Surface-supported clusters forming by aggregation of excessive adatoms could be the main defects of 2D materials after chemical vapor deposition.They will significantly impact the electronic/magnetic properties.Moreov...Surface-supported clusters forming by aggregation of excessive adatoms could be the main defects of 2D materials after chemical vapor deposition.They will significantly impact the electronic/magnetic properties.Moreover,surface supported atoms are also widely explored for high active and selecting catalysts.Severe deformation,even dipping into the surface,of these clusters can be expected because of the very active edge of clusters and strong interaction between supported clusters and surfaces.However,most models of these clusters are supposed to simply float on the top of the surface because ab initio simulations cannot afford the complex reconstructions.Here,we develop an accurate graph neural network machine learning potential(MLP)from ab initio data by active learning architecture through fine-tuning pre-trained models,and then employ the MLP into Monte Carlo to explore the structural evolutions of Mo and S clusters(1-8 atoms)on perfect and various defective MoS2 monolayers.Interestingly,Mo clusters can always sink and embed themselves into MoS2 layers.In contrast,S clusters float on perfect surfaces.On the defective surface,a few S atoms will fill the vacancy and rest S clusters float on the top.Such significant structural reconstructions should be carefully taken into account.展开更多
In materials science,a significant correlation often exists between material input parameters and their corresponding performance attributes.Nevertheless,the inherent challenges associated with small data obscure thes...In materials science,a significant correlation often exists between material input parameters and their corresponding performance attributes.Nevertheless,the inherent challenges associated with small data obscure these statistical correlations,impeding machine learning models from effectively capturing the underlying patterns,thereby hampering efficient optimization of material properties.This work presents a novel active learning framework that integrates generative adversarial networks(GAN)with a directionally constrained expected absolute improvement(EAI)acquisition function to accelerate the discovery of ultra-high temperature ceramics(UHTCs)using small data.The framework employs GAN for data augmentation,symbolic regression for feature weight derivation,and a self-developed EAI function that incorporates input feature importance weighting to quantify bidirectional deviations from zero ablation rate.Through only two iterations,this framework successfully identified the optimal composition of HfB_(2)-3.52SiC-5.23TaSi_(2),which exhibits robust near-zero ablation rates under plasma ablation at 2500℃ for 200 s,demonstrating superior sampling efficiency compared to conventional active learning approaches.Microstructural analysis reveals that the exceptional performance stems from the formation of a highly viscous HfO_(2)-SiO_(2)-Ta_(2)O_(5)-HfSiO_(4)-Hf_(3)(BO_(3))_(4) oxide layer,which provides effective oxygen barrier protection.This work demonstrates an efficient and universal approach for rapid materials discovery using small data.展开更多
Dynamical systems often exhibit multiple attractors representing significantly different functioning conditions.A global map of attraction basins can offer valuable guidance for stabilizing or transitioning system sta...Dynamical systems often exhibit multiple attractors representing significantly different functioning conditions.A global map of attraction basins can offer valuable guidance for stabilizing or transitioning system states.Such a map can be constructed without prior system knowledge by identifying attractors across a sufficient number of points in the state space.However,determining the attractor for each initial state can be a laborious task.Here,we tackle the challenge of reconstructing attraction basins using as few initial points as possible.In each iteration of our approach,informative points are selected through random seeding and are driven along the current classification boundary,promoting the eventual selection of points that are both diverse and enlightening.The results across various experimental dynamical systems demonstrate that our approach requires fewer points than baseline methods while achieving comparable mapping accuracy.Additionally,the reconstructed map allows us to accurately estimate the minimum escape distance required to transition the system state to a target basin.展开更多
Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computation...Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.展开更多
To capture the nonlinear dynamics and gain evolution in chirped pulse amplification(CPA)systems,the split-step Fourier method and the fourth-order Runge–Kutta method are integrated to iteratively address the generali...To capture the nonlinear dynamics and gain evolution in chirped pulse amplification(CPA)systems,the split-step Fourier method and the fourth-order Runge–Kutta method are integrated to iteratively address the generalized nonlinear Schrödinger equation and the rate equations.However,this approach is burdened by substantial computational demands,resulting in significant time expenditures.In the context of intelligent laser optimization and inverse design,the necessity for numerous simulations further exacerbates this issue,highlighting the need for fast and accurate simulation methodologies.Here,we introduce an end-to-end model augmented with active learning(E2E-AL)with decent generalization through different dedicated embedding methods over various parameters.On an identical computational platform,the artificial intelligence–driven model is 2000 times faster than the conventional simulation method.Benefiting from the active learning strategy,the E2E-AL model achieves decent precision with only two-thirds of the training samples compared with the case without such a strategy.Furthermore,we demonstrate a multi-objective inverse design of the CPA systems enabled by the E2E-AL model.The E2E-AL framework manifests the potential of becoming a standard approach for the rapid and accurate modeling of ultrafast lasers and is readily extended to simulate other complex systems.展开更多
