Geochemical survey data are essential across Earth Science disciplines but are often affected by noise,which can obscure important geological signals and compromise subsequent prediction and interpretation.Quantifying...Geochemical survey data are essential across Earth Science disciplines but are often affected by noise,which can obscure important geological signals and compromise subsequent prediction and interpretation.Quantifying prediction uncertainty is hence crucial for robust geoscientific decision-making.This study proposes a novel deep learning framework,the Spatially Constrained Variational Autoencoder(SC-VAE),for denoising geochemical survey data with integrated uncertainty quantification.The SC-VAE incorporates spatial regularization,which enforces spatial coherence by modeling inter-sample relationships directly within the latent space.The performance of the SC-VAE was systematically evaluated against a standard Variational Autoencoder(VAE)using geochemical data from the gold polymetallic district in the northwestern part of Sichuan Province,China.Both models were optimized using Bayesian optimization,with objective functions specifically designed to maintain essential geostatistical characteristics.Evaluation metrics include variogram analysis,quantitative measures of spatial interpolation accuracy,visual assessment of denoised maps,and statistical analysis of data distributions,as well as decomposition of uncertainties.Results show that the SC-VAE achieves superior noise suppression and better preservation of spatial structure compared to the standard VAE,as demonstrated by a significant reduction in the variogram nugget effect and an increased partial sill.The SC-VAE produces denoised maps with clearer anomaly delineation and more regularized data distributions,effectively mitigating outliers and reducing kurtosis.Additionally,it delivers improved interpolation accuracy and spatially explicit uncertainty estimates,facilitating more reliable and interpretable assessments of prediction confidence.The SC-VAE framework thus provides a robust,geostatistically informed solution for enhancing the quality and interpretability of geochemical data,with broad applicability in mineral exploration,environmental geochemistry,and other Earth Science domains.展开更多
The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,wi...The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,with applications such as the gravity-only aerial deployment of high-aspect-ratio solar-powered UAVs,and aerial takeoff of fixed-wing drones in Mars research.However,the significant morphological changes during deployment are accompanied by strong nonlinear dynamic aerodynamic forces,which result in multiple degrees of freedom and an unstable character.This hinders the description and analysis of unknown dynamic behaviors,further leading to difficulties in the design of deployment strategies and flight control.To address this issue,this paper proposes an analysis method for dynamic behaviors during aerial deployment based on the Variational Autoencoder(VAE).Focusing on the gravity-only deployment problem of highaspect-ratio foldable-wing UAVs,the method encodes the multi-degree-of-freedom unstable motion signals into a low-dimensional feature space through a data-driven approach.By clustering in the feature space,this paper identifies and studies several dynamic behaviors during aerial deployment.The research presented in this paper offers a new method and perspective for feature extraction and analysis of complex and difficult-to-describe extreme flight dynamics,guiding the research on aerial deployment drones design and control strategies.展开更多
Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer i...Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer interface(BCI)in practice.We attempt to use the multi-modal data from the past session to realize emotion recognition in the case of a small amount of calibration samples.To solve this problem,we propose a multimodal domain adaptive variational autoencoder(MMDA-VAE)method,which learns shared cross-domain latent representations of the multi-modal data.Our method builds a multi-modal variational autoencoder(MVAE)to project the data of multiple modalities into a common space.Through adversarial learning and cycle-consistency regularization,our method can reduce the distribution difference of each domain on the shared latent representation layer and realize the transfer of knowledge.Extensive experiments are conducted on two public datasets,SEED and SEED-IV,and the results show the superiority of our proposed method.Our work can effectively improve the performance of emotion recognition with a small amount of labelled multi-modal data.展开更多
