Deep neural networks(DNNs)have found extensive applications in safety-critical artificial intelligence systems,such as autonomous driving and facial recognition systems.However,recent research has revealed their susce...Deep neural networks(DNNs)have found extensive applications in safety-critical artificial intelligence systems,such as autonomous driving and facial recognition systems.However,recent research has revealed their susceptibility to backdoors maliciously injected by adversaries.This vulnerability arises due to the intricate architecture and opacity of DNNs,resulting in numerous redundant neurons embedded within the models.Adversaries exploit these vulnerabilities to conceal malicious backdoor information within DNNs,thereby causing erroneous outputs and posing substantial threats to the efficacy of DNN-based applications.This article presents a comprehensive survey of backdoor attacks against DNNs and the countermeasure methods employed to mitigate them.Initially,we trace the evolution of the concept from traditional backdoor attacks to backdoor attacks against DNNs,highlighting the feasibility and practicality of generating backdoor attacks against DNNs.Subsequently,we provide an overview of notable works encompassing various attack and defense strategies,facilitating a comparative analysis of their approaches.Through these discussions,we offer constructive insights aimed at refining these techniques.Finally,we extend our research perspective to the domain of large language models(LLMs)and synthesize the characteristics and developmental trends of backdoor attacks and defense methods targeting LLMs.Through a systematic review of existing studies on backdoor vulnerabilities in LLMs,we identify critical open challenges in this field and propose actionable directions for future research.展开更多
Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression...Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.展开更多
The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the ...The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.展开更多
The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based ...The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.展开更多
The development of deep learning has revolutionized image recognition technology.How to design faster and more accurate image classification algorithms has become our research interests.In this paper,we propose a new ...The development of deep learning has revolutionized image recognition technology.How to design faster and more accurate image classification algorithms has become our research interests.In this paper,we propose a new algorithm called stochastic depth networks with deep energy model(SADIE),and the model improves stochastic depth neural network with deep energy model to provide attributes of images and analysis their characteristics.First,the Bernoulli distribution probability is used to select the current layer of the neural network to prevent gradient dispersion during training.Then in the backpropagation process,the energy function is designed to optimize the target loss function of the neural network.We also explored the possibility of using Adam and SGD combination optimization in deep neural networks.Finally,we use training data to train our network based on deep energy model and testing data to verify the performance of the model.The results we finally obtained in this research include the Classified labels of images.The impacts of our obtained results show that our model has high accuracy and performance.展开更多
To obtain excellent regression results under the condition of small sample hyperspectral data,a deep neural network with simulated annealing(SA-DNN)is proposed.According to the characteristics of data,the attention me...To obtain excellent regression results under the condition of small sample hyperspectral data,a deep neural network with simulated annealing(SA-DNN)is proposed.According to the characteristics of data,the attention mechanism was applied to make the network pay more attention to effective features,thereby improving the operating efficiency.By introducing an improved activation function,the data correlation was reduced based on increasing the operation rate,and the problem of over-fitting was alleviated.By introducing simulated annealing,the network chose the optimal learning rate by itself,which avoided falling into the local optimum to the greatest extent.To evaluate the performance of the SA-DNN,the coefficient of determination(R^(2)),root mean square error(RMSE),and other metrics were used to evaluate the model.The results show that the performance of the SA-DNN is significantly better than other traditional methods.展开更多
As a typical physical retrieval algorithm for retrieving atmospheric parameters,one-dimensional variational(1 DVAR)algorithm is widely used in various climate and meteorological communities and enjoys an important pos...As a typical physical retrieval algorithm for retrieving atmospheric parameters,one-dimensional variational(1 DVAR)algorithm is widely used in various climate and meteorological communities and enjoys an important position in the field of microwave remote sensing.Among algorithm parameters affecting the performance of the 1 DVAR algorithm,the accuracy of the microwave radiative transfer model for calculating the simulated brightness temperature is the fundamental constraint on the retrieval accuracies of the 1 DVAR algorithm for retrieving atmospheric parameters.In this study,a deep neural network(DNN)is used to describe the nonlinear relationship between atmospheric parameters and satellite-based microwave radiometer observations,and a DNN-based radiative transfer model is developed and applied to the 1 DVAR algorithm to carry out retrieval experiments of the atmospheric temperature and humidity profiles.The retrieval results of the temperature and humidity profiles from the Microwave Humidity and Temperature Sounder(MWHTS)onboard the Feng-Yun-3(FY-3)satellite show that the DNN-based radiative transfer model can obtain higher accuracy for simulating MWHTS observations than that of the operational radiative transfer model RTTOV,and also enables the 1 DVAR algorithm to obtain higher retrieval accuracies of the temperature and humidity profiles.In this study,the DNN-based radiative transfer model applied to the 1 DVAR algorithm can fundamentally improve the retrieval accuracies of atmospheric parameters,which may provide important reference for various applied studies in atmospheric sciences.展开更多
Blades are essential components of wind turbines.Reducing their fatigue loads during operation helps to extend their lifespan,but it is difficult to quickly and accurately calculate the fatigue loads of blades.To solv...Blades are essential components of wind turbines.Reducing their fatigue loads during operation helps to extend their lifespan,but it is difficult to quickly and accurately calculate the fatigue loads of blades.To solve this problem,this paper innovatively designs a data-driven blade load modeling method based on a deep learning framework through mechanism analysis,feature selection,and model construction.In the mechanism analysis part,the generation mechanism of blade loads and the load theoretical calculationmethod based on material damage theory are analyzed,and four measurable operating state parameters related to blade loads are screened;in the feature extraction part,15 characteristic indicators of each screened parameter are extracted in the time and frequency domain,and feature selection is completed through correlation analysis with blade loads to determine the input parameters of data-driven modeling;in the model construction part,a deep neural network based on feedforward and feedback propagation is designed to construct the nonlinear coupling relationship between the unit operating parameter characteristics and blade loads.The results show that the proposed method mines the wind turbine operating state characteristics highly correlated with the blade load,such as the standard deviation of wind speed.The model built using these characteristics has reasonable calculation and fitting capabilities for the blade load and shows a better fitting level for untrained out-of-sample data than the traditional scheme.Based on the mean absolute percentage error calculation,the modeling accuracy of the two blade loads can reach more than 90%and 80%,respectively,providing a good foundation for the subsequent optimization control to suppress the blade load.展开更多