The Reliability-Based Design Optimization(RBDO)of complex engineering structures considering uncertainties has problems of being high-dimensional,highly nonlinear,and timeconsuming,which requires a significant amount ...The Reliability-Based Design Optimization(RBDO)of complex engineering structures considering uncertainties has problems of being high-dimensional,highly nonlinear,and timeconsuming,which requires a significant amount of sampling simulation computation.In this paper,a basis-adaptive Polynomial Chaos(PC)-Kriging surrogate model is proposed,in order to relieve the computational burden and enhance the predictive accuracy of a metamodel.The active learning basis-adaptive PC-Kriging model is combined with a quantile-based RBDO framework.Finally,five engineering cases have been implemented,including a benchmark RBDO problem,three high-dimensional explicit problems,and a high-dimensional implicit problem.Compared with Support Vector Regression(SVR),Kriging,and polynomial chaos expansion models,results show that the proposed basis-adaptive PC-Kriging model is more accurate and efficient for RBDO problems of complex engineering structures.展开更多
One-step direct production of methanol from methane and water(PMMW)under mild conditions is challenging in heterogeneous catalysis owing to the absence of highly effective catalysts.Herein,we designed a series of“Sin...One-step direct production of methanol from methane and water(PMMW)under mild conditions is challenging in heterogeneous catalysis owing to the absence of highly effective catalysts.Herein,we designed a series of“Single-Atom”-“Frustrated Lewis Pair”(SA-FLP)dual active sites for the direct PMMW via density functional theory(DFT)calculations combined with a machine learning(ML)approach.The results indicate that the nine designed SA-FLP catalysts are capable of efficiently activate CH4 and H_(2)O and facilitate the coupling of OH^(*)and CH_(3)^(*)into methanol.The DFT-based microkinetic simulation(MKM)results indicate that CH_(3)OH production on Co1-FLP and Pt1-FLP catalysts can reach the turnover frequencies(TOFs)of 1.01×10^(−3)s^(-1)and 8.80×10^(−4)s^(-1),respectively,which exceed the experimentally reported values by three orders of magnitude.ML results unveil that the gradient boosted regression model with 13 simple features could give satisfactory predictions for the TOFs of CH_(3)OH production with RMSE and R^(2)of 0.009 s^(-1)and 1.00,respectively.The ML-predicted MKM results indicate that four catalysts including V_(1-),Fe_(1-),Ti_(1-),and Mn_(1)-FLP exhibit higher TOFs of CH_(3)OH production than the value that the most relevant experiments reported,indicating that the four catalysts are also promising catalysts for the PMMW.This study not only develops a simple and efficient approach for design and screening SA-FLP catalysts but also provides mechanistic insights into the direct PMMW.展开更多
Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),...Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),comprising an initialization followed by subsequent learning,selects a small subset of informative data points for labeling.Recent advancements in pretrained models by supervised or self-supervised learning tailored to chest radiograph have shown broad applicability to diverse downstream tasks.However,their potential in cold-start AL remains unexplored.Methods:To validate the efficacy of domain-specific pretraining,we compared two foundation models:supervised TXRV and self-supervised REMEDIS with their general domain counterparts pretrained on ImageNet.Model performance was evaluated at both initialization and subsequent learning stages on two diagnostic tasks:psychiatric pneumonia and COVID-19.For initialization,we assessed their integration with three strategies:diversity,uncertainty,and hybrid sampling.For subsequent learning,we focused on uncertainty sampling powered by different pretrained models.We also conducted statistical tests to compare the foundation models with ImageNet counterparts,investigate the relationship between initialization and subsequent learning,examine the performance of one-shot initialization against the full AL process,and investigate the influence of class balance in initialization samples on initialization and subsequent learning.Results:First,domain-specific foundation models failed to outperform ImageNet counterparts in six out of eight experiments on informative sample selection.Both domain-specific and general pretrained models were unable to generate representations that could substitute for the original images as model inputs in seven of the eight scenarios.However,pretrained model-based initialization surpassed random sampling,the default approach in cold-start AL.Second,initialization performance was positively correlated with subsequent learning performance,highlighting the importance of initialization strategies.Third,one-shot initialization performed comparably to the full AL process,demonstrating the potential of reducing experts'repeated waiting during AL iterations.Last,a U-shaped correlation was observed between the class balance of initialization samples and model performance,suggesting that the class balance is more strongly associated with performance at middle budget levels than at low or high budgets.Conclusions:In this study,we highlighted the limitations of medical pretraining compared to general pretraining in the context of cold-start AL.We also identified promising outcomes related to cold-start AL,including initialization based on pretrained models,the positive influence of initialization on subsequent learning,the potential for one-shot initialization,and the influence of class balance on middle-budget AL.Researchers are encouraged to improve medical pretraining for versatile DL foundations and explore novel AL methods.展开更多
In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can...In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.展开更多
This study applied machine learning methods to predict the durability performance(specifically shrinkage and freeze-thaw resistance)of solid waste-activated cementitious materials.It also offered insights for optimizi...This study applied machine learning methods to predict the durability performance(specifically shrinkage and freeze-thaw resistance)of solid waste-activated cementitious materials.It also offered insights for optimizing material formulations through feature impact analysis.The study collected a total of 130 sets of shrinkage data and 106 sets of freeze-thaw data,establishing various models,including BP,GA-BP,SVM,RF,RBF,and LSTM.The results revealed that the SVM model performed the best on the test dataset.It achieved an R^(2) of 0.9358 for shrinkage prediction,with MAE and RMSE values of 0.4644 and 0.6254,respectively.Regarding freeze-thaw quality loss prediction,the R^(2) was 0.9178,with MAE and RMSE values of 0.3139 and 0.5328,respectively.The study analyzed the impact of different features on the outcomes using the SHAP method,highlighting that the alkaline activator dosage,Al_(2)O_(3),SiO_(2),and water glass modulus were critical factors influencing shrinkage,while CaO,water-cement ratio,water,and Al_(2)O_(3) were crucial for freeze-thaw resistance.By investigating feature interactions through single-factor and two-factor analysis,the study proposed recommendations for optimizing material formulations.This research validated the efficacy of machine learning in predicting the durability of solid waste cementitious materials and offered insights for material optimization through feature impact analysis,thereby laying the groundwork for the development of related materials.展开更多
Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automa...Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automation has greatly increased across industries worldwide.Real-time detection requires edge devices with limited computational time.This study proposes a novel hybrid deep learning system for human activity recognition(HAR),aiming to enhance the recognition accuracy and reduce the computational time.The proposed system combines a pretrained image classification model with a sequence analysis model.First,the dataset was divided into a training set(70%),validation set(10%),and test set(20%).Second,all the videos were converted into frames and deep-based features were extracted from each frame using convolutional neural networks(CNNs)with a vision transformer.Following that,bidirectional long short-term memory(BiLSTM)-and temporal convolutional network(TCN)-based models were trained using the training set,and their performances were evaluated using the validation set and test set.Four benchmark datasets(UCF11,UCF50,UCF101,and JHMDB)were used to evaluate the performance of the proposed HAR-based system.The experimental results showed that the combination of ConvNeXt and the TCN-based model achieved a recognition accuracy of 97.73%for UCF11,98.81%for UCF50,98.46%for UCF101,and 83.38%for JHMDB,respectively.This represents improvements in the recognition accuracy of 4%,2.67%,3.67%,and 7.08%for the UCF11,UCF50,UCF101,and JHMDB datasets,respectively,over existing models.Moreover,the proposed HAR-based system obtained superior recognition accuracy,shorter computational times,and minimal memory usage compared to the existing models.展开更多
Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral method...Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral methods,most efforts on tree shrew behavior are limited to simple measures,resulting in the loss of much behavioral information.Methods:T o address this issue,we present a deep learning(DL)approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews,including drinking,eating,resting,and staying in the dark house,etc.Results:T his high-t hroughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period.Additionally,we demonstrated an innovative system with reliable apparatus,paradigms,and analysis methods for investigating food grasping behavior.The median duration for each bout of grasping was 0.20 s.Conclusion:T his study provides an efficient tool for quantifying and understand tree shrews'natural behaviors.展开更多
This paper proposes a modified iterative learning control(MILC)periodical feedback-feedforward algorithm to reduce the vibration of a rotor caused by coupled unbalance and parallel misalignment.The control of the vibr...This paper proposes a modified iterative learning control(MILC)periodical feedback-feedforward algorithm to reduce the vibration of a rotor caused by coupled unbalance and parallel misalignment.The control of the vibration of the rotor is provided by an active magnetic actuator(AMA).The iterative gain of the MILC algorithm here presented has a self-adjustment based on the magnitude of the vibration.Notch filters are adopted to extract the synchronous(1×Ω)and twice rotational frequency(2×Ω)components of the rotor vibration.Both the notch frequency of the filter and the size of feedforward storage used during the experiment have a real-time adaptation to the rotational speed.The method proposed in this work can provide effective suppression of the vibration of the rotor in case of sudden changes or fluctuations of the rotor speed.Simulations and experiments using the MILC algorithm proposed here are carried out and give evidence to the feasibility and robustness of the technique proposed.展开更多
Machine learning combined with density functional theory(DFT)enables rapid exploration of catalyst descriptors space such as adsorption energy,facilitating rapid and effective catalyst screening.However,there is still...Machine learning combined with density functional theory(DFT)enables rapid exploration of catalyst descriptors space such as adsorption energy,facilitating rapid and effective catalyst screening.However,there is still a lack of models for predicting adsorption energies on oxides,due to the complexity of elemental species and the ambiguous coordination environment.This work proposes an active learning workflow(LeNN)founded on local electronic transfer features(e)and the principle of coordinate rotation invariance.By accurately characterizing the electron transfer to adsorption site atoms and their surrounding geometric structures,LeNN mitigates abrupt feature changes due to different element types and clarifies coordination environments.As a result,it enables the prediction of^(*)H adsorption energy on binary oxide surfaces with a mean absolute error(MAE)below 0.18 eV.Moreover,we incorporate local coverage(θ_(l))and leverage neutral network ensemble to establish an active learning workflow,attaining a prediction MAE below 0.2 eV for 5419 multi-^(*)H adsorption structures.These findings validate the universality and capability of the proposed features in predicting^(*)H adsorption energy on binary oxide surfaces.展开更多