In this study,the hourly directions of eight banking stocks in Borsa Istanbul were predicted using linear-based,deep-learning(LSTM)and ensemble learning(Light-GBM)models.These models were trained with four different f...In this study,the hourly directions of eight banking stocks in Borsa Istanbul were predicted using linear-based,deep-learning(LSTM)and ensemble learning(Light-GBM)models.These models were trained with four different feature sets and their performances were evaluated in terms of accuracy and F-measure metrics.While the first experiments directly used the own stock features as the model inputs,the second experiments utilized reduced stock features through Variational AutoEncoders(VAE).In the last experiments,in order to grasp the effects of the other banking stocks on individual stock performance,the features belonging to other stocks were also given as inputs to our models.While combining other stock features was done for both own(named as allstock_own)and VAE-reduced(named as allstock_VAE)stock features,the expanded dimensions of the feature sets were reduced by Recursive Feature Elimination.As the highest success rate increased up to 0.685 with allstock_own and LSTM with attention model,the combination of allstock_VAE and LSTM with the attention model obtained an accuracy rate of 0.675.Although the classification results achieved with both feature types was close,allstock_VAE achieved these results using nearly 16.67%less features compared to allstock_own.When all experimental results were examined,it was found out that the models trained with allstock_own and allstock_VAE achieved higher accuracy rates than those using individual stock features.It was also concluded that the results obtained with the VAE-reduced stock features were similar to those obtained by own stock features.展开更多
In modern industry,process monitoring plays a significant role in improving the quality of process conduct.With the higher dimensional of the industrial data,the monitoring methods based on the latent variables have b...In modern industry,process monitoring plays a significant role in improving the quality of process conduct.With the higher dimensional of the industrial data,the monitoring methods based on the latent variables have been widely applied in order to decrease the wasting of the industrial database.Nevertheless,these latent variables do not usually follow the Gaussian distribution and thus perform unsuitable when applying some statistics indices,especially the T^(2) on them.Variational AutoEncoders(VAE),an unsupervised deep learning algorithm using the hierarchy study method,has the ability to make the latent variables follow the Gaussian distribution.The partial least squares(PLS)are used to obtain the information between the dependent variables and independent variables.In this paper,we will integrate these two methods and make a comparison with other methods.The superiority of this proposed method will be verified by the simulation and the Trimethylchlorosilane purification process in terms of the multivariate control charts.展开更多
Supervised machine learning algorithms have been widely used in seismic exploration processing,but the lack of labeled examples complicates its application.Therefore,we propose a seismic labeled data expansion method ...Supervised machine learning algorithms have been widely used in seismic exploration processing,but the lack of labeled examples complicates its application.Therefore,we propose a seismic labeled data expansion method based on deep variational Autoencoders(VAE),which are made of neural networks and contains two partsEncoder and Decoder.Lack of training samples leads to overfitting of the network.We training the VAE with whole seismic data,which is a data-driven process and greatly alleviates the risk of overfitting.The Encoder captures the ability to map the seismic waveform Y to latent deep features z,and the Decoder captures the ability to reconstruct high-dimensional waveform Yb from latent deep features z.Later,we put the labeled seismic data into Encoders and get the latent deep features.We can easily use gaussian mixture model to fit the deep feature distribution of each class labeled data.We resample a mass of expansion deep features z* according to the Gaussian mixture model,and put the expansion deep features into the decoder to generate expansion seismic data.The experiments in synthetic and real data show that our method alleviates the problem of lacking labeled seismic data for supervised seismic facies analysis.展开更多
Learning disentangled representation of data is a key problem in deep learning.Specifically,disentangling 2D facial landmarks into different factors(e.g.,identity and expression)is widely used in the applications of f...Learning disentangled representation of data is a key problem in deep learning.Specifically,disentangling 2D facial landmarks into different factors(e.g.,identity and expression)is widely used in the applications of face reconstruction,face reenactment and talking head et al..However,due to the sparsity of landmarks and the lack of accurate labels for the factors,it is hard to learn the disentangled representation of landmarks.To address these problem,we propose a simple and effective model named FLD-VAE to disentangle arbitrary facial landmarks into identity and expression latent representations,which is based on a Variational Autoencoder framework.Besides,we propose three invariant loss functions in both latent and data levels to constrain the invariance of representations during training stage.Moreover,we implement an identity preservation loss to further enhance the representation ability of identity factor.To the best of our knowledge,this is the first work to end-to-end disentangle identity and expression factors simultaneously from one single facial landmark.展开更多
