Federated semi-supervised learning(FSSL)faces two major challenges:the scarcity of labeled data across clients and the non-independent and identically distributed(Non-IID)nature of data among clients.To address these ...Federated semi-supervised learning(FSSL)faces two major challenges:the scarcity of labeled data across clients and the non-independent and identically distributed(Non-IID)nature of data among clients.To address these issues,we propose diffusion model-based data synthesis aided FSSL(DDSA-FSSL),a novel approach that leverages diffusion model(DM)to generate synthetic data,thereby bridging the gap between heterogeneous local data distributions and the global data distribution.In the proposed DDSA-FSSL,each client addresses the scarcity of labeled data by utilizing a federated learningtrained classifier to perform pseudo labeling for unlabeled data.The DM is then collaboratively trained using both labeled and precision-optimized pseudolabeled data,enabling clients to generate synthetic samples for classes that are absent in their labeled datasets.As a result,the disparity between local and global distributions is reduced and clients can create enriched synthetic datasets that better align with the global data distribution.Extensive experiments on various datasets and Non-IID scenarios demonstrate the effectiveness of DDSA-FSSL,achieving significant performance improvements,such as increasing accuracy from 38.46%to 52.14%on CIFAR-10 datasets with 10%labeled data.展开更多
Accurate prediction of the remaining useful life(RUL)is crucial for the design and management of lithium-ion batteries.Although various machine learning models offer promising predictions,one critical but often overlo...Accurate prediction of the remaining useful life(RUL)is crucial for the design and management of lithium-ion batteries.Although various machine learning models offer promising predictions,one critical but often overlooked challenge is their demand for considerable run-to-failure data for training.Collection of such training data leads to prohibitive testing efforts as the run-to-failure tests can last for years.Here,we propose a semi-supervised representation learning method to enhance prediction accuracy by learning from data without RUL labels.Our approach builds on a sophisticated deep neural network that comprises an encoder and three decoder heads to extract time-dependent representation features from short-term battery operating data regardless of the existence of RUL labels.The approach is validated using three datasets collected from 34 batteries operating under various conditions,encompassing over 19,900 charge and discharge cycles.Our method achieves a root mean squared error(RMSE)within 25 cycles,even when only 1/50 of the training dataset is labelled,representing a reduction of 48%compared to the conventional approach.We also demonstrate the method's robustness with varying numbers of labelled data and different weights assigned to the three decoder heads.The projection of extracted features in low space reveals that our method effectively learns degradation features from unlabelled data.Our approach highlights the promise of utilising semi-supervised learning to reduce the data demand for reliability monitoring of energy devices.展开更多
Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.A challenge is to identify which points to label to bes...Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.A challenge is to identify which points to label to best improve performance while limiting the number of new labels."Model Change"active learning quantifies the resulting change incurred in the classifier by introducing the additional label(s).We pair this idea with graph-based semi-supervised learning(SSL)methods,that use the spectrum of the graph Laplacian matrix,which can be truncated to avoid prohibitively large computational and storage costs.We consider a family of convex loss functions for which the acquisition function can be efficiently approximated using the Laplace approximation of the posterior distribution.We show a variety of multiclass examples that illustrate improved performance over prior state-of-art.展开更多
As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigat...As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigation of degradation mechanisms.However,dynamic operating conditions,cell-to-cell inconsistencies,and limited availability of labeled data have posed significant challenges to accurate and robust prognosis and diagnosis.Herein,we introduce a time-series-decomposition-based ensembled lightweight learning model(TELL-Me),which employs a synergistic dual-module framework to facilitate accurate and reliable forecasting.The feature module formulates features with physical implications and sheds light on battery aging mechanisms,while the gradient module monitors capacity degradation rates and captures aging trend.TELL-Me achieves high accuracy in end-of-life prediction using minimal historical data from a single battery without requiring offline training dataset,and demonstrates impressive generality and robustness across various operating conditions and battery types.Additionally,by correlating feature contributions with degradation mechanisms across different datasets,TELL-Me is endowed with the diagnostic ability that not only enhances prediction reliability but also provides critical insights into the design and optimization of next-generation batteries.展开更多
Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 km.Because they can significantly influence radio communications and navigation systems,...Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 km.Because they can significantly influence radio communications and navigation systems,accurate forecasting of Es layers is crucial for ensuring the precision and dependability of navigation satellite systems.In this study,we present Es predictions made by an empirical model and by a deep learning model,and analyze their differences comprehensively by comparing the model predictions to satellite RO measurements and ground-based ionosonde observations.The deep learning model exhibited significantly better performance,as indicated by its high coefficient of correlation(r=0.87)with RO observations and predictions,than did the empirical model(r=0.53).This study highlights the importance of integrating artificial intelligence technology into ionosphere modelling generally,and into predicting Es layer occurrences and characteristics,in particular.展开更多