The effectiveness of facial expression recognition(FER)algorithms hinges on the model’s quality and the availability of a substantial amount of labeled expression data.However,labeling large datasets demands signific...The effectiveness of facial expression recognition(FER)algorithms hinges on the model’s quality and the availability of a substantial amount of labeled expression data.However,labeling large datasets demands significant human,time,and financial resources.Although active learning methods have mitigated the dependency on extensive labeled data,a cold-start problem persists in small to medium-sized expression recognition datasets.This issue arises because the initial labeled data often fails to represent the full spectrum of facial expression characteristics.This paper introduces an active learning approach that integrates uncertainty estimation,aiming to improve the precision of facial expression recognition regardless of dataset scale variations.The method is divided into two primary phases.First,the model undergoes self-supervised pre-training using contrastive learning and uncertainty estimation to bolster its feature extraction capabilities.Second,the model is fine-tuned using the prior knowledge obtained from the pre-training phase to significantly improve recognition accuracy.In the pretraining phase,the model employs contrastive learning to extract fundamental feature representations from the complete unlabeled dataset.These features are then weighted through a self-attention mechanism with rank regularization.Subsequently,data from the low-weighted set is relabeled to further refine the model’s feature extraction ability.The pre-trained model is then utilized in active learning to select and label information-rich samples more efficiently.Experimental results demonstrate that the proposed method significantly outperforms existing approaches,achieving an improvement in recognition accuracy of 5.09%and 3.82%over the best existing active learning methods,Margin,and Least Confidence methods,respectively,and a 1.61%improvement compared to the conventional segmented active learning method.展开更多
An intelligent wind tunnel using an active learning approach automates flow control experiments to discover the aerodynamic impact of sweeping jet on a swept wing. A Gaussian process regression model is established to...An intelligent wind tunnel using an active learning approach automates flow control experiments to discover the aerodynamic impact of sweeping jet on a swept wing. A Gaussian process regression model is established to study the jet actuator's performance at various attack and flap deflection angles. By selectively focusing on the most informative experiments, the proposed framework was able to predict 3721 wing conditions from just 55experiments, significantly reducing the number of experiments required and leading to faster and cost-effective predictions. The results show that the angle of attack and flap deflection angle are coupled to affect the effectiveness of the sweeping jet. Meanwhile, increasing the jet momentum coefficient can contribute to lift enhancement;a momentum coefficient of 3% can increase the lift coefficient by at most 0.28. Additionally, the improvement effects are more pronounced when actuators are placed closer to the wing root.展开更多
Graph learning,when used as a semi-supervised learning(SSL)method,performs well for classification tasks with a low label rate.We provide a graph-based batch active learning pipeline for pixel/patch neighborhood multi...Graph learning,when used as a semi-supervised learning(SSL)method,performs well for classification tasks with a low label rate.We provide a graph-based batch active learning pipeline for pixel/patch neighborhood multi-or hyperspectral image segmentation.Our batch active learning approach selects a collection of unlabeled pixels that satisfy a graph local maximum constraint for the active learning acquisition function that determines the relative importance of each pixel to the classification.This work builds on recent advances in the design of novel active learning acquisition functions(e.g.,the Model Change approach in arXiv:2110.07739)while adding important further developments including patch-neighborhood image analysis and batch active learning methods to further increase the accuracy and greatly increase the computational efficiency of these methods.In addition to improvements in the accuracy,our approach can greatly reduce the number of labeled pixels needed to achieve the same level of the accuracy based on randomly selected labeled pixels.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
For complex engineering problems,multi-fidelity modeling has been used to achieve efficient reliability analysis by leveraging multiple information sources.However,most methods require nested training samples to captu...For complex engineering problems,multi-fidelity modeling has been used to achieve efficient reliability analysis by leveraging multiple information sources.However,most methods require nested training samples to capture the correlation between different fidelity data,which may lead to a significant increase in low-fidelity samples.In addition,it is difficult to build accurate surrogate models because current methods do not fully consider the nonlinearity between different fidelity samples.To address these problems,a novel multi-fidelity modeling method with active learning is proposed in this paper.Firstly,a nonlinear autoregressive multi-fidelity Kriging(NAMK)model is used to build a surrogate model.To avoid introducing redundant samples in the process of NAMK model updating,a collective learning function is then developed by a combination of a U-learning function,the correlation between different fidelity samples,and the sampling cost.Furthermore,a residual model is constructed to automatically generate low-fidelity samples when high-fidelity samples are selected.The efficiency and accuracy of the proposed method are demonstrated using three numerical examples and an engineering case.展开更多
基金supported by the National Natural Science Foundation of China(Grant No.12374253,12074053,12004064)J.G.thanks the Foreign talents project(G2022127004L),The authors also acknowledge computer support from the Shanghai Supercomputer Center,the DUT Supercomputing Center,and the Tianhe supercomputer of Tianjin Center.
文摘Surface-supported clusters forming by aggregation of excessive adatoms could be the main defects of 2D materials after chemical vapor deposition.They will significantly impact the electronic/magnetic properties.Moreover,surface supported atoms are also widely explored for high active and selecting catalysts.Severe deformation,even dipping into the surface,of these clusters can be expected because of the very active edge of clusters and strong interaction between supported clusters and surfaces.However,most models of these clusters are supposed to simply float on the top of the surface because ab initio simulations cannot afford the complex reconstructions.Here,we develop an accurate graph neural network machine learning potential(MLP)from ab initio data by active learning architecture through fine-tuning pre-trained models,and then employ the MLP into Monte Carlo to explore the structural evolutions of Mo and S clusters(1-8 atoms)on perfect and various defective MoS2 monolayers.Interestingly,Mo clusters can always sink and embed themselves into MoS2 layers.In contrast,S clusters float on perfect surfaces.On the defective surface,a few S atoms will fill the vacancy and rest S clusters float on the top.Such significant structural reconstructions should be carefully taken into account.