With the rapid growth of complexity and functionality of modern electronic systems, creating precise behavioral models of nonlinear circuits has become an attractive topic. Deep neural networks (DNNs) have been recogn...With the rapid growth of complexity and functionality of modern electronic systems, creating precise behavioral models of nonlinear circuits has become an attractive topic. Deep neural networks (DNNs) have been recognized as a powerful tool for nonlinear system modeling. To characterize the behavior of nonlinear circuits, a DNN based modeling approach is proposed in this paper. The procedure is illustrated by modeling a power amplifier (PA), which is a typical nonlinear circuit in electronic systems. The PA model is constructed based on a feedforward neural network with three hidden layers, and then Multisim circuit simulator is applied to generating the raw training data. Training and validation are carried out in Tensorflow deep learning framework. Compared with the commonly used polynomial model, the proposed DNN model exhibits a faster convergence rate and improves the mean squared error by 13 dB. The results demonstrate that the proposed DNN model can accurately depict the input-output characteristics of nonlinear circuits in both training and validation data sets.展开更多
The surge of large-scale models in recent years has led to breakthroughs in numerous fields,but it has also introduced higher computational costs and more complex network architectures.These increasingly large and int...The surge of large-scale models in recent years has led to breakthroughs in numerous fields,but it has also introduced higher computational costs and more complex network architectures.These increasingly large and intricate networks pose challenges for deployment and execution while also exacerbating the issue of network over-parameterization.To address this issue,various network compression techniques have been developed,such as network pruning.A typical pruning algorithm follows a three-step pipeline involving training,pruning,and retraining.Existing methods often directly set the pruned filters to zero during retraining,significantly reducing the parameter space.However,this direct pruning strategy frequently results in irreversible information loss.In the early stages of training,a network still contains much uncertainty,and evaluating filter importance may not be sufficiently rigorous.To manage the pruning process effectively,this paper proposes a flexible neural network pruning algorithm based on the logistic growth differential equation,considering the characteristics of network training.Unlike other pruning algorithms that directly reduce filter weights,this algorithm introduces a three-stage adaptive weight decay strategy inspired by the logistic growth differential equation.It employs a gentle decay rate in the initial training stage,a rapid decay rate during the intermediate stage,and a slower decay rate in the network convergence stage.Additionally,the decay rate is adjusted adaptively based on the filter weights at each stage.By controlling the adaptive decay rate at each stage,the pruning of neural network filters can be effectively managed.In experiments conducted on the CIFAR-10 and ILSVRC-2012 datasets,the pruning of neural networks significantly reduces the floating-point operations while maintaining the same pruning rate.Specifically,when implementing a 30%pruning rate on the ResNet-110 network,the pruned neural network not only decreases floating-point operations by 40.8%but also enhances the classification accuracy by 0.49%compared to the original network.展开更多
With the rapid development of artificial intelligence techniques such as neural networks,data-driven machine learning methods are popular in improving and constructing turbulence models.For high Reynolds number turbul...With the rapid development of artificial intelligence techniques such as neural networks,data-driven machine learning methods are popular in improving and constructing turbulence models.For high Reynolds number turbulence in aerodynamics,our previous work built a data-driven model applicable to subsonic airfoil flows with different free stream conditions.The results calculated by the proposed model are encouraging.In this work,we aim to model the turbulence of transonic wing flows with fully connected deep neural networks,where there is less research at present.The proposed model is driven by two flow cases of the ONERA(Office National d'Etudes et de Recherches Aerospatiales)wing and coupled with the Navier-Stokes equation solver.Four subcritical and transonic benchmark cases of different wings are used to evaluate the model performance.The iteration process is stable,and final convergence is achieved.The proposed model can be used to surrogate the traditional Reynolds averaged Navier-Stokes turbulence model.Compared with the data calculated by the Spallart-Allmaras model,the results show that the proposed model can be well generalized to the test cases.The mean relative error of the drag coefficient at different sections is below 4%for each case.This work demonstrates that modeling turbulence by data-driven methods is feasible and that our modeling pattern is effective.展开更多
Historically,yarn-dyed plaid fabrics(YDPFs)have enjoyed enduring popularity with many rich plaid patterns,but production data are still classified and searched only according to production parameters.The process does ...Historically,yarn-dyed plaid fabrics(YDPFs)have enjoyed enduring popularity with many rich plaid patterns,but production data are still classified and searched only according to production parameters.The process does not satisfy the visual needs of sample order production,fabric design,and stock management.This study produced an image dataset for YDPFs,collected from 10,661 fabric samples.The authors believe that the dataset will have significant utility in further research into YDPFs.Convolutional neural networks,such as VGG,ResNet,and DenseNet,with different hyperparameter groups,seemed themost promising tools for the study.This paper reports on the authors’exhaustive evaluation of the YDPF dataset.With an overall accuracy of 88.78%,CNNs proved to be effective in YDPF image classification.This was true even for the low accuracy of Windowpane fabrics,which often mistakenly includes the Prince ofWales pattern.Image classification of traditional patterns is also improved by utilizing the strip pooling model to extract local detail features and horizontal and vertical directions.The strip pooling model characterizes the horizontal and vertical crisscross patterns of YDPFs with considerable success.The proposed method using the strip pooling model(SPM)improves the classification performance on the YDPF dataset by 2.64%for ResNet18,by 3.66%for VGG16,and by 3.54%for DenseNet121.The results reveal that the SPM significantly improves YDPF classification accuracy and reduces the error rate of Windowpane patterns as well.展开更多