BACKGROUND Ischemic heart disease(IHD)impacts the quality of life and has the highest mortality rate of cardiovascular diseases globally.AIM To compare variations in the parameters of the single-lead electrocardiogram...BACKGROUND Ischemic heart disease(IHD)impacts the quality of life and has the highest mortality rate of cardiovascular diseases globally.AIM To compare variations in the parameters of the single-lead electrocardiogram(ECG)during resting conditions and physical exertion in individuals diagnosed with IHD and those without the condition using vasodilator-induced stress computed tomography(CT)myocardial perfusion imaging as the diagnostic reference standard.METHODS This single center observational study included 80 participants.The participants were aged≥40 years and given an informed written consent to participate in the study.Both groups,G1(n=31)with and G2(n=49)without post stress induced myocardial perfusion defect,passed cardiologist consultation,anthropometric measurements,blood pressure and pulse rate measurement,echocardiography,cardio-ankle vascular index,bicycle ergometry,recording 3-min single-lead ECG(Cardio-Qvark)before and just after bicycle ergometry followed by performing CT myocardial perfusion.The LASSO regression with nested cross-validation was used to find the association between Cardio-Qvark parameters and the existence of the perfusion defect.Statistical processing was performed with the R programming language v4.2,Python v.3.10[^R],and Statistica 12 program.RESULTS Bicycle ergometry yielded an area under the receiver operating characteristic curve of 50.7%[95%confidence interval(CI):0.388-0.625],specificity of 53.1%(95%CI:0.392-0.673),and sensitivity of 48.4%(95%CI:0.306-0.657).In contrast,the Cardio-Qvark test performed notably better with an area under the receiver operating characteristic curve of 67%(95%CI:0.530-0.801),specificity of 75.5%(95%CI:0.628-0.88),and sensitivity of 51.6%(95%CI:0.333-0.695).CONCLUSION The single-lead ECG has a relatively higher diagnostic accuracy compared with bicycle ergometry by using machine learning models,but the difference was not statistically significant.However,further investigations are required to uncover the hidden capabilities of single-lead ECG in IHD diagnosis.展开更多
The high porosity and tunable chemical functionality of metal-organic frameworks(MOFs)make it a promising catalyst design platform.High-throughput screening of catalytic performance is feasible since the large MOF str...The high porosity and tunable chemical functionality of metal-organic frameworks(MOFs)make it a promising catalyst design platform.High-throughput screening of catalytic performance is feasible since the large MOF structure database is available.In this study,we report a machine learning model for high-throughput screening of MOF catalysts for the CO_(2) cycloaddition reaction.The descriptors for model training were judiciously chosen according to the reaction mechanism,which leads to high accuracy up to 97%for the 75%quantile of the training set as the classification criterion.The feature contribution was further evaluated with SHAP and PDP analysis to provide a certain physical understanding.12,415 hypothetical MOF structures and 100 reported MOFs were evaluated under 100℃ and 1 bar within one day using the model,and 239 potentially efficient catalysts were discovered.Among them,MOF-76(Y)achieved the top performance experimentally among reported MOFs,in good agreement with the prediction.展开更多
This work proposes the application of an iterative learning model predictive control(ILMPC)approach based on an adaptive fault observer(FOBILMPC)for fault-tolerant control and trajectory tracking in air-breathing hype...This work proposes the application of an iterative learning model predictive control(ILMPC)approach based on an adaptive fault observer(FOBILMPC)for fault-tolerant control and trajectory tracking in air-breathing hypersonic vehicles.In order to increase the control amount,this online control legislation makes use of model predictive control(MPC)that is based on the concept of iterative learning control(ILC).By using offline data to decrease the linearized model’s faults,the strategy may effectively increase the robustness of the control system and guarantee that disturbances can be suppressed.An adaptive fault observer is created based on the suggested ILMPC approach in order to enhance overall fault tolerance by estimating and compensating for actuator disturbance and fault degree.During the derivation process,a linearized model of longitudinal dynamics is established.The suggested ILMPC approach is likely to be used in the design of hypersonic vehicle control systems since numerical simulations have demonstrated that it can decrease tracking error and speed up convergence when compared to the offline controller.展开更多
Ensemble learning,a pivotal branch of machine learning,amalgamates multiple base models to enhance the overarching performance of predictive models,capitalising on the diversity and collective wisdom of the ensemble t...Ensemble learning,a pivotal branch of machine learning,amalgamates multiple base models to enhance the overarching performance of predictive models,capitalising on the diversity and collective wisdom of the ensemble to surpass individual models and mitigate overfitting.In this review,a four-layer research framework is established for the research of ensemble learning,which can offer a comprehensive and structured review of ensemble learning from bottom to top.Firstly,this survey commences by introducing fundamental ensemble learning techniques,including bagging,boosting,and stacking,while also exploring the ensemble's diversity.Then,deep ensemble learning and semi-supervised ensemble learning are studied in detail.Furthermore,the utilisation of ensemble learning techniques to navigate challenging datasets,such as imbalanced and highdimensional data,is discussed.The application of ensemble learning techniques across various research domains,including healthcare,transportation,finance,manufacturing,and the Internet,is also examined.The survey concludes by discussing challenges intrinsic to ensemble learning.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
Heterogeneous federated learning(HtFL)has gained significant attention due to its ability to accommodate diverse models and data from distributed combat units.The prototype-based HtFL methods were proposed to reduce t...Heterogeneous federated learning(HtFL)has gained significant attention due to its ability to accommodate diverse models and data from distributed combat units.The prototype-based HtFL methods were proposed to reduce the high communication cost of transmitting model parameters.These methods allow for the sharing of only class representatives between heterogeneous clients while maintaining privacy.However,existing prototype learning approaches fail to take the data distribution of clients into consideration,which results in suboptimal global prototype learning and insufficient client model personalization capabilities.To address these issues,we propose a fair trainable prototype federated learning(FedFTP)algorithm,which employs a fair sampling training prototype(FSTP)mechanism and a hyperbolic space constraints(HSC)mechanism to enhance the fairness and effectiveness of prototype learning on the server in heterogeneous environments.Furthermore,a local prototype stable update(LPSU)mechanism is proposed as a means of maintaining personalization while promoting global consistency,based on contrastive learning.Comprehensive experimental results demonstrate that FedFTP achieves state-of-the-art performance in HtFL scenarios.展开更多
