity analysis,design optimization,and prediction beyond the training dataset(consistently exceeding 90%healing efficiency).Experimental validation confirms model robustness in both crack closure and strength recovery.This FEM–ML pipeline thus offers a generalizable,interpretable,and scalable strategy for the design of intelligent,self-adaptive construction materials.
基金supported by the National Key Research and Development Program of China (Grant No. 2024YFB4205101)the National Natural Science Foundation of China (No. 62274098 and No. 62074084)+2 种基金the Natural Science Foundation of Tianjin (No.22JCYBJC01300, No. 23JCYBJC01620 and No. 21JCYBJC00270)the Overseas Expertise Introduction Project for Discipline Innovation of Higher Edu cation of China (Grant No. B16027)the Fundamental Research Funds for the Central Universities,Nankai University (No. 63241568)
文摘Efficient surface passivation is critical for achieving high-performance perovskite solar cells(PSCs),yet the discovery of optimal passivators remains a time-consuming,trial-and-error process.Here,we report a synergistic machine learning(ML)and density functional theory(DFT)approach that enables predictive and rapid identification of effective passivation materials.By training an XGBoost model(91.3%accuracy)with DFT-derived molecular descriptors and activity calculations,we identify 2-(4-aminophenyl)-3H-benzimidazol-5-amine(APBIA)as a promising passivator.Experimental validation demonstrates that APBIA effectively removes surface impurities and passivates defects within perovskite films,leading to a significant increase in power conversion efficiency(PCE)from 22.48%to 25.55%(certified as 25.02%).This ML-DFT framework provides a generalizable pathway for accelerating the development of advanced functional materials for photovoltaic applications.
文摘Edge Machine Learning(EdgeML)and Tiny Machine Learning(TinyML)are fast-growing fields that bring machine learning to resource-constrained devices,allowing real-time data processing and decision-making at the network’s edge.However,the complexity of model conversion techniques,diverse inference mechanisms,and varied learning strategies make designing and deploying these models challenging.Additionally,deploying TinyML models on resource-constrained hardware with specific software frameworks has broadened EdgeML’s applications across various sectors.These factors underscore the necessity for a comprehensive literature review,as current reviews do not systematically encompass the most recent findings on these topics.Consequently,it provides a comprehensive overview of state-of-the-art techniques in model conversion,inference mechanisms,learning strategies within EdgeML,and deploying these models on resource-constrained edge devices using TinyML.It identifies 90 research articles published between 2018 and 2025,categorizing them into two main areas:(1)model conversion,inference,and learning strategies in EdgeML and(2)deploying TinyML models on resource-constrained hardware using specific software frameworks.In the first category,the synthesis of selected research articles compares and critically reviews various model conversion techniques,inference mechanisms,and learning strategies.In the second category,the synthesis identifies and elaborates on major development boards,software frameworks,sensors,and algorithms used in various applications across six major sectors.As a result,this article provides valuable insights for researchers,practitioners,and developers.It assists them in choosing suitable model conversion techniques,inference mechanisms,learning strategies,hardware development boards,software frameworks,sensors,and algorithms tailored to their specific needs and applications across various sectors.
文摘Together,the heart and lung sound comprise the thoracic cavity sound,which provides informative details that reflect patient conditions,particularly heart failure(HF)patients.However,due to the limitations of human hearing,a limited amount of information can be auscultated from thoracic cavity sounds.With the aid of artificial intelligence–machine learning,these features can be analyzed and aid in the care of HF patients.Machine learning of thoracic cavity sound data involves sound data pre-processing by denoising,resampling,segmentation,and normalization.Afterwards,the most crucial step is feature extraction and se-lection where relevant features are selected to train the model.The next step is classification and model performance evaluation.This review summarizes the currently available studies that utilized different machine learning models,different feature extraction and selection methods,and different classifiers to generate the desired output.Most studies have analyzed the heart sound component of thoracic cavity sound to distinguish between normal and HF patients.Additionally,some studies have aimed to classify HF patients based on thoracic cavity sounds in their entirety,while others have focused on risk strati-fication and prognostic evaluation of HF patients using thoracic cavity sounds.Overall,the results from these studies demonstrate a promisingly high level of accuracy.Therefore,future prospective studies should incorporate these machine learning models to expedite their integration into daily clinical practice for managing HF patients.
文摘The advanced driver assistance system(ADAS)primarily serves to assist drivers in monitoring the speed of the car and helps them make the right decision,which leads to fewer fatal accidents and ensures higher safety.In the artificial Intelligence domain,machine learning(ML)was developed to make inferences with a degree of accuracy similar to that of humans;however,enormous amounts of data are required.Machine learning enhances the accuracy of the decisions taken by ADAS,by evaluating all the data received from various vehicle sensors.This study summarizes all the critical algorithms used in ADAS technologies and presents the evolution of ADAS technology.Initially,ADAS technology is introduced,along with its evolution,to understand the objectives of developing this technology.Subsequently,the critical algorithms used in ADAS technology,which include face detection,head-pose estimation,gaze estimation,and link detection are discussed.A further discussion follows on the impact of ML on each algorithm in different environments,leading to increased accuracy at the expense of additional computing,to increase efficiency.The aim of this study was to evaluate all the methods with or without ML for each algorithm.
