Neural networks with physical governing equations as constraints have recently created a new trend in machine learning research.In this context,a review of related research is first presented and discussed.The potenti...Neural networks with physical governing equations as constraints have recently created a new trend in machine learning research.In this context,a review of related research is first presented and discussed.The potential offered by such physics-informed deep learning models for computations in geomechanics is demonstrated by application to one-dimensional(1D)consolidation.The governing equation for 1D problems is applied as a constraint in the deep learning model.The deep learning model relies on automatic differentiation for applying the governing equation as a constraint,based on the mathematical approximations established by the neural network.The total loss is measured as a combination of the training loss(based on analytical and model predicted solutions)and the constraint loss(a requirement to satisfy the governing equation).Two classes of problems are considered:forward and inverse problems.The forward problems demonstrate the performance of a physically constrained neural network model in predicting solutions for 1D consolidation problems.Inverse problems show prediction of the coefficient of consolidation.Terzaghi’s problem,with varying boundary conditions,is used as a numerical example and the deep learning model shows a remarkable performance in both the forward and inverse problems.While the application demonstrated here is a simple 1D consolidation problem,such a deep learning model integrated with a physical law has significant implications for use in,such as,faster realtime numerical prediction for digital twins,numerical model reproducibility and constitutive model parameter optimization.展开更多
Physics-informed deep learning has drawn tremendous interest in recent years to solve computational physics problems,whose basic concept is to embed physical laws to constrain/inform neural networks,with the need of l...Physics-informed deep learning has drawn tremendous interest in recent years to solve computational physics problems,whose basic concept is to embed physical laws to constrain/inform neural networks,with the need of less data for training a reliable model.This can be achieved by incorporating the residual of physics equations into the loss function.Through minimizing the loss function,the network could approximate the solution.In this paper,we propose a mixed-variable scheme of physics-informed neural network(PINN)for fluid dynamics and apply it to simulate steady and transient laminar flows at low Reynolds numbers.A parametric study indicates that the mixed-variable scheme can improve the PINN trainability and the solution accuracy.The predicted velocity and pressure fields by the proposed PINN approach are also compared with the reference numerical solutions.Simulation results demonstrate great potential of the proposed PINN for fluid flow simulation with a high accuracy.展开更多
In this work,a physics-informed neural network(PINN)designed specifically for analyzing digital mate-rials is introduced.This proposed machine learning(ML)model can be trained free of ground truth data by adopting the...In this work,a physics-informed neural network(PINN)designed specifically for analyzing digital mate-rials is introduced.This proposed machine learning(ML)model can be trained free of ground truth data by adopting the minimum energy criteria as its loss function.Results show that our energy-based PINN reaches similar accuracy as supervised ML models.Adding a hinge loss on the Jacobian can constrain the model to avoid erroneous deformation gradient caused by the nonlinear logarithmic strain.Lastly,we discuss how the strain energy of each material element at each numerical integration point can be calculated parallelly on a GPU.The algorithm is tested on different mesh densities to evaluate its com-putational efficiency which scales linearly with respect to the number of nodes in the system.This work provides a foundation for encoding physical behaviors of digital materials directly into neural networks,enabling label-free learning for the design of next-generation composites.展开更多
Accurate traffic forecasting is crucial for understanding and managing congestion for effi-cient transportation planning.However,conventional approaches often neglect epistemic uncertainty,which arises from incomplete...Accurate traffic forecasting is crucial for understanding and managing congestion for effi-cient transportation planning.However,conventional approaches often neglect epistemic uncertainty,which arises from incomplete knowledge across different spatiotemporal scales.This study addresses this challenge by introducing a novel methodology to establish dynamic spatiotemporal correlations that captures the unobserved heterogeneity in travel time through distinct peaks in probability density functions,guided by physics-based prin-ciples.We propose an innovative approach to modifying both prediction and correction steps of the Kalman filter(KF)algorithm by leveraging established spatiotemporal correla-tions.Central to our approach is the development of a novel deep learning(DL)model called the physics informed-graph convolutional gated recurrent neural network(PI-GRNN).Functioning as the state-space model within the KF,the PI-GRNN exploits estab-lished correlations to construct dynamic adjacency matrices that utilize the inherent struc-ture and relationships within the transportation network to capture sequential patterns and dependencies over time.Furthermore,our methodology integrates insights gained from correlations into the correction step of the KF algorithm that helps in enhancing its correctional capabilities.This integrated approach proves instrumental in alleviating the inherent model drift associated with data-driven methods,as periodic corrections through update step of KF refine the predictions generated by the PI-GRNN.To the best of our knowledge,this study represents a pioneering effort in integrating DL and KF algorithms in this unique symbiotic manner.Through extensive experimentation with real-world traf-fic data,we demonstrate the superior performance of our model compared to the bench-mark approaches.展开更多
Physics-informed neural networks(PINNs)are promising to replace conventional mesh-based partial tial differen-equation(PDE)solvers by offering more accurate and flexible PDE solutions.However,PINNs are hampered by the...Physics-informed neural networks(PINNs)are promising to replace conventional mesh-based partial tial differen-equation(PDE)solvers by offering more accurate and flexible PDE solutions.However,PINNs are hampered by the relatively slow convergence and the need to perform additional,potentially expensive training for new PDE parameters.To solve this limitation,we introduce LatentPINN,a framework that utilizes latent representations of the PDE parameters as additional(to the coordinates)inputs into PINNs and allows for training over the distribution of these parameters.Motivated by the recent progress on generative models,we promote using latent diffusion models to learn compressed latent representations of the distribution of PDE parameters as they act as input parameters for NN functional solutions.We use a two-stage training scheme in which,in the first stage,we learn the latent representations for the distribution of PDE parameters.In the second stage,we train a physics-informed neural network over inputs given by randomly drawn samples from the coordinate space within the solution domain and samples from the learned latent representation of the PDE parameters.Considering their importance in capturing evolving interfaces and fronts in various fields,we test the approach on a class of level set equations given,for example,by the nonlinear Eikonal equation.We share results corresponding to three Eikonal parameters(velocity models)sets.The proposed method performs well on new phase velocity models without the need for any additional training.展开更多