Geared-rotor systems are critical components in mechanical applications,and their performance can be severely affected by faults,such as profile errors,wear,pitting,spalling,flaking,and cracks.Profile errors in gear t...Geared-rotor systems are critical components in mechanical applications,and their performance can be severely affected by faults,such as profile errors,wear,pitting,spalling,flaking,and cracks.Profile errors in gear teeth are inevitable in manufacturing and subsequently accumulate during operations.This work aims to predict the status of gear profile deviations based on gear dynamics response using the digital model of an experimental rig setup.The digital model comprises detailed CAD models and has been validated against the expected physical behavior using commercial finite element analysis software.The different profile deviations are then modeled using gear charts,and the dynamic response is captured through simulations.The various features are then obtained by signal processing,and various ML models are then evaluated to predict the fault/no-fault condition for the gear.The best performance is achieved by an artificial neural network with a prediction accuracy of 97.5%,which concludes a strong influence on the dynamics of the gear rotor system due to profile deviations.展开更多
Background Cotton is one of the most important commercial crops after food crops,especially in countries like India,where it’s grown extensively under rainfed conditions.Because of its usage in multiple industries,su...Background Cotton is one of the most important commercial crops after food crops,especially in countries like India,where it’s grown extensively under rainfed conditions.Because of its usage in multiple industries,such as textile,medicine,and automobile industries,it has greater commercial importance.The crop’s performance is greatly influenced by prevailing weather dynamics.As climate changes,assessing how weather changes affect crop performance is essential.Among various techniques that are available,crop models are the most effective and widely used tools for predicting yields.Results This study compares statistical and machine learning models to assess their ability to predict cotton yield across major producing districts of Karnataka,India,utilizing a long-term dataset spanning from 1990 to 2023 that includes yield and weather factors.The artificial neural networks(ANNs)performed superiorly with acceptable yield deviations ranging within±10%during both vegetative stage(F1)and mid stage(F2)for cotton.The model evaluation metrics such as root mean square error(RMSE),normalized root mean square error(nRMSE),and modelling efficiency(EF)were also within the acceptance limits in most districts.Furthermore,the tested ANN model was used to assess the importance of the dominant weather factors influencing crop yield in each district.Specifically,the use of morning relative humidity as an individual parameter and its interaction with maximum and minimum tempera-ture had a major influence on cotton yield in most of the yield predicted districts.These differences highlighted the differential interactions of weather factors in each district for cotton yield formation,highlighting individual response of each weather factor under different soils and management conditions over the major cotton growing districts of Karnataka.Conclusions Compared with statistical models,machine learning models such as ANNs proved higher efficiency in forecasting the cotton yield due to their ability to consider the interactive effects of weather factors on yield forma-tion at different growth stages.This highlights the best suitability of ANNs for yield forecasting in rainfed conditions and for the study on relative impacts of weather factors on yield.Thus,the study aims to provide valuable insights to support stakeholders in planning effective crop management strategies and formulating relevant policies.展开更多
Driven by rapid technological advancements and economic growth,mineral extraction and metal refining have increased dramatically,generating huge volumes of tailings and mine waste(TMWs).Investigating the morphological...Driven by rapid technological advancements and economic growth,mineral extraction and metal refining have increased dramatically,generating huge volumes of tailings and mine waste(TMWs).Investigating the morphological fractions of heavy metals and metalloids(HMMs)in TMWs is key to evaluating their leaching potential into the environment;however,traditional experiments are time-consuming and labor-intensive.In this study,10 machine learning(ML)algorithms were used and compared for rapidly predicting the morphological fractions of HMMs in TMWs.A dataset comprising 2376 data points was used,with mineral composition,elemental properties,and total concentration used as inputs and concentration of morphological fraction used as output.After grid search optimization,the extra tree model performed the best,achieving coefficient of determination(R2)of 0.946 and 0.942 on the validation and test sets,respectively.Electronegativity was found to have the greatest impact on the morphological fraction.The models’performance was enhanced by applying an ensemble method to the top three optimal ML models,including gradient boosting decision tree,extra trees and categorical boosting.Overall,the proposed framework can accurately predict the concentrations of different morphological fractions of HMMs in TMWs.This approach can minimize detection time,aid in the safe management and recovery of TMWs.展开更多
Machine learning(ML)techniques have emerged as powerful tools for improving the predictive capabilities of Reynolds-averaged Navier-Stokes(RANS)turbulence models in separated flows.This improvement is achieved by leve...Machine learning(ML)techniques have emerged as powerful tools for improving the predictive capabilities of Reynolds-averaged Navier-Stokes(RANS)turbulence models in separated flows.This improvement is achieved by leveraging complex ML models,such as those developed using field inversion and machine learning(FIML),to dynamically adjust the constants within the baseline RANS model.However,the ML models often overlook the fundamental calibrations of the RANS turbulence model.Consequently,the basic calibration of the baseline RANS model is disrupted,leading to a degradation in the accuracy,particularly in basic wall-attached flows outside of the training set.To address this issue,a modified version of the Spalart-Allmaras(SA)turbulence model,known as Rubber-band SA(RBSA),has been proposed recently.This modification involves identifying and embedding constraints related to basic wall-attached flows directly into the model.It is shown that no matter how the parameters of the RBSA model are adjusted as constants throughout the flow field,its accuracy in wall-attached flows remains unaffected.In this paper,we propose a new constraint for the RBSA model,which better safeguards the law of wall in extreme conditions where the model parameter is adjusted dramatically.The resultant model is called the RBSA-poly model.We then show that when combined with FIML augmentation,the RBSA-poly model effectively preserves the accuracy of simple wall-attached flows,even when the adjusted parameters become functions of local flow variables rather than constants.A comparative analysis with the FIML-augmented original SA model reveals that the augmented RBSA-poly model reduces error in basic wall-attached flows by 50%while maintaining comparable accuracy in trained separated flows.These findings confirm the effectiveness of utilizing FIML in conjunction with the RBSA model,offering superior accuracy retention in cardinal flows.展开更多
Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradi...Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production.Ensemble simulations from such weather models aim to quantify uncertainty in the future development of the weather,and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions.However,ensemble prediction systems are known to exhibit systematic errors,and thus require post-processing to obtain accurate and reliable probabilistic forecasts.The overarching aim of our study is to systematically evaluate different strategies to apply post-processing in model chain approaches with a specific focus on solar energy:not applying any post-processing at all;post-processing only the irradiance predictions before the conversion;post-processing only the solar power predictions obtained from the model chain;or applying post-processing in both steps.In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S.,we develop statistical and machine learning methods for postprocessing ensemble predictions of global horizontal irradiance(GHI)and solar power generation.Further,we propose a neural-network-based model for direct solar power forecasting that bypasses the model chain.Our results indicate that postprocessing substantially improves the solar power generation forecasts,in particular when post-processing is applied to the power predictions.The machine learning methods for post-processing slightly outperform the statistical methods,and the direct forecasting approach performs comparably to the post-processing strategies.展开更多
This paper aims to provide a window opportunity to share a reflection and learning from different countries and from other disciplines with the focus on resilience.There is also an attempt to theorize the concept of l...This paper aims to provide a window opportunity to share a reflection and learning from different countries and from other disciplines with the focus on resilience.There is also an attempt to theorize the concept of learning from spurious success and failure in the context of COVID-19.The main emphasis is to provide understanding of the causal factors and the identification of improved measures and modelling approaches to prevent and mitigate against future pandemics.Proposed decision tools of resilience and bowtie modelling as enablers for decision makers to prevent hazards and protect against their consequences.展开更多
Objective:To analyze the risk factors of anxiety in young hypertensive patients and build a prediction model to provide a scientific basis for clinical diagnosis and treatment.Methods:According to the research content...Objective:To analyze the risk factors of anxiety in young hypertensive patients and build a prediction model to provide a scientific basis for clinical diagnosis and treatment.Methods:According to the research content,young hypertensive patients admitted to the hospital from January 2022 to December 2024 were selected as the research object and at least 950 patients were included according to the sample size calculation.According to the existence of anxiety,950 patients were divided into control group(n=650)and observation group(n=300),and the clinical data of all patients were collected for univariate analysis and multivariate Logistic regression analysis to get the risk factors of hypertension patients complicated with anxiety in.All patients were randomly divided into a training set(n=665)and a test set(n=285)according to the ratio of 7:3,and the evaluation efficiency of different prediction models was obtained by using machine learning algorithm.To evaluate the clinical application effect of the prediction model.Results:(1)Univariate analysis showed that age,BMI,education background,marital status,smoking,drinking,sleep disorder,family history of hypertension,history of diabetes,history of hyperlipidemia,history of cerebral infarction,and TC were important risk factors for young hypertensive patients complicated with anxiety.(2)Multivariate Logistic regression analysis showed that hypertension history,drinking history,coronary heart disease history,diabetes history,BMI,TC,and TG are important independent risk factors for young hypertensive patients complicated with anxiety.(3)Extra Trees has the highest predictive power for young people with hypertension complicated with anxiety,while Decision-Tree has the lowest predictive power.Conclusion:Hypertension history,drinking history,coronary heart disease history,diabetes history,BMI,TC,and TG are important independent risk factors that affect the anxiety of young hypertensive patients.Extra Trees model has the best prediction efficiency among different groups of models.展开更多
This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curric...This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curricula,it elucidates its advantages and operational mechanisms in interdisciplinary PBL.Combining case studies and empirical research,the investigation proposes implementation pathways and strategies for the generative AI-enhanced interdisciplinary PBL model,detailing specific applications across three phases:project preparation,implementation,and evaluation.The research demonstrates that generative AI-enabled interdisciplinary project-based learning can effectively enhance students’learning motivation,interdisciplinary thinking capabilities,and innovative competencies,providing new conceptual frameworks and practical approaches for educational model innovation.展开更多
基金supported in part by NSF of China under Grant 62222111 and Grant 62431015in part by the Science and Technology Commission Foundation of Shanghai under Grant 24DP1500702.
文摘Federated semi-supervised learning(FSSL)faces two major challenges:the scarcity of labeled data across clients and the non-independent and identically distributed(Non-IID)nature of data among clients.To address these issues,we propose diffusion model-based data synthesis aided FSSL(DDSA-FSSL),a novel approach that leverages diffusion model(DM)to generate synthetic data,thereby bridging the gap between heterogeneous local data distributions and the global data distribution.In the proposed DDSA-FSSL,each client addresses the scarcity of labeled data by utilizing a federated learningtrained classifier to perform pseudo labeling for unlabeled data.The DM is then collaboratively trained using both labeled and precision-optimized pseudolabeled data,enabling clients to generate synthetic samples for classes that are absent in their labeled datasets.As a result,the disparity between local and global distributions is reduced and clients can create enriched synthetic datasets that better align with the global data distribution.Extensive experiments on various datasets and Non-IID scenarios demonstrate the effectiveness of DDSA-FSSL,achieving significant performance improvements,such as increasing accuracy from 38.46%to 52.14%on CIFAR-10 datasets with 10%labeled data.