文摘Machine learning(ML)has been increasingly adopted to solve engineering problems with performance gauged by accuracy,efficiency,and security.Notably,blockchain technology(BT)has been added to ML when security is a particular concern.Nevertheless,there is a research gap that prevailing solutions focus primarily on data security using blockchain but ignore computational security,making the traditional ML process vulnerable to off-chain risks.Therefore,the research objective is to develop a novel ML on blockchain(MLOB)framework to ensure both the data and computational process security.The central tenet is to place them both on the blockchain,execute them as blockchain smart contracts,and protect the execution records on-chain.The framework is established by developing a prototype and further calibrated using a case study of industrial inspection.It is shown that the MLOB framework,compared with existing ML and BT isolated solutions,is superior in terms of security(successfully defending against corruption on six designed attack scenario),maintaining accuracy(0.01%difference with baseline),albeit with a slightly compromised efficiency(0.231 second latency increased).The key finding is MLOB can significantly enhances the computational security of engineering computing without increasing computing power demands.This finding can alleviate concerns regarding the computational resource requirements of ML-BT integration.With proper adaption,the MLOB framework can inform various novel solutions to achieve computational security in broader engineering challenges.
基金Supported by CAS Basic and Interdisciplinary Frontier Scientific Research Pilot Project(XDB1190300,XDB1190302)Youth Innovation Promotion Association CAS(Y2021056)+1 种基金Joint Fund of the Yulin University and the Dalian National Laboratory for Clean Energy(YLU-DNL Fund 2022007)The special fund for Science and Technology Innovation Teams of Shanxi Province(202304051001007)。
文摘Cyclohexene is an important raw material in the production of nylon.Selective hydrogenation of benzene is a key method for preparing cyclohexene.However,the Ru catalysts used in current industrial processes still face challenges,including high metal usage,high process costs,and low cyclohexene yield.This study utilizes existing literature data combined with machine learning methods to analyze the factors influencing benzene conversion,cyclohexene selectivity,and yield in the benzene hydrogenation to cyclohexene reaction.It constructs predictive models based on XGBoost and Random Forest algorithms.After analysis,it was found that reaction time,Ru content,and space velocity are key factors influencing cyclohexene yield,selectivity,and benzene conversion.Shapley Additive Explanations(SHAP)analysis and feature importance analysis further revealed the contribution of each variable to the reaction outcomes.Additionally,we randomly generated one million variable combinations using the Dirichlet distribution to attempt to predict high-yield catalyst formulations.This paper provides new insights into the application of machine learning in heterogeneous catalysis and offers some reference for further research.
基金Guangzhou Metro Scientific Research Project(No.JT204-100111-23001)Chongqing Municipal Special Project for Technological Innovation and Application Development(No.CSTB2022TIAD-KPX0101)Science and Technology Research and Development Program of China State Railway Group Co.,Ltd.(No.N2023G045)。
文摘The uplift resistance of the soil overlying shield tunnels significantly impacts their anti-floating stability.However,research on uplift resistance concerning special-shaped shield tunnels is limited.This study combines numerical simulation with machine learning techniques to explore this issue.It presents a summary of special-shaped tunnel geometries and introduces a shape coefficient.Through the finite element software,Plaxis3D,the study simulates six key parameters—shape coefficient,burial depth ratio,tunnel’s longest horizontal length,internal friction angle,cohesion,and soil submerged bulk density—that impact uplift resistance across different conditions.Employing XGBoost and ANN methods,the feature importance of each parameter was analyzed based on the numerical simulation results.The findings demonstrate that a tunnel shape more closely resembling a circle leads to reduced uplift resistance in the overlying soil,whereas other parameters exhibit the contrary effects.Furthermore,the study reveals a diminishing trend in the feature importance of buried depth ratio,internal friction angle,tunnel longest horizontal length,cohesion,soil submerged bulk density,and shape coefficient in influencing uplift resistance.