Recently,deep learning has yielded transformative success across optics and photonics,especially in optical metrology.Deep neural networks (DNNs) with a fully convolutional architecture (e.g.,U-Net and its derivatives...Recently,deep learning has yielded transformative success across optics and photonics,especially in optical metrology.Deep neural networks (DNNs) with a fully convolutional architecture (e.g.,U-Net and its derivatives) have been widely implemented in an end-to-end manner to accomplish various optical metrology tasks,such as fringe denoising,phase unwrapping,and fringe analysis.However,the task of training a DNN to accurately identify an image-to-image transform from massive input and output data pairs seems at best naive,as the physical laws governing the image formation or other domain expertise pertaining to the measurement have not yet been fully exploited in current deep learning practice.To this end,we introduce a physics-informed deep learning method for fringe pattern analysis (PI-FPA) to overcome this limit by integrating a lightweight DNN with a learning-enhanced Fourier transform profilometry (Le FTP) module.By parameterizing conventional phase retrieval methods,the Le FTP module embeds the prior knowledge in the network structure and the loss function to directly provide reliable phase results for new types of samples,while circumventing the requirement of collecting a large amount of high-quality data in supervised learning methods.Guided by the initial phase from Le FTP,the phase recovery ability of the lightweight DNN is enhanced to further improve the phase accuracy at a low computational cost compared with existing end-to-end networks.Experimental results demonstrate that PI-FPA enables more accurate and computationally efficient single-shot phase retrieval,exhibiting its excellent generalization to various unseen objects during training.The proposed PI-FPA presents that challenging issues in optical metrology can be potentially overcome through the synergy of physics-priors-based traditional tools and data-driven learning approaches,opening new avenues to achieve fast and accurate single-shot 3D imaging.展开更多
Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are...Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.展开更多
Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay di...Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.展开更多
The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To addres...The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To address this issue,this study proposes a transfer learning model based on a sequence-to-sequence twodimensional(2D)convolutional long short-term memory neural network(S2SCL2D).The model can use the existing data from other adjacent similar excavations to achieve wall deflection prediction once a limited amount of monitoring data from the target excavation has been recorded.In the absence of adjacent excavation data,numerical simulation data from the target project can be employed instead.A weight update strategy is proposed to improve the prediction accuracy by integrating the stochastic gradient masking with an early stopping mechanism.To illustrate the proposed methodology,an excavation project in Hangzhou,China is adopted.The proposed deep transfer learning model,which uses either adjacent excavation data or numerical simulation data as the source domain,shows a significant improvement in performance when compared to the non-transfer learning model.Using the simulation data from the target project even leads to better prediction performance than using the actual monitoring data from other adjacent excavations.The results demonstrate that the proposed model can reasonably predict the deformation with limited data from the target project.展开更多
Large language models(LLMs)have emerged as powerful tools for addressing a wide range of problems,including those in scientific computing,particularly in solving partial differential equations(PDEs).However,different ...Large language models(LLMs)have emerged as powerful tools for addressing a wide range of problems,including those in scientific computing,particularly in solving partial differential equations(PDEs).However,different models exhibit distinct strengths and preferences,resulting in varying levels of performance.In this paper,we compare the capabilities of the most advanced LLMs—DeepSeek,ChatGPT,and Claude—along with their reasoning-optimized versions in addressing computational challenges.Specifically,we evaluate their proficiency in solving traditional numerical problems in scientific computing as well as leveraging scientific machine learning techniques for PDE-based problems.We designed all our experiments so that a nontrivial decision is required,e.g,defining the proper space of input functions for neural operator learning.Our findings show that reasoning and hybrid-reasoning models consistently and significantly outperform non-reasoning ones in solving challenging problems,with ChatGPT o3-mini-high generally offering the fastest reasoning speed.展开更多
Bearing is an indispensable key component in mechanical equipment,and its working state is directly related to the stability and safety of the whole equipment.In recent years,with the rapid development of artificial i...Bearing is an indispensable key component in mechanical equipment,and its working state is directly related to the stability and safety of the whole equipment.In recent years,with the rapid development of artificial intelligence technology,especially the breakthrough of deep learning technology,it provides a new idea for bearing fault diagnosis.Deep learning can automatically learn features from a large amount of data,has a strong nonlinear modeling ability,and can effectively solve the problems existing in traditional methods.Aiming at the key problems in bearing fault diagnosis,this paper studies the fault diagnosis method based on deep learning,which not only provides a new solution for bearing fault diagnosis but also provides a reference for the application of deep learning in other mechanical fault diagnosis fields.展开更多
In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fi...In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.展开更多
BACKGROUND Hepatocellular carcinoma(HCC)is a prevalent and life-threatening cancer with increasing incidence worldwide.High Ki-67 risk stratification is closely associated with higher recurrence rates and worse outcom...BACKGROUND Hepatocellular carcinoma(HCC)is a prevalent and life-threatening cancer with increasing incidence worldwide.High Ki-67 risk stratification is closely associated with higher recurrence rates and worse outcomes following curative therapies in patients with HCC.However,the performance of radiomic and deep transfer learning(DTL)models derived from biparametric magnetic resonance imaging(bpMRI)in predicting Ki-67 risk stratification and recurrence-free survival(RFS)in patients with HCC remains limited.AIM To develop a nomogram model integrating bpMRI-based radiomic and DTL signatures for predicting Ki-67 risk stratification and RFS in patients with HCC.METHODS This study included 198 patients with histopathologically confirmed HCC who underwent preoperative bpMRI.Ki-67 risk stratification was categorized as high(>20%)or low(≤20%)according to immunohistochemical staining.Radiomic and DTL signatures were extracted from the T2-weighted and arterial-phase images and combined through a random forest algorithm to establish radiomic and DTL models,respectively.Multivariate regression analysis identified clinical risk factors for high Ki-67 risk stratification,and a predictive nomogram model was developed.RESULTS A nonsmooth margin and the absence of an enhanced capsule were independent factors for high Ki-67 risk stratification.The area under the curve(AUC)of the clinical model was 0.77,while those of the radiomic and DTL models were 0.81 and 0.87,respectively,for the prediction of high Ki-67 risk stratification,and the nomogram model achieved a better AUC of 0.92.The median RFS times for patients with high and low Ki-67 risk stratification were 33.00 months and 66.73 months,respectively(P<0.001).Additionally,patients who were predicted to have high Ki-67 risk stratification by the nomogram model had a lower median RFS than those who were predicted to have low Ki-67 risk stratification(33.53 vs 66.74 months,P=0.007).CONCLUSION Our developed nomogram model demonstrated good performance in predicting Ki-67 risk stratification and predicting survival outcomes in patients with HCC.展开更多