Wheat is a critical crop,extensively consumed worldwide,and its production enhancement is essential to meet escalating demand.The presence of diseases like stem rust,leaf rust,yellow rust,and tan spot significantly di...Wheat is a critical crop,extensively consumed worldwide,and its production enhancement is essential to meet escalating demand.The presence of diseases like stem rust,leaf rust,yellow rust,and tan spot significantly diminishes wheat yield,making the early and precise identification of these diseases vital for effective disease management.With advancements in deep learning algorithms,researchers have proposed many methods for the automated detection of disease pathogens;however,accurately detectingmultiple disease pathogens simultaneously remains a challenge.This challenge arises due to the scarcity of RGB images for multiple diseases,class imbalance in existing public datasets,and the difficulty in extracting features that discriminate between multiple classes of disease pathogens.In this research,a novel method is proposed based on Transfer Generative Adversarial Networks for augmenting existing data,thereby overcoming the problems of class imbalance and data scarcity.This study proposes a customized architecture of Vision Transformers(ViT),where the feature vector is obtained by concatenating features extracted from the custom ViT and Graph Neural Networks.This paper also proposes a Model AgnosticMeta Learning(MAML)based ensemble classifier for accurate classification.The proposedmodel,validated on public datasets for wheat disease pathogen classification,achieved a test accuracy of 99.20%and an F1-score of 97.95%.Compared with existing state-of-the-art methods,this proposed model outperforms in terms of accuracy,F1-score,and the number of disease pathogens detection.In future,more diseases can be included for detection along with some other modalities like pests and weed.展开更多
The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method in...The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.展开更多
Urban traffic prediction with high precision is always the unremitting pursuit of intelligent transportation systems and is instrumental in bringing smart cities into reality.The fundamental challenges for traffic pre...Urban traffic prediction with high precision is always the unremitting pursuit of intelligent transportation systems and is instrumental in bringing smart cities into reality.The fundamental challenges for traffic prediction lie in the accurate modelling of spatial and temporal traffic dynamics.Existing approaches mainly focus on modelling the traffic data itself,but do not explore the traffic correlations implicit in origin-destination(OD)data.In this paper,we propose STOD-Net,a dynamic spatial-temporal OD feature-enhanced deep network,to simultaneously predict the in-traffic and out-traffic for each and every region of a city.We model the OD data as dynamic graphs and adopt graph neural networks in STOD-Net to learn a low-dimensional representation for each region.As per the region feature,we design a gating mechanism and operate it on the traffic feature learning to explicitly capture spatial correlations.To further capture the complicated spatial and temporal dependencies among different regions,we propose a novel joint feature,learning block in STOD-Net and transfer the hybrid OD features to each block to make the learning process spatiotemporal-aware.We evaluate the effectiveness of STOD-Net on two benchmark datasets,and experimental results demonstrate that it outperforms the state-of-the-art by approximately 5%in terms of prediction accuracy and considerably improves prediction stability up to 80%in terms of standard deviation.展开更多
Unmanned aerial vehicle(UAV)tracking is a critical task in surveillance,security,and autonomous navigation applications.In this study,we propose graph neural network-tracker(GNN-tracker),a novel GNN-based UAV tracking...Unmanned aerial vehicle(UAV)tracking is a critical task in surveillance,security,and autonomous navigation applications.In this study,we propose graph neural network-tracker(GNN-tracker),a novel GNN-based UAV tracking framework that effectively integrates graph-based spatial-temporal modelling,Transformer-based feature extraction,and multi-sensor fusion to enhance tracking robustness and accuracy.Unlike traditional tracking approaches,GNNtracker dynamically constructs a spatiotemporal graph representation,improving identity consistency and reducing tracking errors under OCC-heavy scenarios.Experimental evaluations on optical,thermal,and fused UAV datasets demonstrate the superiority of GNN-tracker(fused)over state-of-the-art methods.The proposed model achieves multiple object tracking accuracy(MOTA)scores of 91.4%(fused),89.1%(optical),and 86.3%(thermal),surpassing TransT by 8.9%in MOTA and 7.7%in higher order tracking accuracy(HOTA).The HOTA scores of 82.3%(fused),80.1%(optical),and 78.7%(thermal)validate its strong object association capabilities,while its frames per second of 58.9(fused),56.8(optical),and 54.3(thermal)ensures real-time performance.Additionally,ablation studies confirm the essential role of graph-based modelling and multi-sensor fusion,with performance drops of up to 8.9%in MOTA when these components are removed.Thus,GNN-tracker(fused)offers a highly accurate,robust,and efficient UAV tracking solution,effectively addressing real-world challenges across diverse environmental conditions and multiple sensor modalities.展开更多
Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising t...Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising technologies today,plays a crucial role in the effective assessment of water body health,which is essential for water resource management.This study models using both the original dataset and a dataset augmented with Generative Adversarial Networks(GAN).It integrates optimization algorithms(OA)with Convolutional Neural Networks(CNN)to propose a comprehensive water quality model evaluation method aiming at identifying the optimal models for different pollutants.Specifically,after preprocessing the spectral dataset,data augmentation was conducted to obtain two datasets.Then,six new models were developed on these datasets using particle swarm optimization(PSO),genetic algorithm(GA),and simulated annealing(SA)combined with CNN to simulate and forecast the concentrations of three water pollutants:Chemical Oxygen Demand(COD),Total Nitrogen(TN),and Total Phosphorus(TP).Finally,seven model evaluation methods,including uncertainty analysis,were used to evaluate the constructed models and select the optimal models for the three pollutants.The evaluation results indicate that the GPSCNN model performed best in predicting COD and TP concentrations,while the GGACNN model excelled in TN concentration prediction.Compared to existing technologies,the proposed models and evaluation methods provide a more comprehensive and rapid approach to water body prediction and assessment,offering new insights and methods for water pollution prevention and control.展开更多