文摘Federated Learning(FL)has become a leading decentralized solution that enables multiple clients to train a model in a collaborative environment without directly sharing raw data,making it suitable for privacy-sensitive applications such as healthcare,finance,and smart systems.As the field continues to evolve,the research field has become more complex and scattered,covering different system designs,training methods,and privacy techniques.This survey is organized around the three core challenges:how the data is distributed,how models are synchronized,and how to defend against attacks.It provides a structured and up-to-date review of FL research from 2023 to 2025,offering a unified taxonomy that categorizes works by data distribution(Horizontal FL,Vertical FL,Federated Transfer Learning,and Personalized FL),training synchronization(synchronous and asynchronous FL),optimization strategies,and threat models(data leakage and poisoning attacks).In particular,we summarize the latest contributions in Vertical FL frameworks for secure multi-party learning,communication-efficient Horizontal FL,and domain-adaptive Federated Transfer Learning.Furthermore,we examine synchronization techniques addressing system heterogeneity,including straggler mitigation in synchronous FL and staleness management in asynchronous FL.The survey covers security threats in FL,such as gradient inversion,membership inference,and poisoning attacks,as well as their defense strategies that include privacy-preserving aggregation and anomaly detection.The paper concludes by outlining unresolved issues and highlighting challenges in handling personalized models,scalability,and real-world adoption.
基金supported by a grant(No.CRPG-25-2054)under the Cybersecurity Research and Innovation Pioneers Initiative,provided by the National Cybersecurity Authority(NCA)in the Kingdom of Saudi Arabia.
文摘Split Learning(SL)has been promoted as a promising collaborative machine learning technique designed to address data privacy and resource efficiency.Specifically,neural networks are divided into client and server subnetworks in order to mitigate the exposure of sensitive data and reduce the overhead on client devices,thereby making SL particularly suitable for resource-constrained devices.Although SL prevents the direct transmission of raw data,it does not alleviate entirely the risk of privacy breaches.In fact,the data intermediately transmitted to the server sub-model may include patterns or information that could reveal sensitive data.Moreover,achieving a balance between model utility and data privacy has emerged as a challenging problem.In this article,we propose a novel defense approach that combines:(i)Adversarial learning,and(ii)Network channel pruning.In particular,the proposed adversarial learning approach is specifically designed to reduce the risk of private data exposure while maintaining high performance for the utility task.On the other hand,the suggested channel pruning enables the model to adaptively adjust and reactivate pruned channels while conducting adversarial training.The integration of these two techniques reduces the informativeness of the intermediate data transmitted by the client sub-model,thereby enhancing its robustness against attribute inference attacks without adding significant computational overhead,making it wellsuited for IoT devices,mobile platforms,and Internet of Vehicles(IoV)scenarios.The proposed defense approach was evaluated using EfficientNet-B0,a widely adopted compact model,along with three benchmark datasets.The obtained results showcased its superior defense capability against attribute inference attacks compared to existing state-of-the-art methods.This research’s findings demonstrated the effectiveness of the proposed channel pruning-based adversarial training approach in achieving the intended compromise between utility and privacy within SL frameworks.In fact,the classification accuracy attained by the attackers witnessed a drastic decrease of 70%.
文摘Knowledge distillation has become a standard technique for compressing large language models into efficient student models,but existing methods often struggle to balance prediction accuracy with explanation quality.Recent approaches such as Distilling Step-by-Step(DSbS)introduce explanation supervision,yet they apply it in a uniform manner that may not fully exploit the different learning dynamics of prediction and explanation.In this work,we propose a task-structured curriculum learning(TSCL)framework that structures training into three sequential phases:(i)prediction-only,to establish stable feature representations;(ii)joint prediction-explanation,to align task outputs with rationale generation;and(iii)explanation-only,to refine the quality of rationales.This design provides a simple but effective modification to DSbS,requiring no architectural changes and adding negligible training cost.We justify the phase scheduling with ablation studies and convergence analysis,showing that an initial prediction-heavy stage followed by a balanced joint phase improves both stability and explanation alignment.Extensive experiments on five datasets(e-SNLI,ANLI,CommonsenseQA,SVAMP,and MedNLI)demonstrate that TSCL consistently outperforms strong baselines,achieving gains of+1.7-2.6 points in accuracy and 0.8-1.2 in ROUGE-L,corresponding to relative error reductions of up to 21%.Beyond lexical metrics,human evaluation and ERASERstyle faithfulness diagnostics confirm that TSCL produces more faithful and informative explanations.Comparative training curves further reveal faster convergence and lower variance across seeds.Efficiency analysis shows less than 3%overhead in wall-clock training time and no additional inference cost,making the approach practical for realworld deployment.This study demonstrates that a simple task-structured curriculum can significantly improve the effectiveness of knowledge distillation.By separating and sequencing objectives,TSCL achieves a better balance between accuracy,stability,and explanation quality.The framework generalizes across domains,including medical NLI,and offers a principled recipe for future applications in multimodal reasoning and reinforcement learning.