Negative logarithm of the acid dissociation constant(pK_(a))significantly influences the absorption,dis-tribution,metabolism,excretion,and toxicity(ADMET)properties of molecules and is a crucial indicator in drug rese...Negative logarithm of the acid dissociation constant(pK_(a))significantly influences the absorption,dis-tribution,metabolism,excretion,and toxicity(ADMET)properties of molecules and is a crucial indicator in drug research.Given the rapid and accurate characteristics of computational methods,their role in predicting drug properties is increasingly important.Although many pK_(a) prediction models currently exist,they often focus on enhancing model precision while neglecting interpretability.In this study,we present GraFpKa,a pK_(a) prediction model using graph neural networks(GNNs)and molecular finger-prints.The results show that our acidic and basic models achieved mean absolute errors(MAEs)of 0.621 and 0.402,respectively,on the test set,demonstrating good predictive performance.Notably,to improve interpretability,GraFpKa also incorporates Integrated Gradients(IGs),providing a clearer visual description of the atoms significantly affecting the pK_(a) values.The high reliability and interpretability of GraFpKa ensure accurate pKa predictions while also facilitating a deeper understanding of the relation-ship between molecular structure and pK_(a) values,making it a valuable tool in the field of pK_(a) prediction.展开更多
Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and di...Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and differences of various surface features.Currently,topographic maps are mainly stored in raster and vector formats.Extraction of the spatio-temporal knowledge in the maps—such as spatial distribution patterns,feature relationships,and dynamic evolution—still primarily relies on manual interpretation.However,manual interpretation is time-consuming and laborious,especially for large-scale,long-term map knowledge extraction and application.With the development of artificial intelligence technology,it is possible to improve the automation level of map knowledge interpretation.Therefore,the present study proposes an automatic interpretation method for raster topographic map knowledge based on deep learning.To address the limitations of current data-driven intelligent technology in learning map spatial relations and cognitive logic,we establish a formal description of map knowledge by mapping the relationship between map knowledge and features,thereby ensuring interpretation accuracy.Subsequently,deep learning techniques are employed to extract map features automatically,and the spatio-temporal knowledge is constructed by combining formal descriptions of geographic feature knowledge.Validation experiments demonstrate that the proposed method effectively achieves automatic interpretation of spatio-temporal knowledge of geographic features in maps,with an accuracy exceeding 80%.The findings of the present study contribute to machine understanding of spatio-temporal differences in map knowledge and advances the intelligent interpretation and utilization of cartographic information.展开更多
Multimodal deep learning has emerged as a key paradigm in contemporary medical diagnostics,advancing precision medicine by enabling integration and learning from diverse data sources.The exponential growth of high-dim...Multimodal deep learning has emerged as a key paradigm in contemporary medical diagnostics,advancing precision medicine by enabling integration and learning from diverse data sources.The exponential growth of high-dimensional healthcare data,encompassing genomic,transcriptomic,and other omics profiles,as well as radiological imaging and histopathological slides,makes this approach increasingly important because,when examined separately,these data sources only offer a fragmented picture of intricate disease processes.Multimodal deep learning leverages the complementary properties of multiple data modalities to enable more accurate prognostic modeling,more robust disease characterization,and improved treatment decision-making.This review provides a comprehensive overview of the current state of multimodal deep learning approaches in medical diagnosis.We classify and examine important application domains,such as(1)radiology,where automated report generation and lesion detection are facilitated by image-text integration;(2)histopathology,where fusion models improve tumor classification and grading;and(3)multi-omics,where molecular subtypes and latent biomarkers are revealed through cross-modal learning.We provide an overview of representative research,methodological advancements,and clinical consequences for each domain.Additionally,we critically analyzed the fundamental issues preventing wider adoption,including computational complexity(particularly in training scalable,multi-branch networks),data heterogeneity(resulting from modality-specific noise,resolution variations,and inconsistent annotations),and the challenge of maintaining significant cross-modal correlations during fusion.These problems impede interpretability,which is crucial for clinical trust and use,in addition to performance and generalizability.Lastly,we outline important areas for future research,including the development of standardized protocols for harmonizing data,the creation of lightweight and interpretable fusion architectures,the integration of real-time clinical decision support systems,and the promotion of cooperation for federated multimodal learning.Our goal is to provide researchers and clinicians with a concise overview of the field’s present state,enduring constraints,and exciting directions for further research through this review.展开更多
Liver cancer remains a leading cause of mortality worldwide,and precise diagnostic tools are essential for effective treatment planning.Liver Tumors(LTs)vary significantly in size,shape,and location,and can present wi...Liver cancer remains a leading cause of mortality worldwide,and precise diagnostic tools are essential for effective treatment planning.Liver Tumors(LTs)vary significantly in size,shape,and location,and can present with tissues of similar intensities,making automatically segmenting and classifying LTs from abdominal tomography images crucial and challenging.This review examines recent advancements in Liver Segmentation(LS)and Tumor Segmentation(TS)algorithms,highlighting their strengths and limitations regarding precision,automation,and resilience.Performance metrics are utilized to assess key detection algorithms and analytical methods,emphasizing their effectiveness and relevance in clinical contexts.The review also addresses ongoing challenges in liver tumor segmentation and identification,such as managing high variability in patient data and ensuring robustness across different imaging conditions.It suggests directions for future research,with insights into technological advancements that can enhance surgical planning and diagnostic accuracy by comparing popular methods.This paper contributes to a comprehensive understanding of current liver tumor detection techniques,provides a roadmap for future innovations,and improves diagnostic and therapeutic outcomes for liver cancer by integrating recent progress with remaining challenges.展开更多