The rapid shift to online education has introduced significant challenges to maintaining academic integrity in remote assessments,as traditional proctoring methods fall short in preventing cheating.The increase in che...The rapid shift to online education has introduced significant challenges to maintaining academic integrity in remote assessments,as traditional proctoring methods fall short in preventing cheating.The increase in cheating during online exams highlights the need for efficient,adaptable detection models to uphold academic credibility.This paper presents a comprehensive analysis of various deep learning models for cheating detection in online proctoring systems,evaluating their accuracy,efficiency,and adaptability.We benchmark several advanced architectures,including EfficientNet,MobileNetV2,ResNet variants and more,using two specialized datasets(OEP and OP)tailored for online proctoring contexts.Our findings reveal that EfficientNetB1 and YOLOv5 achieve top performance on the OP dataset,with EfficientNetB1 attaining a peak accuracy of 94.59% and YOLOv5 reaching a mean average precision(mAP@0.5)of 98.3%.For the OEP dataset,ResNet50-CBAM,YOLOv5 and EfficientNetB0 stand out,with ResNet50-CBAMachieving an accuracy of 93.61% and EfficientNetB0 showing robust detection performance with balanced accuracy and computational efficiency.These results underscore the importance of selectingmodels that balance accuracy and efficiency,supporting scalable,effective cheating detection in online assessments.展开更多
With the continuous deepening of Artificial Neural Network(ANN)research,ANN model structure and function are improving towards diversification and intelligence.However,the model is more evaluated from the pros and con...With the continuous deepening of Artificial Neural Network(ANN)research,ANN model structure and function are improving towards diversification and intelligence.However,the model is more evaluated from the pros and cons of the problem-solving results and the lack of evaluation from the biomimetic aspect of imitating neural networks is not inclusive enough.Hence,a new ANN models evaluation strategy is proposed from the perspective of bionics in response to this problem in the paper.Firstly,four classical neural network models are illustrated:Back Propagation(BP)network,Deep Belief Network(DBN),LeNet5 network,and olfactory bionic model(KIII model),and the neuron transmission mode and equation,network structure,and weight updating principle of the models are analyzed qualitatively.The analysis results show that the KIII model comes closer to the actual biological nervous system compared with other models,and the LeNet5 network simulates the nervous system in depth.Secondly,evaluation indexes of ANN are constructed from the perspective of bionics in this paper:small-world,synchronous,and chaotic characteristics.Finally,the network model is quantitatively analyzed by evaluation indexes from the perspective of bionics.The experimental results show that the DBN network,LeNet5 network,and BP network have synchronous characteristics.And the DBN network and LeNet5 network have certain chaotic characteristics,but there is still a certain distance between the three classical neural networks and actual biological neural networks.The KIII model has certain small-world characteristics in structure,and its network also exhibits synchronization characteristics and chaotic characteristics.Compared with the DBN network,LeNet5 network,and the BP network,the KIII model is closer to the real biological neural network.展开更多
This paper first proposes a new self-learning data-driven methodology that can develop the failure criteria of unknown anisotropic ductile materials from the minimal number of experimental tests.Establishing failure c...This paper first proposes a new self-learning data-driven methodology that can develop the failure criteria of unknown anisotropic ductile materials from the minimal number of experimental tests.Establishing failure criteria of anisotropic ductile materials requires time-consuming tests and manual data evaluation.The proposed method can overcome such practical challenges.The methodology is formalized by combining four ideas:1)The deep learning neural network(DLNN)-based material constitutive model,2)Self-learning inverse finite element(SELIFE)simulation,3)Algorithmic identification of failure points from the selflearned stress-strain curves and 4)Derivation of the failure criteria through symbolic regression of the genetic programming.Stress update and the algorithmic tangent operator were formulated in terms of DLNN parameters for nonlinear finite element analysis.Then,the SELIFE simulation algorithm gradually makes the DLNN model learn highly complex multi-axial stress and strain relationships,being guided by the experimental boundary measurements.Following the failure point identification,a self-learning data-driven failure criteria are eventually developed with the help of a reliable symbolic regression algorithm.The methodology and the self-learning data-driven failure criteria were verified by comparing with a reference failure criteria and simulating with different materials orientations,respectively.展开更多
基金supported in part by the National Natural Science Foundation of China under Grants No.62372087 and No.62072076the Research Fund of State Key Laboratory of Processors under Grant No.CLQ202310the CSC scholarship.
文摘Deep neural networks(DNNs)have found extensive applications in safety-critical artificial intelligence systems,such as autonomous driving and facial recognition systems.However,recent research has revealed their susceptibility to backdoors maliciously injected by adversaries.This vulnerability arises due to the intricate architecture and opacity of DNNs,resulting in numerous redundant neurons embedded within the models.Adversaries exploit these vulnerabilities to conceal malicious backdoor information within DNNs,thereby causing erroneous outputs and posing substantial threats to the efficacy of DNN-based applications.This article presents a comprehensive survey of backdoor attacks against DNNs and the countermeasure methods employed to mitigate them.Initially,we trace the evolution of the concept from traditional backdoor attacks to backdoor attacks against DNNs,highlighting the feasibility and practicality of generating backdoor attacks against DNNs.Subsequently,we provide an overview of notable works encompassing various attack and defense strategies,facilitating a comparative analysis of their approaches.Through these discussions,we offer constructive insights aimed at refining these techniques.Finally,we extend our research perspective to the domain of large language models(LLMs)and synthesize the characteristics and developmental trends of backdoor attacks and defense methods targeting LLMs.Through a systematic review of existing studies on backdoor vulnerabilities in LLMs,we identify critical open challenges in this field and propose actionable directions for future research.
基金supported by the Science and Technology Innovation Key R&D Program of Chongqing(CSTB2025TIAD-STX0032)National Key Research and Development Program of China(2024YFF0908200)+1 种基金the Chongqing Technology Innovation and Application Development Special Key Project(CSTB2024TIAD-KPX0018)the Southwest University Graduate Student Research Innovation(SWUB24051)。
文摘Dear Editor,The letter proposes a tensor low-rank orthogonal compression(TLOC)model for a convolutional neural network(CNN),which facilitates its efficient and highly-accurate low-rank representation.Model compression is crucial for deploying deep neural network(DNN)models on resource-constrained embedded devices.
基金funded by the Deanship of Scientific Research at Princess Nourah bint Abdulrahman University,through the Research Funding Program,Grant No.(FRP-1443-15).