Future 6G communications will open up opportunities for innovative applications,including Cyber-Physical Systems,edge computing,supporting Industry 5.0,and digital agriculture.While automation is creating efficiencies...Future 6G communications will open up opportunities for innovative applications,including Cyber-Physical Systems,edge computing,supporting Industry 5.0,and digital agriculture.While automation is creating efficiencies,it can also create new cyber threats,such as vulnerabilities in trust and malicious node injection.Denialof-Service(DoS)attacks can stop many forms of operations by overwhelming networks and systems with data noise.Current anomaly detection methods require extensive software changes and only detect static threats.Data collection is important for being accurate,but it is often a slow,tedious,and sometimes inefficient process.This paper proposes a new wavelet transformassisted Bayesian deep learning based probabilistic(WT-BDLP)approach tomitigate malicious data injection attacks in 6G edge networks.The proposed approach combines outlier detection based on a Bayesian learning conditional variational autoencoder(Bay-LCVariAE)and traffic pattern analysis based on continuous wavelet transform(CWT).The Bay-LCVariAE framework allows for probabilistic modelling of generative features to facilitate capturing how features of interest change over time,spatially,and for recognition of anomalies.Similarly,CWT allows emphasizing the multi-resolution spectral analysis and permits temporally relevant frequency pattern recognition.Experimental testing showed that the flexibility of the Bayesian probabilistic framework offers a vast improvement in anomaly detection accuracy over existing methods,with a maximum accuracy of 98.21%recognizing anomalies.展开更多
Anomaly detection is one of the many challenging areas in cybersecurity.The anomaly can occur in many forms,such as fraudulent credit card transactions,network intrusions,and anomalous imageries or documents.One of th...Anomaly detection is one of the many challenging areas in cybersecurity.The anomaly can occur in many forms,such as fraudulent credit card transactions,network intrusions,and anomalous imageries or documents.One of the most common challenges in anomaly detection is the obscurity of the normal state and the lack of anomalous samples.Traditionally,this problem is tackled by using resampling techniques or choosing models that approximate the distribution of the normal states.Variational AutoEncoder(VAE)has been studied in anomaly detections despite being more suitable in generative tasks.This study aims to explore the usage of VAE in credit card anomaly detection and evaluate latent space sampling techniques.In this study,we evaluate the usage of the convolutional network-based VAE model on a credit card transaction dataset.We train two VAE models,one with a large number of normal data and one with a small number of anomalous data.We compare the performance of both VAE models and evaluate the latent space of both VAE models by rescaling them with reconstruction error vectors.We also compare the effectiveness of the VAE model with other anomaly detection models when they are trained on imbalanced dataset.展开更多
Autism Spectrum Disorder(ASD)is a highly disabling mental disease that brings significant impairments of social interaction ability to the patients,making early screening and intervention of ASD critical.With the deve...Autism Spectrum Disorder(ASD)is a highly disabling mental disease that brings significant impairments of social interaction ability to the patients,making early screening and intervention of ASD critical.With the development of the machine learning and neuroimaging technology,extensive research has been conducted on machine classification of ASD based on structural Magnetic Resonance Imaging(s-MRI).However,most studies involve with datasets where participants'age are above 5 and lack interpretability.In this paper,we propose a machine learning method for ASD classification in children with age range from 0.92 to 4.83 years,based on s-MRI features extracted using Contrastive Variational AutoEncoder(CVAE).78 s-MRIs,collected from Shenzhen Children's Hospital,are used for training CVAE,which consists of both ASD-specific feature channel and common-shared feature channel.The ASD participants represented by ASD-specific features can be easily discriminated from Typical Control(TC)participants represented by the common-shared features.In case of degraded predictive accuracy when data size is extremely small,a transfer learning strategy is proposed here as a potential solution.Finally,we conduct neuroanatomical interpretation based on the correlation between s-MRI features extracted from CVAE and surface area of different cortical regions,which discloses potential biomarkers that could help target treatments of ASD in the future.展开更多