App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their products.Automating the analysis of these reviews is vital for efficient review management.While t...App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their products.Automating the analysis of these reviews is vital for efficient review management.While traditional machine learning(ML)models rely on basic word-based feature extraction,deep learning(DL)methods,enhanced with advanced word embeddings,have shown superior performance.This research introduces a novel aspectbased sentiment analysis(ABSA)framework to classify app reviews based on key non-functional requirements,focusing on usability factors:effectiveness,efficiency,and satisfaction.We propose a hybrid DL model,combining BERT(Bidirectional Encoder Representations from Transformers)with BiLSTM(Bidirectional Long Short-Term Memory)and CNN(Convolutional Neural Networks)layers,to enhance classification accuracy.Comparative analysis against state-of-the-art models demonstrates that our BERT-BiLSTM-CNN model achieves exceptional performance,with precision,recall,F1-score,and accuracy of 96%,87%,91%,and 94%,respectively.Thesignificant contributions of this work include a refined ABSA-based relabeling framework,the development of a highperformance classifier,and the comprehensive relabeling of the Instagram App Reviews dataset.These advancements provide valuable insights for software developers to enhance usability and drive user-centric application development.展开更多
As more and more devices in Cyber-Physical Systems(CPS)are connected to the Internet,physical components such as programmable logic controller(PLC),sensors,and actuators are facing greater risks of network attacks,and...As more and more devices in Cyber-Physical Systems(CPS)are connected to the Internet,physical components such as programmable logic controller(PLC),sensors,and actuators are facing greater risks of network attacks,and fast and accurate attack detection techniques are crucial.The key problem in distinguishing between normal and abnormal sequences is to model sequential changes in a large and diverse field of time series.To address this issue,we propose an anomaly detection method based on distributed deep learning.Our method uses a bilateral filtering algorithm for sequential sequences to remove noise in the time series,which can maintain the edge of discrete features.We use a distributed linear deep learning model to establish a sequential prediction model and adjust the threshold for anomaly detection based on the prediction error of the validation set.Our method can not only detect abnormal attacks but also locate the sensors that cause anomalies.We conducted experiments on the Secure Water Treatment(SWAT)and Water Distribution(WADI)public datasets.The experimental results show that our method is superior to the baseline method in identifying the types of attacks and detecting efficiency.展开更多
Exo-atmospheric vehicles are constrained by limited maneuverability,which leads to the contradiction between evasive maneuver and precision strike.To address the problem of Integrated Evasion and Impact(IEI)decision u...Exo-atmospheric vehicles are constrained by limited maneuverability,which leads to the contradiction between evasive maneuver and precision strike.To address the problem of Integrated Evasion and Impact(IEI)decision under multi-constraint conditions,a hierarchical intelligent decision-making method based on Deep Reinforcement Learning(DRL)was proposed.First,an intelligent decision-making framework of“DRL evasion decision”+“impact prediction guidance decision”was established:it takes the impact point deviation correction ability as the constraint and the maximum miss distance as the objective,and effectively solves the problem of poor decisionmaking effect caused by the large IEI decision space.Second,to solve the sparse reward problem faced by evasion decision-making,a hierarchical decision-making method consisting of maneuver timing decision and maneuver duration decision was proposed,and the corresponding Markov Decision Process(MDP)was designed.A detailed simulation experiment was designed to analyze the advantages and computational complexity of the proposed method.Simulation results show that the proposed model has good performance and low computational resource requirement.The minimum miss distance is 21.3 m under the condition of guaranteeing the impact point accuracy,and the single decision-making time is 4.086 ms on an STM32F407 single-chip microcomputer,which has engineering application value.展开更多
基金The research is supported by internal funding from SINTEF through a strategic project focusing on Machine Learning and Digitalization in the infrastructure sector.
文摘Neural networks with physical governing equations as constraints have recently created a new trend in machine learning research.In this context,a review of related research is first presented and discussed.The potential offered by such physics-informed deep learning models for computations in geomechanics is demonstrated by application to one-dimensional(1D)consolidation.The governing equation for 1D problems is applied as a constraint in the deep learning model.The deep learning model relies on automatic differentiation for applying the governing equation as a constraint,based on the mathematical approximations established by the neural network.The total loss is measured as a combination of the training loss(based on analytical and model predicted solutions)and the constraint loss(a requirement to satisfy the governing equation).Two classes of problems are considered:forward and inverse problems.The forward problems demonstrate the performance of a physically constrained neural network model in predicting solutions for 1D consolidation problems.Inverse problems show prediction of the coefficient of consolidation.Terzaghi’s problem,with varying boundary conditions,is used as a numerical example and the deep learning model shows a remarkable performance in both the forward and inverse problems.While the application demonstrated here is a simple 1D consolidation problem,such a deep learning model integrated with a physical law has significant implications for use in,such as,faster realtime numerical prediction for digital twins,numerical model reproducibility and constitutive model parameter optimization.
文摘Physics-informed deep learning has drawn tremendous interest in recent years to solve computational physics problems,whose basic concept is to embed physical laws to constrain/inform neural networks,with the need of less data for training a reliable model.This can be achieved by incorporating the residual of physics equations into the loss function.Through minimizing the loss function,the network could approximate the solution.In this paper,we propose a mixed-variable scheme of physics-informed neural network(PINN)for fluid dynamics and apply it to simulate steady and transient laminar flows at low Reynolds numbers.A parametric study indicates that the mixed-variable scheme can improve the PINN trainability and the solution accuracy.The predicted velocity and pressure fields by the proposed PINN approach are also compared with the reference numerical solutions.Simulation results demonstrate great potential of the proposed PINN for fluid flow simulation with a high accuracy.