文摘The analysis of Android malware shows that this threat is constantly increasing and is a real threat to mobile devices since traditional approaches,such as signature-based detection,are no longer effective due to the continuously advancing level of sophistication.To resolve this problem,efficient and flexible malware detection tools are needed.This work examines the possibility of employing deep CNNs to detect Android malware by transforming network traffic into image data representations.Moreover,the dataset used in this study is the CIC-AndMal2017,which contains 20,000 instances of network traffic across five distinct malware categories:a.Trojan,b.Adware,c.Ransomware,d.Spyware,e.Worm.These network traffic features are then converted to image formats for deep learning,which is applied in a CNN framework,including the VGG16 pre-trained model.In addition,our approach yielded high performance,yielding an accuracy of 0.92,accuracy of 99.1%,precision of 98.2%,recall of 99.5%,and F1 score of 98.7%.Subsequent improvements to the classification model through changes within the VGG19 framework improved the classification rate to 99.25%.Through the results obtained,it is clear that CNNs are a very effective way to classify Android malware,providing greater accuracy than conventional techniques.The success of this approach also shows the applicability of deep learning in mobile security along with the direction for the future advancement of the real-time detection system and other deeper learning techniques to counter the increasing number of threats emerging in the future.
基金financially supported by the National Natural Science Foundation of China (Nos.51974023 and52374321)the funding of State Key Laboratory of Advanced Metallurgy,University of Science and Technology Beijing,China (No.41620007)。
文摘The amount of oxygen blown into the converter is one of the key parameters for the control of the converter blowing process,which directly affects the tap-to-tap time of converter. In this study, a hybrid model based on oxygen balance mechanism (OBM) and deep neural network (DNN) was established for predicting oxygen blowing time in converter. A three-step method was utilized in the hybrid model. First, the oxygen consumption volume was predicted by the OBM model and DNN model, respectively. Second, a more accurate oxygen consumption volume was obtained by integrating the OBM model and DNN model. Finally, the converter oxygen blowing time was calculated according to the oxygen consumption volume and the oxygen supply intensity of each heat. The proposed hybrid model was verified using the actual data collected from an integrated steel plant in China, and compared with multiple linear regression model, OBM model, and neural network model including extreme learning machine, back propagation neural network, and DNN. The test results indicate that the hybrid model with a network structure of 3 hidden layer layers, 32-16-8 neurons per hidden layer, and 0.1 learning rate has the best prediction accuracy and stronger generalization ability compared with other models. The predicted hit ratio of oxygen consumption volume within the error±300 m^(3)is 96.67%;determination coefficient (R^(2)) and root mean square error (RMSE) are0.6984 and 150.03 m^(3), respectively. The oxygen blow time prediction hit ratio within the error±0.6 min is 89.50%;R2and RMSE are0.9486 and 0.3592 min, respectively. As a result, the proposed model can effectively predict the oxygen consumption volume and oxygen blowing time in the converter.
文摘The development of deep learning has revolutionized image recognition technology.How to design faster and more accurate image classification algorithms has become our research interests.In this paper,we propose a new algorithm called stochastic depth networks with deep energy model(SADIE),and the model improves stochastic depth neural network with deep energy model to provide attributes of images and analysis their characteristics.First,the Bernoulli distribution probability is used to select the current layer of the neural network to prevent gradient dispersion during training.Then in the backpropagation process,the energy function is designed to optimize the target loss function of the neural network.We also explored the possibility of using Adam and SGD combination optimization in deep neural networks.Finally,we use training data to train our network based on deep energy model and testing data to verify the performance of the model.The results we finally obtained in this research include the Classified labels of images.The impacts of our obtained results show that our model has high accuracy and performance.
基金supported by the National Natural Science Foundation of China(Nos.62001023,61922013)Beijing Natural Science Foundation(No.4232013).
文摘To obtain excellent regression results under the condition of small sample hyperspectral data,a deep neural network with simulated annealing(SA-DNN)is proposed.According to the characteristics of data,the attention mechanism was applied to make the network pay more attention to effective features,thereby improving the operating efficiency.By introducing an improved activation function,the data correlation was reduced based on increasing the operation rate,and the problem of over-fitting was alleviated.By introducing simulated annealing,the network chose the optimal learning rate by itself,which avoided falling into the local optimum to the greatest extent.To evaluate the performance of the SA-DNN,the coefficient of determination(R^(2)),root mean square error(RMSE),and other metrics were used to evaluate the model.The results show that the performance of the SA-DNN is significantly better than other traditional methods.
基金National Natural Science Foundation of China(41901297,41806209)Science and Technology Key Project of Henan Province(202102310017)+1 种基金Key Research Projects for the Universities of Henan Province(20A170013)China Postdoctoral Science Foundation(2021M693201)。
文摘As a typical physical retrieval algorithm for retrieving atmospheric parameters,one-dimensional variational(1 DVAR)algorithm is widely used in various climate and meteorological communities and enjoys an important position in the field of microwave remote sensing.Among algorithm parameters affecting the performance of the 1 DVAR algorithm,the accuracy of the microwave radiative transfer model for calculating the simulated brightness temperature is the fundamental constraint on the retrieval accuracies of the 1 DVAR algorithm for retrieving atmospheric parameters.In this study,a deep neural network(DNN)is used to describe the nonlinear relationship between atmospheric parameters and satellite-based microwave radiometer observations,and a DNN-based radiative transfer model is developed and applied to the 1 DVAR algorithm to carry out retrieval experiments of the atmospheric temperature and humidity profiles.The retrieval results of the temperature and humidity profiles from the Microwave Humidity and Temperature Sounder(MWHTS)onboard the Feng-Yun-3(FY-3)satellite show that the DNN-based radiative transfer model can obtain higher accuracy for simulating MWHTS observations than that of the operational radiative transfer model RTTOV,and also enables the 1 DVAR algorithm to obtain higher retrieval accuracies of the temperature and humidity profiles.In this study,the DNN-based radiative transfer model applied to the 1 DVAR algorithm can fundamentally improve the retrieval accuracies of atmospheric parameters,which may provide important reference for various applied studies in atmospheric sciences.
基金supported by Science and Technology Project funding from China Southern Power Grid Corporation No.GDKJXM20230245(031700KC23020003).