Federated Learning(FL) heralds a paradigm shift in the training of artificial intelligence(AI) models by fostering collaborative model training while safeguarding client data privacy. In sectors where data sensitivity...Federated Learning(FL) heralds a paradigm shift in the training of artificial intelligence(AI) models by fostering collaborative model training while safeguarding client data privacy. In sectors where data sensitivity and AI model security are of paramount importance, such as fintech and biomedicine, maintaining the utility of models without compromising privacy is crucial with the growing application of AI technologies. Therefore, the adoption of FL is attracting significant attention. However, traditional FL methods are susceptible to Deep Leakage from Gradients(DLG) attacks, and typical defensive strategies in current research, such as secure multi-party computation and diferential privacy, often lead to excessive computational costs or significant decreases in model accuracy. To address DLG attacks in FL, this study introduces VAEFL, an innovative FL framework that incorporates Variational Autoencoders(VAEs) to enhance privacy protection without undermining the predictive prowess of the models. VAEFL strategically partitions the model into a private encoder and a public decoder. The private encoder, remaining local, transmutes sensitive data into a latent space fortified for privacy, while the public decoder and classifier, through collaborative training across clients, learn to derive precise predictions from the encoded data. This bifurcation ensures that sensitive data attributes are not disclosed, circumventing gradient leakage attacks and simultaneously allowing the global model to benefit from the diverse knowledge of client datasets. Comprehensive experiments demonstrate that VAEFL not only surpasses standard FL benchmarks in privacy preservation but also maintains competitive performance in predictive tasks. VAEFL thus establishes a novel equilibrium between data privacy and model utility, ofering a secure and efficient FL approach for the sensitive application of FL in the financial domain.展开更多
The generation and optimization of simulation data for electrical machines remain challenging,largely due to the complexities of magneto-staticfinite element analysis.Traditional methodologies are not only resource-in...The generation and optimization of simulation data for electrical machines remain challenging,largely due to the complexities of magneto-staticfinite element analysis.Traditional methodologies are not only resource-intensive,but also time-consuming.Deep learning models can be used to shortcut these calculations.However,challenges arise when considering the unique parameter sets specific to each machine topology.Building on two recent studies(Parekh et al.in IEEE Trans.Magn.58(9):1-4,2022;Parekh et al.,Deep learning based meta-modeling for multi-objective technology optimization of electrical machines,2023,arXiv:2306.09087),that utilized a variational autoencoder to cohesively map diverse topologies into a singular latent space for subsequent optimization,this paper proposes a refined architecture and optimization workflow.Our modifications aim to streamline and enhance the robustness of both the training and optimization processes,and compare the results with the variational autoencoder architecture proposed recently.展开更多
Single-cell RNA sequencing(scRNA-seq) is a powerful technique to analyze the transcriptomic heterogeneities at the single cell level. It is an important step for studying cell subpopulations and lineages, with an effe...Single-cell RNA sequencing(scRNA-seq) is a powerful technique to analyze the transcriptomic heterogeneities at the single cell level. It is an important step for studying cell subpopulations and lineages, with an effective low-dimensional representation and visualization of the original scRNA-Seq data. At the single cell level, the transcriptional fluctuations are much larger than the average of a cell population, and the low amount of RNA transcripts will increase the rate of technical dropout events. Therefore, scRNA-seq data are much noisier than traditional bulk RNA-seq data. In this study, we proposed the deep variational autoencoder for scRNA-seq data(VASC), a deep multi-layer generative model, for the unsupervised dimension reduction and visualization of scRNA-seq data. VASC can explicitly model the dropout events and find the nonlinear hierarchical feature representations of the original data. Tested on over 20 datasets, VASC shows superior performances in most cases and exhibits broader dataset compatibility compared to four state-of-the-art dimension reduction and visualization methods. In addition, VASC provides better representations for very rare cell populations in the 2D visualization. As a case study, VASC successfully re-establishes the cell dynamics in pre-implantation embryos and identifies several candidate marker genes associated with early embryo development. Moreover, VASC also performs well on a 10× Genomics dataset with more cells and higher dropout rate.展开更多