文摘In this work,a physics-informed neural network(PINN)designed specifically for analyzing digital mate-rials is introduced.This proposed machine learning(ML)model can be trained free of ground truth data by adopting the minimum energy criteria as its loss function.Results show that our energy-based PINN reaches similar accuracy as supervised ML models.Adding a hinge loss on the Jacobian can constrain the model to avoid erroneous deformation gradient caused by the nonlinear logarithmic strain.Lastly,we discuss how the strain energy of each material element at each numerical integration point can be calculated parallelly on a GPU.The algorithm is tested on different mesh densities to evaluate its com-putational efficiency which scales linearly with respect to the number of nodes in the system.This work provides a foundation for encoding physical behaviors of digital materials directly into neural networks,enabling label-free learning for the design of next-generation composites.
基金Funding for this research was provided by NSF[1910397,2106989]NCDOT[TCE2020-01].
文摘Accurate traffic forecasting is crucial for understanding and managing congestion for effi-cient transportation planning.However,conventional approaches often neglect epistemic uncertainty,which arises from incomplete knowledge across different spatiotemporal scales.This study addresses this challenge by introducing a novel methodology to establish dynamic spatiotemporal correlations that captures the unobserved heterogeneity in travel time through distinct peaks in probability density functions,guided by physics-based prin-ciples.We propose an innovative approach to modifying both prediction and correction steps of the Kalman filter(KF)algorithm by leveraging established spatiotemporal correla-tions.Central to our approach is the development of a novel deep learning(DL)model called the physics informed-graph convolutional gated recurrent neural network(PI-GRNN).Functioning as the state-space model within the KF,the PI-GRNN exploits estab-lished correlations to construct dynamic adjacency matrices that utilize the inherent struc-ture and relationships within the transportation network to capture sequential patterns and dependencies over time.Furthermore,our methodology integrates insights gained from correlations into the correction step of the KF algorithm that helps in enhancing its correctional capabilities.This integrated approach proves instrumental in alleviating the inherent model drift associated with data-driven methods,as periodic corrections through update step of KF refine the predictions generated by the PI-GRNN.To the best of our knowledge,this study represents a pioneering effort in integrating DL and KF algorithms in this unique symbiotic manner.Through extensive experimentation with real-world traf-fic data,we demonstrate the superior performance of our model compared to the bench-mark approaches.
基金King Abdullah University of Science and Technol-ogy(KAUST)for supporting this research and the Seismic Wave Anal-ysis group for the supportive and encouraging environment.
文摘Physics-informed neural networks(PINNs)are promising to replace conventional mesh-based partial tial differen-equation(PDE)solvers by offering more accurate and flexible PDE solutions.However,PINNs are hampered by the relatively slow convergence and the need to perform additional,potentially expensive training for new PDE parameters.To solve this limitation,we introduce LatentPINN,a framework that utilizes latent representations of the PDE parameters as additional(to the coordinates)inputs into PINNs and allows for training over the distribution of these parameters.Motivated by the recent progress on generative models,we promote using latent diffusion models to learn compressed latent representations of the distribution of PDE parameters as they act as input parameters for NN functional solutions.We use a two-stage training scheme in which,in the first stage,we learn the latent representations for the distribution of PDE parameters.In the second stage,we train a physics-informed neural network over inputs given by randomly drawn samples from the coordinate space within the solution domain and samples from the learned latent representation of the PDE parameters.Considering their importance in capturing evolving interfaces and fronts in various fields,we test the approach on a class of level set equations given,for example,by the nonlinear Eikonal equation.We share results corresponding to three Eikonal parameters(velocity models)sets.The proposed method performs well on new phase velocity models without the need for any additional training.
基金funded by National Key Research and Development Program of China (2022YFB2804603,2022YFB2804604)National Natural Science Foundation of China (62075096,62205147,U21B2033)+7 种基金China Postdoctoral Science Foundation (2023T160318,2022M711630,2022M721619)Jiangsu Funding Program for Excellent Postdoctoral Talent (2022ZB254)The Leading Technology of Jiangsu Basic Research Plan (BK20192003)The“333 Engineering”Research Project of Jiangsu Province (BRA2016407)The Jiangsu Provincial“One belt and one road”innovation cooperation project (BZ2020007)Open Research Fund of Jiangsu Key Laboratory of Spectral Imaging&Intelligent Sense (JSGP202105)Fundamental Research Funds for the Central Universities (30922010405,30921011208,30920032101,30919011222)National Major Scientific Instrument Development Project (62227818).
文摘Recently,deep learning has yielded transformative success across optics and photonics,especially in optical metrology.Deep neural networks (DNNs) with a fully convolutional architecture (e.g.,U-Net and its derivatives) have been widely implemented in an end-to-end manner to accomplish various optical metrology tasks,such as fringe denoising,phase unwrapping,and fringe analysis.However,the task of training a DNN to accurately identify an image-to-image transform from massive input and output data pairs seems at best naive,as the physical laws governing the image formation or other domain expertise pertaining to the measurement have not yet been fully exploited in current deep learning practice.To this end,we introduce a physics-informed deep learning method for fringe pattern analysis (PI-FPA) to overcome this limit by integrating a lightweight DNN with a learning-enhanced Fourier transform profilometry (Le FTP) module.By parameterizing conventional phase retrieval methods,the Le FTP module embeds the prior knowledge in the network structure and the loss function to directly provide reliable phase results for new types of samples,while circumventing the requirement of collecting a large amount of high-quality data in supervised learning methods.Guided by the initial phase from Le FTP,the phase recovery ability of the lightweight DNN is enhanced to further improve the phase accuracy at a low computational cost compared with existing end-to-end networks.Experimental results demonstrate that PI-FPA enables more accurate and computationally efficient single-shot phase retrieval,exhibiting its excellent generalization to various unseen objects during training.The proposed PI-FPA presents that challenging issues in optical metrology can be potentially overcome through the synergy of physics-priors-based traditional tools and data-driven learning approaches,opening new avenues to achieve fast and accurate single-shot 3D imaging.
基金supported by the Ministry of Science and Technology of China,No.2020AAA0109605(to XL)Meizhou Major Scientific and Technological Innovation PlatformsProjects of Guangdong Provincial Science & Technology Plan Projects,No.2019A0102005(to HW).