基金supported by the Natural Science Foundation of China[grant numbers 52302093]Natural Science Foundation of Jiangxi Province[grant numbers 20224BAB204021].
文摘In materials science,a significant correlation often exists between material input parameters and their corresponding performance attributes.Nevertheless,the inherent challenges associated with small data obscure these statistical correlations,impeding machine learning models from effectively capturing the underlying patterns,thereby hampering efficient optimization of material properties.This work presents a novel active learning framework that integrates generative adversarial networks(GAN)with a directionally constrained expected absolute improvement(EAI)acquisition function to accelerate the discovery of ultra-high temperature ceramics(UHTCs)using small data.The framework employs GAN for data augmentation,symbolic regression for feature weight derivation,and a self-developed EAI function that incorporates input feature importance weighting to quantify bidirectional deviations from zero ablation rate.Through only two iterations,this framework successfully identified the optimal composition of HfB_(2)-3.52SiC-5.23TaSi_(2),which exhibits robust near-zero ablation rates under plasma ablation at 2500℃ for 200 s,demonstrating superior sampling efficiency compared to conventional active learning approaches.Microstructural analysis reveals that the exceptional performance stems from the formation of a highly viscous HfO_(2)-SiO_(2)-Ta_(2)O_(5)-HfSiO_(4)-Hf_(3)(BO_(3))_(4) oxide layer,which provides effective oxygen barrier protection.This work demonstrates an efficient and universal approach for rapid materials discovery using small data.
基金supported by the National Natural Science Foundation of China(Grant Nos.T2225022,12350710786,62088101,and 12161141016)Shuguang Program of Shanghai Education Development Foundation(Grant No.22SG21)Shanghai Municipal Education Commission,and the Fundamental Research Funds for the Central Universities。
文摘Dynamical systems often exhibit multiple attractors representing significantly different functioning conditions.A global map of attraction basins can offer valuable guidance for stabilizing or transitioning system states.Such a map can be constructed without prior system knowledge by identifying attractors across a sufficient number of points in the state space.However,determining the attractor for each initial state can be a laborious task.Here,we tackle the challenge of reconstructing attraction basins using as few initial points as possible.In each iteration of our approach,informative points are selected through random seeding and are driven along the current classification boundary,promoting the eventual selection of points that are both diverse and enlightening.The results across various experimental dynamical systems demonstrate that our approach requires fewer points than baseline methods while achieving comparable mapping accuracy.Additionally,the reconstructed map allows us to accurately estimate the minimum escape distance required to transition the system state to a target basin.
文摘Human Activity Recognition(HAR)has become increasingly critical in civic surveillance,medical care monitoring,and institutional protection.Current deep learning-based approaches often suffer from excessive computational complexity,limited generalizability under varying conditions,and compromised real-time performance.To counter these,this paper introduces an Active Learning-aided Heuristic Deep Spatio-Textural Ensemble Learning(ALH-DSEL)framework.The model initially identifies keyframes from the surveillance videos with a Multi-Constraint Active Learning(MCAL)approach,with features extracted from DenseNet121.The frames are then segmented employing an optimized Fuzzy C-Means clustering algorithm with Firefly to identify areas of interest.A deep ensemble feature extractor,comprising DenseNet121,EfficientNet-B7,MobileNet,and GLCM,extracts varied spatial and textural features.Fused characteristics are enhanced through PCA and Min-Max normalization and discriminated by a maximum voting ensemble of RF,AdaBoost,and XGBoost.The experimental results show that ALH-DSEL provides higher accuracy,precision,recall,and F1-score,validating its superiority for real-time HAR in surveillance scenarios.
基金supported by the National Natural Science Foundation of China(Grant Nos.62227821,62025503,and 62205199).
文摘To capture the nonlinear dynamics and gain evolution in chirped pulse amplification(CPA)systems,the split-step Fourier method and the fourth-order Runge–Kutta method are integrated to iteratively address the generalized nonlinear Schrödinger equation and the rate equations.However,this approach is burdened by substantial computational demands,resulting in significant time expenditures.In the context of intelligent laser optimization and inverse design,the necessity for numerous simulations further exacerbates this issue,highlighting the need for fast and accurate simulation methodologies.Here,we introduce an end-to-end model augmented with active learning(E2E-AL)with decent generalization through different dedicated embedding methods over various parameters.On an identical computational platform,the artificial intelligence–driven model is 2000 times faster than the conventional simulation method.Benefiting from the active learning strategy,the E2E-AL model achieves decent precision with only two-thirds of the training samples compared with the case without such a strategy.Furthermore,we demonstrate a multi-objective inverse design of the CPA systems enabled by the E2E-AL model.The E2E-AL framework manifests the potential of becoming a standard approach for the rapid and accurate modeling of ultrafast lasers and is readily extended to simulate other complex systems.