文摘Blades are essential components of wind turbines.Reducing their fatigue loads during operation helps to extend their lifespan,but it is difficult to quickly and accurately calculate the fatigue loads of blades.To solve this problem,this paper innovatively designs a data-driven blade load modeling method based on a deep learning framework through mechanism analysis,feature selection,and model construction.In the mechanism analysis part,the generation mechanism of blade loads and the load theoretical calculationmethod based on material damage theory are analyzed,and four measurable operating state parameters related to blade loads are screened;in the feature extraction part,15 characteristic indicators of each screened parameter are extracted in the time and frequency domain,and feature selection is completed through correlation analysis with blade loads to determine the input parameters of data-driven modeling;in the model construction part,a deep neural network based on feedforward and feedback propagation is designed to construct the nonlinear coupling relationship between the unit operating parameter characteristics and blade loads.The results show that the proposed method mines the wind turbine operating state characteristics highly correlated with the blade load,such as the standard deviation of wind speed.The model built using these characteristics has reasonable calculation and fitting capabilities for the blade load and shows a better fitting level for untrained out-of-sample data than the traditional scheme.Based on the mean absolute percentage error calculation,the modeling accuracy of the two blade loads can reach more than 90%and 80%,respectively,providing a good foundation for the subsequent optimization control to suppress the blade load.
文摘With the rapid growth of complexity and functionality of modern electronic systems, creating precise behavioral models of nonlinear circuits has become an attractive topic. Deep neural networks (DNNs) have been recognized as a powerful tool for nonlinear system modeling. To characterize the behavior of nonlinear circuits, a DNN based modeling approach is proposed in this paper. The procedure is illustrated by modeling a power amplifier (PA), which is a typical nonlinear circuit in electronic systems. The PA model is constructed based on a feedforward neural network with three hidden layers, and then Multisim circuit simulator is applied to generating the raw training data. Training and validation are carried out in Tensorflow deep learning framework. Compared with the commonly used polynomial model, the proposed DNN model exhibits a faster convergence rate and improves the mean squared error by 13 dB. The results demonstrate that the proposed DNN model can accurately depict the input-output characteristics of nonlinear circuits in both training and validation data sets.
基金supported by the National Natural Science Foundation of China under Grant No.62172132.
文摘The surge of large-scale models in recent years has led to breakthroughs in numerous fields,but it has also introduced higher computational costs and more complex network architectures.These increasingly large and intricate networks pose challenges for deployment and execution while also exacerbating the issue of network over-parameterization.To address this issue,various network compression techniques have been developed,such as network pruning.A typical pruning algorithm follows a three-step pipeline involving training,pruning,and retraining.Existing methods often directly set the pruned filters to zero during retraining,significantly reducing the parameter space.However,this direct pruning strategy frequently results in irreversible information loss.In the early stages of training,a network still contains much uncertainty,and evaluating filter importance may not be sufficiently rigorous.To manage the pruning process effectively,this paper proposes a flexible neural network pruning algorithm based on the logistic growth differential equation,considering the characteristics of network training.Unlike other pruning algorithms that directly reduce filter weights,this algorithm introduces a three-stage adaptive weight decay strategy inspired by the logistic growth differential equation.It employs a gentle decay rate in the initial training stage,a rapid decay rate during the intermediate stage,and a slower decay rate in the network convergence stage.Additionally,the decay rate is adjusted adaptively based on the filter weights at each stage.By controlling the adaptive decay rate at each stage,the pruning of neural network filters can be effectively managed.In experiments conducted on the CIFAR-10 and ILSVRC-2012 datasets,the pruning of neural networks significantly reduces the floating-point operations while maintaining the same pruning rate.Specifically,when implementing a 30%pruning rate on the ResNet-110 network,the pruned neural network not only decreases floating-point operations by 40.8%but also enhances the classification accuracy by 0.49%compared to the original network.
基金supported by the National Natural Science Foundation of China(Grant Nos.92152301,and 91852115)the National Numerical Wind tunnel Project(Grand No.NNW2018-ZT1B01).
文摘With the rapid development of artificial intelligence techniques such as neural networks,data-driven machine learning methods are popular in improving and constructing turbulence models.For high Reynolds number turbulence in aerodynamics,our previous work built a data-driven model applicable to subsonic airfoil flows with different free stream conditions.The results calculated by the proposed model are encouraging.In this work,we aim to model the turbulence of transonic wing flows with fully connected deep neural networks,where there is less research at present.The proposed model is driven by two flow cases of the ONERA(Office National d'Etudes et de Recherches Aerospatiales)wing and coupled with the Navier-Stokes equation solver.Four subcritical and transonic benchmark cases of different wings are used to evaluate the model performance.The iteration process is stable,and final convergence is achieved.The proposed model can be used to surrogate the traditional Reynolds averaged Navier-Stokes turbulence model.Compared with the data calculated by the Spallart-Allmaras model,the results show that the proposed model can be well generalized to the test cases.The mean relative error of the drag coefficient at different sections is below 4%for each case.This work demonstrates that modeling turbulence by data-driven methods is feasible and that our modeling pattern is effective.
基金This work was supported by China Social Science Foundation under Grant[17CG209]The fabric samples were supported by Jiangsu Sunshine Group and Jiangsu Lianfa Textile Group.
文摘Historically,yarn-dyed plaid fabrics(YDPFs)have enjoyed enduring popularity with many rich plaid patterns,but production data are still classified and searched only according to production parameters.The process does not satisfy the visual needs of sample order production,fabric design,and stock management.This study produced an image dataset for YDPFs,collected from 10,661 fabric samples.The authors believe that the dataset will have significant utility in further research into YDPFs.Convolutional neural networks,such as VGG,ResNet,and DenseNet,with different hyperparameter groups,seemed themost promising tools for the study.This paper reports on the authors’exhaustive evaluation of the YDPF dataset.With an overall accuracy of 88.78%,CNNs proved to be effective in YDPF image classification.This was true even for the low accuracy of Windowpane fabrics,which often mistakenly includes the Prince ofWales pattern.Image classification of traditional patterns is also improved by utilizing the strip pooling model to extract local detail features and horizontal and vertical directions.The strip pooling model characterizes the horizontal and vertical crisscross patterns of YDPFs with considerable success.The proposed method using the strip pooling model(SPM)improves the classification performance on the YDPF dataset by 2.64%for ResNet18,by 3.66%for VGG16,and by 3.54%for DenseNet121.The results reveal that the SPM significantly improves YDPF classification accuracy and reduces the error rate of Windowpane patterns as well.