文摘Early identification and treatment of stroke can greatly improve patient outcomes and quality of life.Although clinical tests such as the Cincinnati Pre-hospital Stroke Scale(CPSS)and the Face Arm Speech Test(FAST)are commonly used for stroke screening,accurate administration is dependent on specialized training.In this study,we proposed a novel multimodal deep learning approach,based on the FAST,for assessing suspected stroke patients exhibiting symptoms such as limb weakness,facial paresis,and speech disorders in acute settings.We collected a dataset comprising videos and audio recordings of emergency room patients performing designated limb movements,facial expressions,and speech tests based on the FAST.We compared the constructed deep learning model,which was designed to process multi-modal datasets,with six prior models that achieved good action classification performance,including the I3D,SlowFast,X3D,TPN,TimeSformer,and MViT.We found that the findings of our deep learning model had a higher clinical value compared with the other approaches.Moreover,the multi-modal model outperformed its single-module variants,highlighting the benefit of utilizing multiple types of patient data,such as action videos and speech audio.These results indicate that a multi-modal deep learning model combined with the FAST could greatly improve the accuracy and sensitivity of early stroke identification of stroke,thus providing a practical and powerful tool for assessing stroke patients in an emergency clinical setting.
文摘Deep neural networks(DNNs)are effective in solving both forward and inverse problems for nonlinear partial differential equations(PDEs).However,conventional DNNs are not effective in handling problems such as delay differential equations(DDEs)and delay integrodifferential equations(DIDEs)with constant delays,primarily due to their low regularity at delayinduced breaking points.In this paper,a DNN method that combines multi-task learning(MTL)which is proposed to solve both the forward and inverse problems of DIDEs.The core idea of this approach is to divide the original equation into multiple tasks based on the delay,using auxiliary outputs to represent the integral terms,followed by the use of MTL to seamlessly incorporate the properties at the breaking points into the loss function.Furthermore,given the increased training dificulty associated with multiple tasks and outputs,we employ a sequential training scheme to reduce training complexity and provide reference solutions for subsequent tasks.This approach significantly enhances the approximation accuracy of solving DIDEs with DNNs,as demonstrated by comparisons with traditional DNN methods.We validate the effectiveness of this method through several numerical experiments,test various parameter sharing structures in MTL and compare the testing results of these structures.Finally,this method is implemented to solve the inverse problem of nonlinear DIDE and the results show that the unknown parameters of DIDE can be discovered with sparse or noisy data.
基金supported by the National Key Research and Development Program of China(Grant No.2023YFC3009400)the National Natural Science Foundation of China(Grant Nos.42307218 and U2239251).
文摘The current deep learning models for braced excavation cannot predict deformation from the beginning of excavation due to the need for a substantial corpus of sufficient historical data for training purposes.To address this issue,this study proposes a transfer learning model based on a sequence-to-sequence twodimensional(2D)convolutional long short-term memory neural network(S2SCL2D).The model can use the existing data from other adjacent similar excavations to achieve wall deflection prediction once a limited amount of monitoring data from the target excavation has been recorded.In the absence of adjacent excavation data,numerical simulation data from the target project can be employed instead.A weight update strategy is proposed to improve the prediction accuracy by integrating the stochastic gradient masking with an early stopping mechanism.To illustrate the proposed methodology,an excavation project in Hangzhou,China is adopted.The proposed deep transfer learning model,which uses either adjacent excavation data or numerical simulation data as the source domain,shows a significant improvement in performance when compared to the non-transfer learning model.Using the simulation data from the target project even leads to better prediction performance than using the actual monitoring data from other adjacent excavations.The results demonstrate that the proposed model can reasonably predict the deformation with limited data from the target project.
基金supported by the ONR Vannevar Bush Faculty Fellowship(Grant No.N00014-22-1-2795).
文摘Large language models(LLMs)have emerged as powerful tools for addressing a wide range of problems,including those in scientific computing,particularly in solving partial differential equations(PDEs).However,different models exhibit distinct strengths and preferences,resulting in varying levels of performance.In this paper,we compare the capabilities of the most advanced LLMs—DeepSeek,ChatGPT,and Claude—along with their reasoning-optimized versions in addressing computational challenges.Specifically,we evaluate their proficiency in solving traditional numerical problems in scientific computing as well as leveraging scientific machine learning techniques for PDE-based problems.We designed all our experiments so that a nontrivial decision is required,e.g,defining the proper space of input functions for neural operator learning.Our findings show that reasoning and hybrid-reasoning models consistently and significantly outperform non-reasoning ones in solving challenging problems,with ChatGPT o3-mini-high generally offering the fastest reasoning speed.
文摘Bearing is an indispensable key component in mechanical equipment,and its working state is directly related to the stability and safety of the whole equipment.In recent years,with the rapid development of artificial intelligence technology,especially the breakthrough of deep learning technology,it provides a new idea for bearing fault diagnosis.Deep learning can automatically learn features from a large amount of data,has a strong nonlinear modeling ability,and can effectively solve the problems existing in traditional methods.Aiming at the key problems in bearing fault diagnosis,this paper studies the fault diagnosis method based on deep learning,which not only provides a new solution for bearing fault diagnosis but also provides a reference for the application of deep learning in other mechanical fault diagnosis fields.
文摘In computer vision and artificial intelligence,automatic facial expression-based emotion identification of humans has become a popular research and industry problem.Recent demonstrations and applications in several fields,including computer games,smart homes,expression analysis,gesture recognition,surveillance films,depression therapy,patientmonitoring,anxiety,and others,have brought attention to its significant academic and commercial importance.This study emphasizes research that has only employed facial images for face expression recognition(FER),because facial expressions are a basic way that people communicate meaning to each other.The immense achievement of deep learning has resulted in a growing use of its much architecture to enhance efficiency.This review is on machine learning,deep learning,and hybrid methods’use of preprocessing,augmentation techniques,and feature extraction for temporal properties of successive frames of data.The following section gives a brief summary of assessment criteria that are accessible to the public and then compares them with benchmark results the most trustworthy way to assess FER-related research topics statistically.In this review,a brief synopsis of the subject matter may be beneficial for novices in the field of FER as well as seasoned scholars seeking fruitful avenues for further investigation.The information conveys fundamental knowledge and provides a comprehensive understanding of the most recent state-of-the-art research.