基金supported by the National Key R&D Program of China(No.2021YFB1715000)the National Natural Science Foundation of China(No.52375073)。
文摘The Reliability-Based Design Optimization(RBDO)of complex engineering structures considering uncertainties has problems of being high-dimensional,highly nonlinear,and timeconsuming,which requires a significant amount of sampling simulation computation.In this paper,a basis-adaptive Polynomial Chaos(PC)-Kriging surrogate model is proposed,in order to relieve the computational burden and enhance the predictive accuracy of a metamodel.The active learning basis-adaptive PC-Kriging model is combined with a quantile-based RBDO framework.Finally,five engineering cases have been implemented,including a benchmark RBDO problem,three high-dimensional explicit problems,and a high-dimensional implicit problem.Compared with Support Vector Regression(SVR),Kriging,and polynomial chaos expansion models,results show that the proposed basis-adaptive PC-Kriging model is more accurate and efficient for RBDO problems of complex engineering structures.
文摘One-step direct production of methanol from methane and water(PMMW)under mild conditions is challenging in heterogeneous catalysis owing to the absence of highly effective catalysts.Herein,we designed a series of“Single-Atom”-“Frustrated Lewis Pair”(SA-FLP)dual active sites for the direct PMMW via density functional theory(DFT)calculations combined with a machine learning(ML)approach.The results indicate that the nine designed SA-FLP catalysts are capable of efficiently activate CH4 and H_(2)O and facilitate the coupling of OH^(*)and CH_(3)^(*)into methanol.The DFT-based microkinetic simulation(MKM)results indicate that CH_(3)OH production on Co1-FLP and Pt1-FLP catalysts can reach the turnover frequencies(TOFs)of 1.01×10^(−3)s^(-1)and 8.80×10^(−4)s^(-1),respectively,which exceed the experimentally reported values by three orders of magnitude.ML results unveil that the gradient boosted regression model with 13 simple features could give satisfactory predictions for the TOFs of CH_(3)OH production with RMSE and R^(2)of 0.009 s^(-1)and 1.00,respectively.The ML-predicted MKM results indicate that four catalysts including V_(1-),Fe_(1-),Ti_(1-),and Mn_(1)-FLP exhibit higher TOFs of CH_(3)OH production than the value that the most relevant experiments reported,indicating that the four catalysts are also promising catalysts for the PMMW.This study not only develops a simple and efficient approach for design and screening SA-FLP catalysts but also provides mechanistic insights into the direct PMMW.
文摘Objective:Deep learning(DL)has become the prevailing method in chest radiograph analysis,yet its performance heavily depends on large quantities of annotated images.To mitigate the cost,cold-start active learning(AL),comprising an initialization followed by subsequent learning,selects a small subset of informative data points for labeling.Recent advancements in pretrained models by supervised or self-supervised learning tailored to chest radiograph have shown broad applicability to diverse downstream tasks.However,their potential in cold-start AL remains unexplored.Methods:To validate the efficacy of domain-specific pretraining,we compared two foundation models:supervised TXRV and self-supervised REMEDIS with their general domain counterparts pretrained on ImageNet.Model performance was evaluated at both initialization and subsequent learning stages on two diagnostic tasks:psychiatric pneumonia and COVID-19.For initialization,we assessed their integration with three strategies:diversity,uncertainty,and hybrid sampling.For subsequent learning,we focused on uncertainty sampling powered by different pretrained models.We also conducted statistical tests to compare the foundation models with ImageNet counterparts,investigate the relationship between initialization and subsequent learning,examine the performance of one-shot initialization against the full AL process,and investigate the influence of class balance in initialization samples on initialization and subsequent learning.Results:First,domain-specific foundation models failed to outperform ImageNet counterparts in six out of eight experiments on informative sample selection.Both domain-specific and general pretrained models were unable to generate representations that could substitute for the original images as model inputs in seven of the eight scenarios.However,pretrained model-based initialization surpassed random sampling,the default approach in cold-start AL.Second,initialization performance was positively correlated with subsequent learning performance,highlighting the importance of initialization strategies.Third,one-shot initialization performed comparably to the full AL process,demonstrating the potential of reducing experts'repeated waiting during AL iterations.Last,a U-shaped correlation was observed between the class balance of initialization samples and model performance,suggesting that the class balance is more strongly associated with performance at middle budget levels than at low or high budgets.Conclusions:In this study,we highlighted the limitations of medical pretraining compared to general pretraining in the context of cold-start AL.We also identified promising outcomes related to cold-start AL,including initialization based on pretrained models,the positive influence of initialization on subsequent learning,the potential for one-shot initialization,and the influence of class balance on middle-budget AL.Researchers are encouraged to improve medical pretraining for versatile DL foundations and explore novel AL methods.
文摘In the field of optoelectronics,certain types of data may be difficult to accurately annotate,such as high-resolution optoelectronic imaging or imaging in certain special spectral ranges.Weakly supervised learning can provide a more reliable approach in these situations.Current popular approaches mainly adopt the classification-based class activation maps(CAM)as initial pseudo labels to solve the task.