基金supported by the National Natural Science Foundation of China(No.52207229)the Key Research and Development Program of Ningxia Hui Autonomous Region of China(No.2024BEE02003)+1 种基金the financial support from the AEGiS Research Grant 2024,University of Wollongong(No.R6254)the financial support from the China Scholarship Council(No.202207550010).
文摘Accurate prediction of the remaining useful life(RUL)is crucial for the design and management of lithium-ion batteries.Although various machine learning models offer promising predictions,one critical but often overlooked challenge is their demand for considerable run-to-failure data for training.Collection of such training data leads to prohibitive testing efforts as the run-to-failure tests can last for years.Here,we propose a semi-supervised representation learning method to enhance prediction accuracy by learning from data without RUL labels.Our approach builds on a sophisticated deep neural network that comprises an encoder and three decoder heads to extract time-dependent representation features from short-term battery operating data regardless of the existence of RUL labels.The approach is validated using three datasets collected from 34 batteries operating under various conditions,encompassing over 19,900 charge and discharge cycles.Our method achieves a root mean squared error(RMSE)within 25 cycles,even when only 1/50 of the training dataset is labelled,representing a reduction of 48%compared to the conventional approach.We also demonstrate the method's robustness with varying numbers of labelled data and different weights assigned to the three decoder heads.The projection of extracted features in low space reveals that our method effectively learns degradation features from unlabelled data.Our approach highlights the promise of utilising semi-supervised learning to reduce the data demand for reliability monitoring of energy devices.
基金supported by the DOD National Defense Science and Engineering Graduate(NDSEG)Research Fellowshipsupported by the NGA under Contract No.HM04762110003.
文摘Active learning in semi-supervised classification involves introducing additional labels for unlabelled data to improve the accuracy of the underlying classifier.A challenge is to identify which points to label to best improve performance while limiting the number of new labels."Model Change"active learning quantifies the resulting change incurred in the classifier by introducing the additional label(s).We pair this idea with graph-based semi-supervised learning(SSL)methods,that use the spectrum of the graph Laplacian matrix,which can be truncated to avoid prohibitively large computational and storage costs.We consider a family of convex loss functions for which the acquisition function can be efficiently approximated using the Laplace approximation of the posterior distribution.We show a variety of multiclass examples that illustrate improved performance over prior state-of-art.
基金supported by the National Natural Science Foundation of China(22379021 and 22479021)。
文摘As batteries become increasingly essential for energy storage technologies,battery prognosis,and diagnosis remain central to ensure reliable operation and effective management,as well as to aid the in-depth investigation of degradation mechanisms.However,dynamic operating conditions,cell-to-cell inconsistencies,and limited availability of labeled data have posed significant challenges to accurate and robust prognosis and diagnosis.Herein,we introduce a time-series-decomposition-based ensembled lightweight learning model(TELL-Me),which employs a synergistic dual-module framework to facilitate accurate and reliable forecasting.The feature module formulates features with physical implications and sheds light on battery aging mechanisms,while the gradient module monitors capacity degradation rates and captures aging trend.TELL-Me achieves high accuracy in end-of-life prediction using minimal historical data from a single battery without requiring offline training dataset,and demonstrates impressive generality and robustness across various operating conditions and battery types.Additionally,by correlating feature contributions with degradation mechanisms across different datasets,TELL-Me is endowed with the diagnostic ability that not only enhances prediction reliability but also provides critical insights into the design and optimization of next-generation batteries.
基金supported by the Project of Stable Support for Youth Team in Basic Research Field,CAS(grant No.YSBR-018)the National Natural Science Foundation of China(grant Nos.42188101,42130204)+4 种基金the B-type Strategic Priority Program of CAS(grant no.XDB41000000)the National Natural Science Foundation of China(NSFC)Distinguished Overseas Young Talents Program,Innovation Program for Quantum Science and Technology(2021ZD0300301)the Open Research Project of Large Research Infrastructures of CAS-“Study on the interaction between low/mid-latitude atmosphere and ionosphere based on the Chinese Meridian Project”.The project was supported also by the National Key Laboratory of Deep Space Exploration(Grant No.NKLDSE2023A002)the Open Fund of Anhui Provincial Key Laboratory of Intelligent Underground Detection(Grant No.APKLIUD23KF01)the China National Space Administration(CNSA)pre-research Project on Civil Aerospace Technologies No.D010305,D010301.
文摘Sporadic E(Es)layers in the ionosphere are characterized by intense plasma irregularities in the E region at altitudes of 90-130 km.Because they can significantly influence radio communications and navigation systems,accurate forecasting of Es layers is crucial for ensuring the precision and dependability of navigation satellite systems.In this study,we present Es predictions made by an empirical model and by a deep learning model,and analyze their differences comprehensively by comparing the model predictions to satellite RO measurements and ground-based ionosonde observations.The deep learning model exhibited significantly better performance,as indicated by its high coefficient of correlation(r=0.87)with RO observations and predictions,than did the empirical model(r=0.53).This study highlights the importance of integrating artificial intelligence technology into ionosphere modelling generally,and into predicting Es layer occurrences and characteristics,in particular.
基金Supported by Government Assignment,No.1023022600020-6RSF Grant,No.24-15-00549Ministry of Science and Higher Education of the Russian Federation within the Framework of State Support for the Creation and Development of World-Class Research Center,No.075-15-2022-304.