基金Researchers Supporting Project Number(RSPD2024R 553),King Saud University,Riyadh,Saudi Arabia.
文摘Wheat is a critical crop,extensively consumed worldwide,and its production enhancement is essential to meet escalating demand.The presence of diseases like stem rust,leaf rust,yellow rust,and tan spot significantly diminishes wheat yield,making the early and precise identification of these diseases vital for effective disease management.With advancements in deep learning algorithms,researchers have proposed many methods for the automated detection of disease pathogens;however,accurately detectingmultiple disease pathogens simultaneously remains a challenge.This challenge arises due to the scarcity of RGB images for multiple diseases,class imbalance in existing public datasets,and the difficulty in extracting features that discriminate between multiple classes of disease pathogens.In this research,a novel method is proposed based on Transfer Generative Adversarial Networks for augmenting existing data,thereby overcoming the problems of class imbalance and data scarcity.This study proposes a customized architecture of Vision Transformers(ViT),where the feature vector is obtained by concatenating features extracted from the custom ViT and Graph Neural Networks.This paper also proposes a Model AgnosticMeta Learning(MAML)based ensemble classifier for accurate classification.The proposedmodel,validated on public datasets for wheat disease pathogen classification,achieved a test accuracy of 99.20%and an F1-score of 97.95%.Compared with existing state-of-the-art methods,this proposed model outperforms in terms of accuracy,F1-score,and the number of disease pathogens detection.In future,more diseases can be included for detection along with some other modalities like pests and weed.
基金Science and Technology Funds from the Liaoning Education Department(Serial Number:LJKZ0104).
文摘The motivation for this study is that the quality of deep fakes is constantly improving,which leads to the need to develop new methods for their detection.The proposed Customized Convolutional Neural Network method involves extracting structured data from video frames using facial landmark detection,which is then used as input to the CNN.The customized Convolutional Neural Network method is the date augmented-based CNN model to generate‘fake data’or‘fake images’.This study was carried out using Python and its libraries.We used 242 films from the dataset gathered by the Deep Fake Detection Challenge,of which 199 were made up and the remaining 53 were real.Ten seconds were allotted for each video.There were 318 videos used in all,199 of which were fake and 119 of which were real.Our proposedmethod achieved a testing accuracy of 91.47%,loss of 0.342,and AUC score of 0.92,outperforming two alternative approaches,CNN and MLP-CNN.Furthermore,our method succeeded in greater accuracy than contemporary models such as XceptionNet,Meso-4,EfficientNet-BO,MesoInception-4,VGG-16,and DST-Net.The novelty of this investigation is the development of a new Convolutional Neural Network(CNN)learning model that can accurately detect deep fake face photos.
基金supported by the National Natural Science Foundation of China,Grant/Award Number:62401338by the Shandong Province Excellent Youth Science Fund Project(Overseas),Grant/Award Number:2024HWYQ-028by the Fundamental Research Funds of Shandong University.
文摘Urban traffic prediction with high precision is always the unremitting pursuit of intelligent transportation systems and is instrumental in bringing smart cities into reality.The fundamental challenges for traffic prediction lie in the accurate modelling of spatial and temporal traffic dynamics.Existing approaches mainly focus on modelling the traffic data itself,but do not explore the traffic correlations implicit in origin-destination(OD)data.In this paper,we propose STOD-Net,a dynamic spatial-temporal OD feature-enhanced deep network,to simultaneously predict the in-traffic and out-traffic for each and every region of a city.We model the OD data as dynamic graphs and adopt graph neural networks in STOD-Net to learn a low-dimensional representation for each region.As per the region feature,we design a gating mechanism and operate it on the traffic feature learning to explicitly capture spatial correlations.To further capture the complicated spatial and temporal dependencies among different regions,we propose a novel joint feature,learning block in STOD-Net and transfer the hybrid OD features to each block to make the learning process spatiotemporal-aware.We evaluate the effectiveness of STOD-Net on two benchmark datasets,and experimental results demonstrate that it outperforms the state-of-the-art by approximately 5%in terms of prediction accuracy and considerably improves prediction stability up to 80%in terms of standard deviation.
文摘Unmanned aerial vehicle(UAV)tracking is a critical task in surveillance,security,and autonomous navigation applications.In this study,we propose graph neural network-tracker(GNN-tracker),a novel GNN-based UAV tracking framework that effectively integrates graph-based spatial-temporal modelling,Transformer-based feature extraction,and multi-sensor fusion to enhance tracking robustness and accuracy.Unlike traditional tracking approaches,GNNtracker dynamically constructs a spatiotemporal graph representation,improving identity consistency and reducing tracking errors under OCC-heavy scenarios.Experimental evaluations on optical,thermal,and fused UAV datasets demonstrate the superiority of GNN-tracker(fused)over state-of-the-art methods.The proposed model achieves multiple object tracking accuracy(MOTA)scores of 91.4%(fused),89.1%(optical),and 86.3%(thermal),surpassing TransT by 8.9%in MOTA and 7.7%in higher order tracking accuracy(HOTA).The HOTA scores of 82.3%(fused),80.1%(optical),and 78.7%(thermal)validate its strong object association capabilities,while its frames per second of 58.9(fused),56.8(optical),and 54.3(thermal)ensures real-time performance.Additionally,ablation studies confirm the essential role of graph-based modelling and multi-sensor fusion,with performance drops of up to 8.9%in MOTA when these components are removed.Thus,GNN-tracker(fused)offers a highly accurate,robust,and efficient UAV tracking solution,effectively addressing real-world challenges across diverse environmental conditions and multiple sensor modalities.