In the face of the unrelenting challenge posed by earthquakes-a natural hazard of unpredictable nature with a legacy of significant loss of life,destruction of infrastructure,and profound economic and social impacts-t...In the face of the unrelenting challenge posed by earthquakes-a natural hazard of unpredictable nature with a legacy of significant loss of life,destruction of infrastructure,and profound economic and social impacts-the scientific community has pursued advancements in earthquake early warning systems(EEWSs).These systems are vital for pre-emptive actions and decision-making that can save lives and safeguard critical infrastructure.This study proposes and validates a domain-informed deep learning-based EEWS called the hybrid earthquake early warning framework for estimating response spectra(HEWFERS),which represents a significant leap forward in the capabilities to predict ground shaking intensity in real-time,aligning with the United Nations’disaster risk reduction goals.HEWFERS ingeniously integrates a domain-informed variational autoencoder for physics-based latent variable(LV)extraction,a feed-forward neural network for on-site prediction,and Gaussian process regression for spatial prediction.Adopting explainable artificial intelligence-based Shapley explanations further elucidates the predictive mechanisms,ensuring stakeholder-informed decisions.By conducting an extensive analysis of the proposed framework under a large database of approximately 14000 recorded ground motions,this study offers insights into the potential of integrating machine learning with seismology to revolutionize earthquake preparedness and response,thus paving the way for a safer and more resilient future.展开更多
To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation me...To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation method.This method utilizes a variational autoencoder(VAE)to generate low-cycle fatigue data and form an augmented dataset.The Pearson correlation coefficient(PCC)is employed to verify the similarity of feature distributions between the original and augmented datasets.Six machine learning models,namely random forest(RF),artificial neural network(ANN),support vector machine(SVM),gradient-boosted decision tree(GBDT),eXtreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost),are utilized to predict the LCF life of nickel-based superalloys.Results indicate that the proposed data augmentation method based on VAE can effectively expand the dataset,and the mean absolute error(MAE),root mean square error(RMSE),and R-squared(R^(2))values achieved using the CatBoost model,with respective values of 0.0242,0.0391,and 0.9538,are superior to those of the other models.The proposed method reduces the cost and time associated with LCF experiments and accurately establishes the relationship between fatigue characteristics and LCF life of nickel-based superalloys.展开更多
Direct coal liquefaction products offer a considerable quantity of cycloalkanes, which are the valuable candidates for making the high energy density fuels. The creation of such fuels depends on designing molecular st...Direct coal liquefaction products offer a considerable quantity of cycloalkanes, which are the valuable candidates for making the high energy density fuels. The creation of such fuels depends on designing molecular structures and calculating their properties, which can be expedited with computer-aided techniques. In this study, a dataset containing 367 fuel molecules was constructed based on the analysis of direct coal liquefied oil. Three convolutional neural network property prediction models have been created based on molecular structure-physical and chemical property data from the library. All the models have good fitting ability with R2 values above 0.97. Then, a variational autoencoder generation model has been established using the molecular structures from the library, focusing on the structure of saturated cycloalkanes. The structure-property prediction model was then applied to the newly generated molecules, assessing their density, volumetric calorific value, and melting point. As a result, 70000 novel molecular structures were generated, and 25 molecular structures meeting the criteria for high energy density fuels were identified. The established variational autoencoder model in this study effectively assimilates the structural information from the sample set and autonomously generates novel high energy density fuels, which is difficult to achieve in traditional experimental methods.展开更多