文摘BACKGROUND Ischemic heart disease(IHD)impacts the quality of life and has the highest mortality rate of cardiovascular diseases globally.AIM To compare variations in the parameters of the single-lead electrocardiogram(ECG)during resting conditions and physical exertion in individuals diagnosed with IHD and those without the condition using vasodilator-induced stress computed tomography(CT)myocardial perfusion imaging as the diagnostic reference standard.METHODS This single center observational study included 80 participants.The participants were aged≥40 years and given an informed written consent to participate in the study.Both groups,G1(n=31)with and G2(n=49)without post stress induced myocardial perfusion defect,passed cardiologist consultation,anthropometric measurements,blood pressure and pulse rate measurement,echocardiography,cardio-ankle vascular index,bicycle ergometry,recording 3-min single-lead ECG(Cardio-Qvark)before and just after bicycle ergometry followed by performing CT myocardial perfusion.The LASSO regression with nested cross-validation was used to find the association between Cardio-Qvark parameters and the existence of the perfusion defect.Statistical processing was performed with the R programming language v4.2,Python v.3.10[^R],and Statistica 12 program.RESULTS Bicycle ergometry yielded an area under the receiver operating characteristic curve of 50.7%[95%confidence interval(CI):0.388-0.625],specificity of 53.1%(95%CI:0.392-0.673),and sensitivity of 48.4%(95%CI:0.306-0.657).In contrast,the Cardio-Qvark test performed notably better with an area under the receiver operating characteristic curve of 67%(95%CI:0.530-0.801),specificity of 75.5%(95%CI:0.628-0.88),and sensitivity of 51.6%(95%CI:0.333-0.695).CONCLUSION The single-lead ECG has a relatively higher diagnostic accuracy compared with bicycle ergometry by using machine learning models,but the difference was not statistically significant.However,further investigations are required to uncover the hidden capabilities of single-lead ECG in IHD diagnosis.
基金financial support from the National Key Research and Development Program of China(2021YFB 3501501)the National Natural Science Foundation of China(No.22225803,22038001,22108007 and 22278011)+1 种基金Beijing Natural Science Foundation(No.Z230023)Beijing Science and Technology Commission(No.Z211100004321001).
文摘The high porosity and tunable chemical functionality of metal-organic frameworks(MOFs)make it a promising catalyst design platform.High-throughput screening of catalytic performance is feasible since the large MOF structure database is available.In this study,we report a machine learning model for high-throughput screening of MOF catalysts for the CO_(2) cycloaddition reaction.The descriptors for model training were judiciously chosen according to the reaction mechanism,which leads to high accuracy up to 97%for the 75%quantile of the training set as the classification criterion.The feature contribution was further evaluated with SHAP and PDP analysis to provide a certain physical understanding.12,415 hypothetical MOF structures and 100 reported MOFs were evaluated under 100℃ and 1 bar within one day using the model,and 239 potentially efficient catalysts were discovered.Among them,MOF-76(Y)achieved the top performance experimentally among reported MOFs,in good agreement with the prediction.
基金supported by the National Natural Science Foundation of China(12072090).
文摘This work proposes the application of an iterative learning model predictive control(ILMPC)approach based on an adaptive fault observer(FOBILMPC)for fault-tolerant control and trajectory tracking in air-breathing hypersonic vehicles.In order to increase the control amount,this online control legislation makes use of model predictive control(MPC)that is based on the concept of iterative learning control(ILC).By using offline data to decrease the linearized model’s faults,the strategy may effectively increase the robustness of the control system and guarantee that disturbances can be suppressed.An adaptive fault observer is created based on the suggested ILMPC approach in order to enhance overall fault tolerance by estimating and compensating for actuator disturbance and fault degree.During the derivation process,a linearized model of longitudinal dynamics is established.The suggested ILMPC approach is likely to be used in the design of hypersonic vehicle control systems since numerical simulations have demonstrated that it can decrease tracking error and speed up convergence when compared to the offline controller.
基金supported in part by National Natural Science Foundation of China No.92467109,U21A20478National Key R&D Program of China 2023YFA1011601the Major Key Project of PCL(Grant PCL2024A05).
文摘Ensemble learning,a pivotal branch of machine learning,amalgamates multiple base models to enhance the overarching performance of predictive models,capitalising on the diversity and collective wisdom of the ensemble to surpass individual models and mitigate overfitting.In this review,a four-layer research framework is established for the research of ensemble learning,which can offer a comprehensive and structured review of ensemble learning from bottom to top.Firstly,this survey commences by introducing fundamental ensemble learning techniques,including bagging,boosting,and stacking,while also exploring the ensemble's diversity.Then,deep ensemble learning and semi-supervised ensemble learning are studied in detail.Furthermore,the utilisation of ensemble learning techniques to navigate challenging datasets,such as imbalanced and highdimensional data,is discussed.The application of ensemble learning techniques across various research domains,including healthcare,transportation,finance,manufacturing,and the Internet,is also examined.The survey concludes by discussing challenges intrinsic to ensemble learning.
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.
基金supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region(No.2022D01B187).