文摘This study applied machine learning methods to predict the durability performance(specifically shrinkage and freeze-thaw resistance)of solid waste-activated cementitious materials.It also offered insights for optimizing material formulations through feature impact analysis.The study collected a total of 130 sets of shrinkage data and 106 sets of freeze-thaw data,establishing various models,including BP,GA-BP,SVM,RF,RBF,and LSTM.The results revealed that the SVM model performed the best on the test dataset.It achieved an R^(2) of 0.9358 for shrinkage prediction,with MAE and RMSE values of 0.4644 and 0.6254,respectively.Regarding freeze-thaw quality loss prediction,the R^(2) was 0.9178,with MAE and RMSE values of 0.3139 and 0.5328,respectively.The study analyzed the impact of different features on the outcomes using the SHAP method,highlighting that the alkaline activator dosage,Al_(2)O_(3),SiO_(2),and water glass modulus were critical factors influencing shrinkage,while CaO,water-cement ratio,water,and Al_(2)O_(3) were crucial for freeze-thaw resistance.By investigating feature interactions through single-factor and two-factor analysis,the study proposed recommendations for optimizing material formulations.This research validated the efficacy of machine learning in predicting the durability of solid waste cementitious materials and offered insights for material optimization through feature impact analysis,thereby laying the groundwork for the development of related materials.
基金funded by the Ongoing Research Funding Program(ORF-2025-890),King Saud University,Riyadh,Saudi Arabia.
文摘Activity recognition is a challenging topic in the field of computer vision that has various applications,including surveillance systems,industrial automation,and human-computer interaction.Today,the demand for automation has greatly increased across industries worldwide.Real-time detection requires edge devices with limited computational time.This study proposes a novel hybrid deep learning system for human activity recognition(HAR),aiming to enhance the recognition accuracy and reduce the computational time.The proposed system combines a pretrained image classification model with a sequence analysis model.First,the dataset was divided into a training set(70%),validation set(10%),and test set(20%).Second,all the videos were converted into frames and deep-based features were extracted from each frame using convolutional neural networks(CNNs)with a vision transformer.Following that,bidirectional long short-term memory(BiLSTM)-and temporal convolutional network(TCN)-based models were trained using the training set,and their performances were evaluated using the validation set and test set.Four benchmark datasets(UCF11,UCF50,UCF101,and JHMDB)were used to evaluate the performance of the proposed HAR-based system.The experimental results showed that the combination of ConvNeXt and the TCN-based model achieved a recognition accuracy of 97.73%for UCF11,98.81%for UCF50,98.46%for UCF101,and 83.38%for JHMDB,respectively.This represents improvements in the recognition accuracy of 4%,2.67%,3.67%,and 7.08%for the UCF11,UCF50,UCF101,and JHMDB datasets,respectively,over existing models.Moreover,the proposed HAR-based system obtained superior recognition accuracy,shorter computational times,and minimal memory usage compared to the existing models.
基金supported by grants from the National Key Research and Development Program of China(2023YFF0724902)the China Postdoctoral Science Foundation(2020?M670027,2023TQ0183)the Local Standards Research of BeiJing Laboratory Tree Shrew(CHYX-2023-DGB001)。
文摘Background:Q uantifying the rich home-c age activities of tree shrews provides a reliable basis for understanding their daily routines and building disease models.However,due to the lack of effective behavioral methods,most efforts on tree shrew behavior are limited to simple measures,resulting in the loss of much behavioral information.Methods:T o address this issue,we present a deep learning(DL)approach to achieve markerless pose estimation and recognize multiple spontaneous behaviors of tree shrews,including drinking,eating,resting,and staying in the dark house,etc.Results:T his high-t hroughput approach can monitor the home-cage activities of 16 tree shrews simultaneously over an extended period.Additionally,we demonstrated an innovative system with reliable apparatus,paradigms,and analysis methods for investigating food grasping behavior.The median duration for each bout of grasping was 0.20 s.Conclusion:T his study provides an efficient tool for quantifying and understand tree shrews'natural behaviors.
基金Supported by National Natural Science Foundation of China(Grant Nos.51975037,52375075).
文摘This paper proposes a modified iterative learning control(MILC)periodical feedback-feedforward algorithm to reduce the vibration of a rotor caused by coupled unbalance and parallel misalignment.The control of the vibration of the rotor is provided by an active magnetic actuator(AMA).The iterative gain of the MILC algorithm here presented has a self-adjustment based on the magnitude of the vibration.Notch filters are adopted to extract the synchronous(1×Ω)and twice rotational frequency(2×Ω)components of the rotor vibration.Both the notch frequency of the filter and the size of feedforward storage used during the experiment have a real-time adaptation to the rotational speed.The method proposed in this work can provide effective suppression of the vibration of the rotor in case of sudden changes or fluctuations of the rotor speed.Simulations and experiments using the MILC algorithm proposed here are carried out and give evidence to the feasibility and robustness of the technique proposed.
基金supported by the National Natural Science Foundation of China(No.52488201)the Natural Science Basic Research Program of Shaanxi(No.2024JC-YBMS-284)+1 种基金the Key Research and Development Program of Shaanxi(No.2024GHYBXM-02)the Fundamental Research Funds for the Central Universities.