基金Supported by Clinical Trials from the Third Affiliated Hospital of Soochow University,No.2024-156Changzhou Science and Technology Program,No.CJ20244017。
文摘BACKGROUND Hepatocellular carcinoma(HCC)is a prevalent and life-threatening cancer with increasing incidence worldwide.High Ki-67 risk stratification is closely associated with higher recurrence rates and worse outcomes following curative therapies in patients with HCC.However,the performance of radiomic and deep transfer learning(DTL)models derived from biparametric magnetic resonance imaging(bpMRI)in predicting Ki-67 risk stratification and recurrence-free survival(RFS)in patients with HCC remains limited.AIM To develop a nomogram model integrating bpMRI-based radiomic and DTL signatures for predicting Ki-67 risk stratification and RFS in patients with HCC.METHODS This study included 198 patients with histopathologically confirmed HCC who underwent preoperative bpMRI.Ki-67 risk stratification was categorized as high(>20%)or low(≤20%)according to immunohistochemical staining.Radiomic and DTL signatures were extracted from the T2-weighted and arterial-phase images and combined through a random forest algorithm to establish radiomic and DTL models,respectively.Multivariate regression analysis identified clinical risk factors for high Ki-67 risk stratification,and a predictive nomogram model was developed.RESULTS A nonsmooth margin and the absence of an enhanced capsule were independent factors for high Ki-67 risk stratification.The area under the curve(AUC)of the clinical model was 0.77,while those of the radiomic and DTL models were 0.81 and 0.87,respectively,for the prediction of high Ki-67 risk stratification,and the nomogram model achieved a better AUC of 0.92.The median RFS times for patients with high and low Ki-67 risk stratification were 33.00 months and 66.73 months,respectively(P<0.001).Additionally,patients who were predicted to have high Ki-67 risk stratification by the nomogram model had a lower median RFS than those who were predicted to have low Ki-67 risk stratification(33.53 vs 66.74 months,P=0.007).CONCLUSION Our developed nomogram model demonstrated good performance in predicting Ki-67 risk stratification and predicting survival outcomes in patients with HCC.
基金upported by the National Key Research and Development Program of China(Grant No.:2023YFF1204904)the National Natural Science Foundation of China(Grant Nos.:U23A20530 and 82173746)Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism(Shanghai Municipal Education Commission,China).
文摘Negative logarithm of the acid dissociation constant(pK_(a))significantly influences the absorption,dis-tribution,metabolism,excretion,and toxicity(ADMET)properties of molecules and is a crucial indicator in drug research.Given the rapid and accurate characteristics of computational methods,their role in predicting drug properties is increasingly important.Although many pK_(a) prediction models currently exist,they often focus on enhancing model precision while neglecting interpretability.In this study,we present GraFpKa,a pK_(a) prediction model using graph neural networks(GNNs)and molecular finger-prints.The results show that our acidic and basic models achieved mean absolute errors(MAEs)of 0.621 and 0.402,respectively,on the test set,demonstrating good predictive performance.Notably,to improve interpretability,GraFpKa also incorporates Integrated Gradients(IGs),providing a clearer visual description of the atoms significantly affecting the pK_(a) values.The high reliability and interpretability of GraFpKa ensure accurate pKa predictions while also facilitating a deeper understanding of the relation-ship between molecular structure and pK_(a) values,making it a valuable tool in the field of pK_(a) prediction.
基金Deep-time Digital Earth(DDE)Big Science Program(No.GJ-C03-SGF-2025-004)National Natural Science Foundation of China(No.42394063)Sichuan Science and Technology Program(No.2025ZNSFSC0325).
文摘Topographic maps,as essential tools and sources of information for geographic research,contain precise spatial locations and rich map features,and they illustrate spatio-temporal information on the distribution and differences of various surface features.Currently,topographic maps are mainly stored in raster and vector formats.Extraction of the spatio-temporal knowledge in the maps—such as spatial distribution patterns,feature relationships,and dynamic evolution—still primarily relies on manual interpretation.However,manual interpretation is time-consuming and laborious,especially for large-scale,long-term map knowledge extraction and application.With the development of artificial intelligence technology,it is possible to improve the automation level of map knowledge interpretation.Therefore,the present study proposes an automatic interpretation method for raster topographic map knowledge based on deep learning.To address the limitations of current data-driven intelligent technology in learning map spatial relations and cognitive logic,we establish a formal description of map knowledge by mapping the relationship between map knowledge and features,thereby ensuring interpretation accuracy.Subsequently,deep learning techniques are employed to extract map features automatically,and the spatio-temporal knowledge is constructed by combining formal descriptions of geographic feature knowledge.Validation experiments demonstrate that the proposed method effectively achieves automatic interpretation of spatio-temporal knowledge of geographic features in maps,with an accuracy exceeding 80%.The findings of the present study contribute to machine understanding of spatio-temporal differences in map knowledge and advances the intelligent interpretation and utilization of cartographic information.