文摘Heterogeneous federated learning(HtFL)has gained significant attention due to its ability to accommodate diverse models and data from distributed combat units.The prototype-based HtFL methods were proposed to reduce the high communication cost of transmitting model parameters.These methods allow for the sharing of only class representatives between heterogeneous clients while maintaining privacy.However,existing prototype learning approaches fail to take the data distribution of clients into consideration,which results in suboptimal global prototype learning and insufficient client model personalization capabilities.To address these issues,we propose a fair trainable prototype federated learning(FedFTP)algorithm,which employs a fair sampling training prototype(FSTP)mechanism and a hyperbolic space constraints(HSC)mechanism to enhance the fairness and effectiveness of prototype learning on the server in heterogeneous environments.Furthermore,a local prototype stable update(LPSU)mechanism is proposed as a means of maintaining personalization while promoting global consistency,based on contrastive learning.Comprehensive experimental results demonstrate that FedFTP achieves state-of-the-art performance in HtFL scenarios.
文摘Geared-rotor systems are critical components in mechanical applications,and their performance can be severely affected by faults,such as profile errors,wear,pitting,spalling,flaking,and cracks.Profile errors in gear teeth are inevitable in manufacturing and subsequently accumulate during operations.This work aims to predict the status of gear profile deviations based on gear dynamics response using the digital model of an experimental rig setup.The digital model comprises detailed CAD models and has been validated against the expected physical behavior using commercial finite element analysis software.The different profile deviations are then modeled using gear charts,and the dynamic response is captured through simulations.The various features are then obtained by signal processing,and various ML models are then evaluated to predict the fault/no-fault condition for the gear.The best performance is achieved by an artificial neural network with a prediction accuracy of 97.5%,which concludes a strong influence on the dynamics of the gear rotor system due to profile deviations.
基金funded through India Meteorological Department,New Delhi,India under the Forecasting Agricultural output using Space,Agrometeorol ogy and Land based observations(FASAL)project and fund number:No.ASC/FASAL/KT-11/01/HQ-2010.
文摘Background Cotton is one of the most important commercial crops after food crops,especially in countries like India,where it’s grown extensively under rainfed conditions.Because of its usage in multiple industries,such as textile,medicine,and automobile industries,it has greater commercial importance.The crop’s performance is greatly influenced by prevailing weather dynamics.As climate changes,assessing how weather changes affect crop performance is essential.Among various techniques that are available,crop models are the most effective and widely used tools for predicting yields.Results This study compares statistical and machine learning models to assess their ability to predict cotton yield across major producing districts of Karnataka,India,utilizing a long-term dataset spanning from 1990 to 2023 that includes yield and weather factors.The artificial neural networks(ANNs)performed superiorly with acceptable yield deviations ranging within±10%during both vegetative stage(F1)and mid stage(F2)for cotton.The model evaluation metrics such as root mean square error(RMSE),normalized root mean square error(nRMSE),and modelling efficiency(EF)were also within the acceptance limits in most districts.Furthermore,the tested ANN model was used to assess the importance of the dominant weather factors influencing crop yield in each district.Specifically,the use of morning relative humidity as an individual parameter and its interaction with maximum and minimum tempera-ture had a major influence on cotton yield in most of the yield predicted districts.These differences highlighted the differential interactions of weather factors in each district for cotton yield formation,highlighting individual response of each weather factor under different soils and management conditions over the major cotton growing districts of Karnataka.Conclusions Compared with statistical models,machine learning models such as ANNs proved higher efficiency in forecasting the cotton yield due to their ability to consider the interactive effects of weather factors on yield forma-tion at different growth stages.This highlights the best suitability of ANNs for yield forecasting in rainfed conditions and for the study on relative impacts of weather factors on yield.Thus,the study aims to provide valuable insights to support stakeholders in planning effective crop management strategies and formulating relevant policies.
基金Project(2024JJ2074) supported by the Natural Science Foundation of Hunan Province,ChinaProject(22376221) supported by the National Natural Science Foundation of ChinaProject(2023QNRC001) supported by the Young Elite Scientists Sponsorship Program by CAST,China。
文摘Driven by rapid technological advancements and economic growth,mineral extraction and metal refining have increased dramatically,generating huge volumes of tailings and mine waste(TMWs).Investigating the morphological fractions of heavy metals and metalloids(HMMs)in TMWs is key to evaluating their leaching potential into the environment;however,traditional experiments are time-consuming and labor-intensive.In this study,10 machine learning(ML)algorithms were used and compared for rapidly predicting the morphological fractions of HMMs in TMWs.A dataset comprising 2376 data points was used,with mineral composition,elemental properties,and total concentration used as inputs and concentration of morphological fraction used as output.After grid search optimization,the extra tree model performed the best,achieving coefficient of determination(R2)of 0.946 and 0.942 on the validation and test sets,respectively.Electronegativity was found to have the greatest impact on the morphological fraction.The models’performance was enhanced by applying an ensemble method to the top three optimal ML models,including gradient boosting decision tree,extra trees and categorical boosting.Overall,the proposed framework can accurately predict the concentrations of different morphological fractions of HMMs in TMWs.This approach can minimize detection time,aid in the safe management and recovery of TMWs.
基金supported by the National Natural Science Foundation of China(Grant Nos.12388101,12372288,U23A2069,and 92152301).