基金Supported by Natural Science Basic Research Plan in Shaanxi Province of China(Program No.2022JM-396)the Strategic Priority Research Program of the Chinese Academy of Sciences,Grant No.XDA23040101+4 种基金Shaanxi Province Key Research and Development Projects(Program No.2023-YBSF-437)Xi'an Shiyou University Graduate Student Innovation Fund Program(Program No.YCX2412041)State Key Laboratory of Air Traffic Management System and Technology(SKLATM202001)Tianjin Education Commission Research Program Project(2020KJ028)Fundamental Research Funds for the Central Universities(3122019132)。
文摘Developing an accurate and efficient comprehensive water quality prediction model and its assessment method is crucial for the prevention and control of water pollution.Deep learning(DL),as one of the most promising technologies today,plays a crucial role in the effective assessment of water body health,which is essential for water resource management.This study models using both the original dataset and a dataset augmented with Generative Adversarial Networks(GAN).It integrates optimization algorithms(OA)with Convolutional Neural Networks(CNN)to propose a comprehensive water quality model evaluation method aiming at identifying the optimal models for different pollutants.Specifically,after preprocessing the spectral dataset,data augmentation was conducted to obtain two datasets.Then,six new models were developed on these datasets using particle swarm optimization(PSO),genetic algorithm(GA),and simulated annealing(SA)combined with CNN to simulate and forecast the concentrations of three water pollutants:Chemical Oxygen Demand(COD),Total Nitrogen(TN),and Total Phosphorus(TP).Finally,seven model evaluation methods,including uncertainty analysis,were used to evaluate the constructed models and select the optimal models for the three pollutants.The evaluation results indicate that the GPSCNN model performed best in predicting COD and TP concentrations,while the GGACNN model excelled in TN concentration prediction.Compared to existing technologies,the proposed models and evaluation methods provide a more comprehensive and rapid approach to water body prediction and assessment,offering new insights and methods for water pollution prevention and control.
基金funded by the Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2025R752),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The rapid shift to online education has introduced significant challenges to maintaining academic integrity in remote assessments,as traditional proctoring methods fall short in preventing cheating.The increase in cheating during online exams highlights the need for efficient,adaptable detection models to uphold academic credibility.This paper presents a comprehensive analysis of various deep learning models for cheating detection in online proctoring systems,evaluating their accuracy,efficiency,and adaptability.We benchmark several advanced architectures,including EfficientNet,MobileNetV2,ResNet variants and more,using two specialized datasets(OEP and OP)tailored for online proctoring contexts.Our findings reveal that EfficientNetB1 and YOLOv5 achieve top performance on the OP dataset,with EfficientNetB1 attaining a peak accuracy of 94.59% and YOLOv5 reaching a mean average precision(mAP@0.5)of 98.3%.For the OEP dataset,ResNet50-CBAM,YOLOv5 and EfficientNetB0 stand out,with ResNet50-CBAMachieving an accuracy of 93.61% and EfficientNetB0 showing robust detection performance with balanced accuracy and computational efficiency.These results underscore the importance of selectingmodels that balance accuracy and efficiency,supporting scalable,effective cheating detection in online assessments.
基金supported by the Open Research Project of the State Key Laboratory of Industrial Control Technology(No.ICT2021B10)the Natural Science Foundation of Hunan Province(2021JJ30456)+2 种基金the Open Fund of Science and Technology on Parallel and Distributed Processing Laboratory(WDZC20205500119)the Hunan Provincial Science and Technology Department High-tech Industry Science and Technology Innovation Leading Project(2020GK2009)the Scientific and Technological Progress and Innovation Program of the Transportation Department of Hunan Province(201927),etc.
文摘With the continuous deepening of Artificial Neural Network(ANN)research,ANN model structure and function are improving towards diversification and intelligence.However,the model is more evaluated from the pros and cons of the problem-solving results and the lack of evaluation from the biomimetic aspect of imitating neural networks is not inclusive enough.Hence,a new ANN models evaluation strategy is proposed from the perspective of bionics in response to this problem in the paper.Firstly,four classical neural network models are illustrated:Back Propagation(BP)network,Deep Belief Network(DBN),LeNet5 network,and olfactory bionic model(KIII model),and the neuron transmission mode and equation,network structure,and weight updating principle of the models are analyzed qualitatively.The analysis results show that the KIII model comes closer to the actual biological nervous system compared with other models,and the LeNet5 network simulates the nervous system in depth.Secondly,evaluation indexes of ANN are constructed from the perspective of bionics in this paper:small-world,synchronous,and chaotic characteristics.Finally,the network model is quantitatively analyzed by evaluation indexes from the perspective of bionics.The experimental results show that the DBN network,LeNet5 network,and BP network have synchronous characteristics.And the DBN network and LeNet5 network have certain chaotic characteristics,but there is still a certain distance between the three classical neural networks and actual biological neural networks.The KIII model has certain small-world characteristics in structure,and its network also exhibits synchronization characteristics and chaotic characteristics.Compared with the DBN network,LeNet5 network,and the BP network,the KIII model is closer to the real biological neural network.
基金the National Research Foundation of Korea(NRF)grant of the Korea government(MSIP)(2020R1A2B5B01001899)(Grantee:GJY,http://www.nrf.re.kr)and Institute of Engineering Research at Seoul National University(Grantee:GJY,http://www.snu.ac.kr).The authors are grateful for their supports.
文摘This paper first proposes a new self-learning data-driven methodology that can develop the failure criteria of unknown anisotropic ductile materials from the minimal number of experimental tests.Establishing failure criteria of anisotropic ductile materials requires time-consuming tests and manual data evaluation.The proposed method can overcome such practical challenges.The methodology is formalized by combining four ideas:1)The deep learning neural network(DLNN)-based material constitutive model,2)Self-learning inverse finite element(SELIFE)simulation,3)Algorithmic identification of failure points from the selflearned stress-strain curves and 4)Derivation of the failure criteria through symbolic regression of the genetic programming.Stress update and the algorithmic tangent operator were formulated in terms of DLNN parameters for nonlinear finite element analysis.Then,the SELIFE simulation algorithm gradually makes the DLNN model learn highly complex multi-axial stress and strain relationships,being guided by the experimental boundary measurements.Following the failure point identification,a self-learning data-driven failure criteria are eventually developed with the help of a reliable symbolic regression algorithm.The methodology and the self-learning data-driven failure criteria were verified by comparing with a reference failure criteria and simulating with different materials orientations,respectively.