文摘Multimodal deep learning has emerged as a key paradigm in contemporary medical diagnostics,advancing precision medicine by enabling integration and learning from diverse data sources.The exponential growth of high-dimensional healthcare data,encompassing genomic,transcriptomic,and other omics profiles,as well as radiological imaging and histopathological slides,makes this approach increasingly important because,when examined separately,these data sources only offer a fragmented picture of intricate disease processes.Multimodal deep learning leverages the complementary properties of multiple data modalities to enable more accurate prognostic modeling,more robust disease characterization,and improved treatment decision-making.This review provides a comprehensive overview of the current state of multimodal deep learning approaches in medical diagnosis.We classify and examine important application domains,such as(1)radiology,where automated report generation and lesion detection are facilitated by image-text integration;(2)histopathology,where fusion models improve tumor classification and grading;and(3)multi-omics,where molecular subtypes and latent biomarkers are revealed through cross-modal learning.We provide an overview of representative research,methodological advancements,and clinical consequences for each domain.Additionally,we critically analyzed the fundamental issues preventing wider adoption,including computational complexity(particularly in training scalable,multi-branch networks),data heterogeneity(resulting from modality-specific noise,resolution variations,and inconsistent annotations),and the challenge of maintaining significant cross-modal correlations during fusion.These problems impede interpretability,which is crucial for clinical trust and use,in addition to performance and generalizability.Lastly,we outline important areas for future research,including the development of standardized protocols for harmonizing data,the creation of lightweight and interpretable fusion architectures,the integration of real-time clinical decision support systems,and the promotion of cooperation for federated multimodal learning.Our goal is to provide researchers and clinicians with a concise overview of the field’s present state,enduring constraints,and exciting directions for further research through this review.
基金the“Intelligent Recognition Industry Service Center”as part of the Featured Areas Research Center Program under the Higher Education Sprout Project by the Ministry of Education(MOE)in Taiwan,and the National Science and Technology Council,Taiwan,under grants 113-2221-E-224-041 and 113-2622-E-224-002.Additionally,partial support was provided by Isuzu Optics Corporation.
文摘Liver cancer remains a leading cause of mortality worldwide,and precise diagnostic tools are essential for effective treatment planning.Liver Tumors(LTs)vary significantly in size,shape,and location,and can present with tissues of similar intensities,making automatically segmenting and classifying LTs from abdominal tomography images crucial and challenging.This review examines recent advancements in Liver Segmentation(LS)and Tumor Segmentation(TS)algorithms,highlighting their strengths and limitations regarding precision,automation,and resilience.Performance metrics are utilized to assess key detection algorithms and analytical methods,emphasizing their effectiveness and relevance in clinical contexts.The review also addresses ongoing challenges in liver tumor segmentation and identification,such as managing high variability in patient data and ensuring robustness across different imaging conditions.It suggests directions for future research,with insights into technological advancements that can enhance surgical planning and diagnostic accuracy by comparing popular methods.This paper contributes to a comprehensive understanding of current liver tumor detection techniques,provides a roadmap for future innovations,and improves diagnostic and therapeutic outcomes for liver cancer by integrating recent progress with remaining challenges.
基金supported by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,under grant no.(GPIP:13-612-2024).
文摘App reviews are crucial in influencing user decisions and providing essential feedback for developers to improve their products.Automating the analysis of these reviews is vital for efficient review management.While traditional machine learning(ML)models rely on basic word-based feature extraction,deep learning(DL)methods,enhanced with advanced word embeddings,have shown superior performance.This research introduces a novel aspectbased sentiment analysis(ABSA)framework to classify app reviews based on key non-functional requirements,focusing on usability factors:effectiveness,efficiency,and satisfaction.We propose a hybrid DL model,combining BERT(Bidirectional Encoder Representations from Transformers)with BiLSTM(Bidirectional Long Short-Term Memory)and CNN(Convolutional Neural Networks)layers,to enhance classification accuracy.Comparative analysis against state-of-the-art models demonstrates that our BERT-BiLSTM-CNN model achieves exceptional performance,with precision,recall,F1-score,and accuracy of 96%,87%,91%,and 94%,respectively.Thesignificant contributions of this work include a refined ABSA-based relabeling framework,the development of a highperformance classifier,and the comprehensive relabeling of the Instagram App Reviews dataset.These advancements provide valuable insights for software developers to enhance usability and drive user-centric application development.
基金supported in part by the Guangxi Science and Technology Major Program under grant AA22068067the Guangxi Natural Science Foundation under grant 2023GXNSFAA026236 and 2024GXNSFDA010064the National Natural Science Foundation of China under project 62172119.
文摘As more and more devices in Cyber-Physical Systems(CPS)are connected to the Internet,physical components such as programmable logic controller(PLC),sensors,and actuators are facing greater risks of network attacks,and fast and accurate attack detection techniques are crucial.The key problem in distinguishing between normal and abnormal sequences is to model sequential changes in a large and diverse field of time series.To address this issue,we propose an anomaly detection method based on distributed deep learning.Our method uses a bilateral filtering algorithm for sequential sequences to remove noise in the time series,which can maintain the edge of discrete features.We use a distributed linear deep learning model to establish a sequential prediction model and adjust the threshold for anomaly detection based on the prediction error of the validation set.Our method can not only detect abnormal attacks but also locate the sensors that cause anomalies.We conducted experiments on the Secure Water Treatment(SWAT)and Water Distribution(WADI)public datasets.The experimental results show that our method is superior to the baseline method in identifying the types of attacks and detecting efficiency.
基金co-supported by the National Natural Science Foundation of China(No.62103432)the China Postdoctoral Science Foundation(No.284881)the Young Talent fund of University Association for Science and Technology in Shaanxi,China(No.20210108)。
文摘Exo-atmospheric vehicles are constrained by limited maneuverability,which leads to the contradiction between evasive maneuver and precision strike.To address the problem of Integrated Evasion and Impact(IEI)decision under multi-constraint conditions,a hierarchical intelligent decision-making method based on Deep Reinforcement Learning(DRL)was proposed.First,an intelligent decision-making framework of“DRL evasion decision”+“impact prediction guidance decision”was established:it takes the impact point deviation correction ability as the constraint and the maximum miss distance as the objective,and effectively solves the problem of poor decisionmaking effect caused by the large IEI decision space.Second,to solve the sparse reward problem faced by evasion decision-making,a hierarchical decision-making method consisting of maneuver timing decision and maneuver duration decision was proposed,and the corresponding Markov Decision Process(MDP)was designed.A detailed simulation experiment was designed to analyze the advantages and computational complexity of the proposed method.Simulation results show that the proposed model has good performance and low computational resource requirement.The minimum miss distance is 21.3 m under the condition of guaranteeing the impact point accuracy,and the single decision-making time is 4.086 ms on an STM32F407 single-chip microcomputer,which has engineering application value.