文摘Machine learning(ML)techniques have emerged as powerful tools for improving the predictive capabilities of Reynolds-averaged Navier-Stokes(RANS)turbulence models in separated flows.This improvement is achieved by leveraging complex ML models,such as those developed using field inversion and machine learning(FIML),to dynamically adjust the constants within the baseline RANS model.However,the ML models often overlook the fundamental calibrations of the RANS turbulence model.Consequently,the basic calibration of the baseline RANS model is disrupted,leading to a degradation in the accuracy,particularly in basic wall-attached flows outside of the training set.To address this issue,a modified version of the Spalart-Allmaras(SA)turbulence model,known as Rubber-band SA(RBSA),has been proposed recently.This modification involves identifying and embedding constraints related to basic wall-attached flows directly into the model.It is shown that no matter how the parameters of the RBSA model are adjusted as constants throughout the flow field,its accuracy in wall-attached flows remains unaffected.In this paper,we propose a new constraint for the RBSA model,which better safeguards the law of wall in extreme conditions where the model parameter is adjusted dramatically.The resultant model is called the RBSA-poly model.We then show that when combined with FIML augmentation,the RBSA-poly model effectively preserves the accuracy of simple wall-attached flows,even when the adjusted parameters become functions of local flow variables rather than constants.A comparative analysis with the FIML-augmented original SA model reveals that the augmented RBSA-poly model reduces error in basic wall-attached flows by 50%while maintaining comparable accuracy in trained separated flows.These findings confirm the effectiveness of utilizing FIML in conjunction with the RBSA model,offering superior accuracy retention in cardinal flows.
基金the Young Investigator Group“Artificial Intelligence for Probabilistic Weather Forecasting”funded by the Vector Stiftungfunding from the Federal Ministry of Education and Research(BMBF)and the Baden-Württemberg Ministry of Science as part of the Excellence Strategy of the German Federal and State Governments。
文摘Weather forecasts from numerical weather prediction models play a central role in solar energy forecasting,where a cascade of physics-based models is used in a model chain approach to convert forecasts of solar irradiance to solar power production.Ensemble simulations from such weather models aim to quantify uncertainty in the future development of the weather,and can be used to propagate this uncertainty through the model chain to generate probabilistic solar energy predictions.However,ensemble prediction systems are known to exhibit systematic errors,and thus require post-processing to obtain accurate and reliable probabilistic forecasts.The overarching aim of our study is to systematically evaluate different strategies to apply post-processing in model chain approaches with a specific focus on solar energy:not applying any post-processing at all;post-processing only the irradiance predictions before the conversion;post-processing only the solar power predictions obtained from the model chain;or applying post-processing in both steps.In a case study based on a benchmark dataset for the Jacumba solar plant in the U.S.,we develop statistical and machine learning methods for postprocessing ensemble predictions of global horizontal irradiance(GHI)and solar power generation.Further,we propose a neural-network-based model for direct solar power forecasting that bypasses the model chain.Our results indicate that postprocessing substantially improves the solar power generation forecasts,in particular when post-processing is applied to the power predictions.The machine learning methods for post-processing slightly outperform the statistical methods,and the direct forecasting approach performs comparably to the post-processing strategies.
基金supported by the project“Societal and Economic Resilience within multi-hazards environment in Romania”funded by European Union-Next generation EU and Romanian Government,under National Recovery and Resilience Plan for Romania,contract no.760050/23.05.2023,cod PNRR-C9-I8-CF 267/29.11.2022through the Romanian Ministry of Research,Innovation and Digitalization,within Component 9,Investment I8.
文摘This paper aims to provide a window opportunity to share a reflection and learning from different countries and from other disciplines with the focus on resilience.There is also an attempt to theorize the concept of learning from spurious success and failure in the context of COVID-19.The main emphasis is to provide understanding of the causal factors and the identification of improved measures and modelling approaches to prevent and mitigate against future pandemics.Proposed decision tools of resilience and bowtie modelling as enablers for decision makers to prevent hazards and protect against their consequences.
文摘Objective:To analyze the risk factors of anxiety in young hypertensive patients and build a prediction model to provide a scientific basis for clinical diagnosis and treatment.Methods:According to the research content,young hypertensive patients admitted to the hospital from January 2022 to December 2024 were selected as the research object and at least 950 patients were included according to the sample size calculation.According to the existence of anxiety,950 patients were divided into control group(n=650)and observation group(n=300),and the clinical data of all patients were collected for univariate analysis and multivariate Logistic regression analysis to get the risk factors of hypertension patients complicated with anxiety in.All patients were randomly divided into a training set(n=665)and a test set(n=285)according to the ratio of 7:3,and the evaluation efficiency of different prediction models was obtained by using machine learning algorithm.To evaluate the clinical application effect of the prediction model.Results:(1)Univariate analysis showed that age,BMI,education background,marital status,smoking,drinking,sleep disorder,family history of hypertension,history of diabetes,history of hyperlipidemia,history of cerebral infarction,and TC were important risk factors for young hypertensive patients complicated with anxiety.(2)Multivariate Logistic regression analysis showed that hypertension history,drinking history,coronary heart disease history,diabetes history,BMI,TC,and TG are important independent risk factors for young hypertensive patients complicated with anxiety.(3)Extra Trees has the highest predictive power for young people with hypertension complicated with anxiety,while Decision-Tree has the lowest predictive power.Conclusion:Hypertension history,drinking history,coronary heart disease history,diabetes history,BMI,TC,and TG are important independent risk factors that affect the anxiety of young hypertensive patients.Extra Trees model has the best prediction efficiency among different groups of models.
文摘This study explores a novel educational model of generative AI-empowered interdisciplinary project-based learning(PBL).By analyzing the current applications of generative AI technology in information technology curricula,it elucidates its advantages and operational mechanisms in interdisciplinary PBL.Combining case studies and empirical research,the investigation proposes implementation pathways and strategies for the generative AI-enhanced interdisciplinary PBL model,detailing specific applications across three phases:project preparation,implementation,and evaluation.The research demonstrates that generative AI-enabled interdisciplinary project-based learning can effectively enhance students’learning motivation,interdisciplinary thinking capabilities,and innovative competencies,providing new conceptual frameworks and practical approaches for educational model innovation.