文摘Machine learning combined with density functional theory(DFT)enables rapid exploration of catalyst descriptors space such as adsorption energy,facilitating rapid and effective catalyst screening.However,there is still a lack of models for predicting adsorption energies on oxides,due to the complexity of elemental species and the ambiguous coordination environment.This work proposes an active learning workflow(LeNN)founded on local electronic transfer features(e)and the principle of coordinate rotation invariance.By accurately characterizing the electron transfer to adsorption site atoms and their surrounding geometric structures,LeNN mitigates abrupt feature changes due to different element types and clarifies coordination environments.As a result,it enables the prediction of^(*)H adsorption energy on binary oxide surfaces with a mean absolute error(MAE)below 0.18 eV.Moreover,we incorporate local coverage(θ_(l))and leverage neutral network ensemble to establish an active learning workflow,attaining a prediction MAE below 0.2 eV for 5419 multi-^(*)H adsorption structures.These findings validate the universality and capability of the proposed features in predicting^(*)H adsorption energy on binary oxide surfaces.
基金supported by National Science Foundation of China(61971078)Chongqing Municipal Education Commission Science and Technology Major Project(KJZDM202301901).
文摘The effectiveness of facial expression recognition(FER)algorithms hinges on the model’s quality and the availability of a substantial amount of labeled expression data.However,labeling large datasets demands significant human,time,and financial resources.Although active learning methods have mitigated the dependency on extensive labeled data,a cold-start problem persists in small to medium-sized expression recognition datasets.This issue arises because the initial labeled data often fails to represent the full spectrum of facial expression characteristics.This paper introduces an active learning approach that integrates uncertainty estimation,aiming to improve the precision of facial expression recognition regardless of dataset scale variations.The method is divided into two primary phases.First,the model undergoes self-supervised pre-training using contrastive learning and uncertainty estimation to bolster its feature extraction capabilities.Second,the model is fine-tuned using the prior knowledge obtained from the pre-training phase to significantly improve recognition accuracy.In the pretraining phase,the model employs contrastive learning to extract fundamental feature representations from the complete unlabeled dataset.These features are then weighted through a self-attention mechanism with rank regularization.Subsequently,data from the low-weighted set is relabeled to further refine the model’s feature extraction ability.The pre-trained model is then utilized in active learning to select and label information-rich samples more efficiently.Experimental results demonstrate that the proposed method significantly outperforms existing approaches,achieving an improvement in recognition accuracy of 5.09%and 3.82%over the best existing active learning methods,Margin,and Least Confidence methods,respectively,and a 1.61%improvement compared to the conventional segmented active learning method.
基金supported by the National Natural Science Foundation of China (Grant No.92271107)。
文摘An intelligent wind tunnel using an active learning approach automates flow control experiments to discover the aerodynamic impact of sweeping jet on a swept wing. A Gaussian process regression model is established to study the jet actuator's performance at various attack and flap deflection angles. By selectively focusing on the most informative experiments, the proposed framework was able to predict 3721 wing conditions from just 55experiments, significantly reducing the number of experiments required and leading to faster and cost-effective predictions. The results show that the angle of attack and flap deflection angle are coupled to affect the effectiveness of the sweeping jet. Meanwhile, increasing the jet momentum coefficient can contribute to lift enhancement;a momentum coefficient of 3% can increase the lift coefficient by at most 0.28. Additionally, the improvement effects are more pronounced when actuators are placed closer to the wing root.
基金supported by the UC-National Lab In-Residence Graduate Fellowship Grant L21GF3606supported by a DOD National Defense Science and Engineering Graduate(NDSEG)Research Fellowship+1 种基金supported by the Laboratory Directed Research and Development program of Los Alamos National Laboratory under project numbers 20170668PRD1 and 20210213ERsupported by the NGA under Contract No.HM04762110003.
文摘Graph learning,when used as a semi-supervised learning(SSL)method,performs well for classification tasks with a low label rate.We provide a graph-based batch active learning pipeline for pixel/patch neighborhood multi-or hyperspectral image segmentation.Our batch active learning approach selects a collection of unlabeled pixels that satisfy a graph local maximum constraint for the active learning acquisition function that determines the relative importance of each pixel to the classification.This work builds on recent advances in the design of novel active learning acquisition functions(e.g.,the Model Change approach in arXiv:2110.07739)while adding important further developments including patch-neighborhood image analysis and batch active learning methods to further increase the accuracy and greatly increase the computational efficiency of these methods.In addition to improvements in the accuracy,our approach can greatly reduce the number of labeled pixels needed to achieve the same level of the accuracy based on randomly selected labeled pixels.
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 Major Projects of Zhejiang Provincial Natural Science Foundation of China(No.LD22E050009)the National Natural Science Foundation of China(No.51475425)the College Student’s Science and Technology Innovation Project of Zhejiang Province(No.2022R403B060),China.
文摘For complex engineering problems,multi-fidelity modeling has been used to achieve efficient reliability analysis by leveraging multiple information sources.However,most methods require nested training samples to capture the correlation between different fidelity data,which may lead to a significant increase in low-fidelity samples.In addition,it is difficult to build accurate surrogate models because current methods do not fully consider the nonlinearity between different fidelity samples.To address these problems,a novel multi-fidelity modeling method with active learning is proposed in this paper.Firstly,a nonlinear autoregressive multi-fidelity Kriging(NAMK)model is used to build a surrogate model.To avoid introducing redundant samples in the process of NAMK model updating,a collective learning function is then developed by a combination of a U-learning function,the correlation between different fidelity samples,and the sampling cost.Furthermore,a residual model is constructed to automatically generate low-fidelity samples when high-fidelity samples are selected.The efficiency and accuracy of the proposed method are demonstrated using three numerical examples and an engineering case.