文摘Latest digital advancements have intensified the necessity for adaptive,data-driven and socially-centered learning ecosystems.This paper presents the formulation of a cross-platform,innovative,gamified and personalized Learning Ecosystem,which integrates 3D/VR environments,as well as machine learning algorithms,and business intelligence frameworks to enhance learner-centered education and inferenced decision-making.This Learning System makes use of immersive,analytically assessed virtual learning spaces,therefore facilitating real-time monitoring of not just learning performance,but also overall engagement and behavioral patterns,via a comprehensive set of sustainability-oriented ESG-aligned Key Performance Indicators(KPIs).Machine learning models support predictive analysis,personalized feedback,and hybrid recommendation mechanisms,whilst dedicated dashboards translate complex educational data into actionable insights for all Use Cases of the System(Educational Institutions,Educators and Learners).Additionally,the presented Learning System introduces a structured Mentoring and Consulting Subsystem,thence reinforcing human-centered guidance alongside automated intelligence.The Platform’s modular architecture and simulation-centered evaluation approach actively support personalized,and continuously optimized learning pathways.Thence,it exemplifies a mature,adaptive Learning Ecosystem,supporting immersive technologies,analytics,and pedagogical support,hence,contributing to contemporary digital learning innovation and sociotechnical transformation in education.
文摘Automated grading of dandruff severity is a clinically significant but challenging task due to the inherent ordinal nature of severity levels and the high prevalence of label noise from subjective expert annotations.Standard classification methods fail to address these dual challenges,limiting their real-world performance.In this paper,a novel,three-phase training framework is proposed that learns a robust ordinal classifier directly from noisy labels.The approach synergistically combines a rank-based ordinal regression backbone with a cooperative,semi-supervised learning strategy to dynamically partition the data into clean and noisy subsets.A hybrid training objective is then employed,applying a supervised ordinal loss to the clean set.The noisy set is simultaneously trained using a dualobjective that combines a semi-supervised ordinal loss with a parallel,label-agnostic contrastive loss.This design allows themodel to learn fromthe entire noisy subset while using contrastive learning to mitigate the risk of error propagation frompotentially corrupt supervision.Extensive experiments on a new,large-scale,multi-site clinical dataset validate our approach.Themethod achieves state-of-the-art performance with 80.71%accuracy and a 76.86%F1-score,significantly outperforming existing approaches,including a 2.26%improvement over the strongest baseline method.This work provides not only a robust solution for a practical medical imaging problem but also a generalizable framework for other tasks plagued by noisy ordinal labels.
文摘Adversarial Reinforcement Learning(ARL)models for intelligent devices and Network Intrusion Detection Systems(NIDS)improve systemresilience against sophisticated cyber-attacks.As a core component of ARL,Adversarial Training(AT)enables NIDS agents to discover and prevent newattack paths by exposing them to competing examples,thereby increasing detection accuracy,reducing False Positives(FPs),and enhancing network security.To develop robust decision-making capabilities for real-world network disruptions and hostile activity,NIDS agents are trained in adversarial scenarios to monitor the current state and notify management of any abnormal or malicious activity.The accuracy and timeliness of the IDS were crucial to the network’s availability and reliability at this time.This paper analyzes ARL applications in NIDS,revealing State-of-The-Art(SoTA)methodology,issues,and future research prospects.This includes Reinforcement Machine Learning(RML)-based NIDS,which enables an agent to interact with the environment to achieve a goal,andDeep Reinforcement Learning(DRL)-based NIDS,which can solve complex decision-making problems.Additionally,this survey study addresses cybersecurity adversarial circumstances and their importance for ARL and NIDS.Architectural design,RL algorithms,feature representation,and training methodologies are examined in the ARL-NIDS study.This comprehensive study evaluates ARL for intelligent NIDS research,benefiting cybersecurity researchers,practitioners,and policymakers.The report promotes cybersecurity defense research and innovation.
文摘As urbanization continues to accelerate,the challenges associated with managing transportation in metropolitan areas become increasingly complex.The surge in population density contributes to traffic congestion,impacting travel experiences and posing safety risks.Smart urban transportation management emerges as a strategic solution,conceptualized here as a multidimensional big data problem.The success of this strategy hinges on the effective collection of information from diverse,extensive,and heterogeneous data sources,necessitating the implementation of full⁃stack Information and Communication Technology(ICT)solutions.The main idea of the work is to investigate the current technologies of Intelligent Transportation Systems(ITS)and enhance the safety of urban transportation systems.Machine learning models,trained on historical data,can predict traffic congestion,allowing for the implementation of preventive measures.Deep learning architectures,with their ability to handle complex data representations,further refine traffic predictions,contributing to more accurate and dynamic transportation management.The background of this research underscores the challenges posed by traffic congestion in metropolitan areas and emphasizes the need for advanced technological solutions.By integrating GPS and GIS technologies with machine learning algorithms,this work aims to pay attention to the development of intelligent transportation systems that not only address current challenges but also pave the way for future advancements in urban transportation management.