Contemporary attackers,mainly motivated by financial gain,consistently devise sophisticated penetration techniques to access important information or data.The growing use of Internet of Things(IoT)technology in the co...Contemporary attackers,mainly motivated by financial gain,consistently devise sophisticated penetration techniques to access important information or data.The growing use of Internet of Things(IoT)technology in the contemporary convergence environment to connect to corporate networks and cloud-based applications only worsens this situation,as it facilitates multiple new attack vectors to emerge effortlessly.As such,existing intrusion detection systems suffer from performance degradation mainly because of insufficient considerations and poorly modeled detection systems.To address this problem,we designed a blended threat detection approach,considering the possible impact and dimensionality of new attack surfaces due to the aforementioned convergence.We collectively refer to the convergence of different technology sectors as the internet of blended environment.The proposed approach encompasses an ensemble of heterogeneous probabilistic autoencoders that leverage the corresponding advantages of a convolutional variational autoencoder and long short-term memory variational autoencoder.An extensive experimental analysis conducted on the TON_IoT dataset demonstrated 96.02%detection accuracy.Furthermore,performance of the proposed approach was compared with various single model(autoencoder)-based network intrusion detection approaches:autoencoder,variational autoencoder,convolutional variational autoencoder,and long short-term memory variational autoencoder.The proposed model outperformed all compared models,demonstrating F1-score improvements of 4.99%,2.25%,1.92%,and 3.69%,respectively.展开更多
As the popularity and dependence on the Internet increase,DDoS(distributed denial of service)attacks seriously threaten network security.By accurately distinguishing between different types of DDoS attacks,targeted de...As the popularity and dependence on the Internet increase,DDoS(distributed denial of service)attacks seriously threaten network security.By accurately distinguishing between different types of DDoS attacks,targeted defense strategies can be formulated,significantly improving network protection efficiency.DDoS attacks usually manifest as an abnormal increase in network traffic,and their diverse types of attacks,along with a severe data imbalance,make it difficult for traditional classification methods to effectively identify a small number of attack types.To solve this problem,this paper proposes a DDoS recognition method CVWGG(Conditional Variational Autoencoder-Wasserstein Generative Adversarial Network-gradient penalty-Gated Recurrent Unit)for unbalanced data,which generates less noisy data and high data quality compared with existing methods.CVWGG mainly includes unbalanced data processing for CVWG,feature extraction,and classification.CVWGG uses the CVAE(Conditional Variational Autoencoder)to improve the WGAN(Wasserstein Generative Adversarial Network)and introduces a GP(gradient penalty)term to design the loss function to generate balanced data,which enhances the learning ability and stability of the data.Subsequently,the GRU(Gated Recurrent Units)are used to capture the temporal features and patterns of the data.Finally,the logsoftmax function is used to differentiate DDoS attack categories.Using PyCharm and Python 3.10 for programming and evaluating performance with metrics such as accuracy and precision,the results show that the method achieved accuracy rates of 96.0%and 97.3%on two datasets,respectively.Additionally,comparison and ablation experiment results demonstrate that CVWGG effectively mitigates the imbalance between DDoS attack categories,significantly improves the classification accuracy of different types of attacks and provides a valuable reference for network security defense.展开更多
Geological model compression is crucial for making large and complex models more manageable.By reducing the size of these models,compression techniques enable efficient storage,enhance computational efficiency,making ...Geological model compression is crucial for making large and complex models more manageable.By reducing the size of these models,compression techniques enable efficient storage,enhance computational efficiency,making it feasible to perform complex simulations and analyses in a shorter time.This is particularly important in applications such as reservoir management,groundwater hydrology,and geological carbon storage,where large geomodels with millions of grid cells are common.This study presents a comprehensive overview of previous work on geomodel compression and introduces several autoencoder-based deep-learning architectures for low-dimensional representation of modified Bruggefield geomodels.The compression and reconstruction efficiencies of autoencoders(AE),variational autoencoders(VAE),vector-quantized variational autoencoders(VQ-VAE),and vector-quantized variational autoencoders 2(VQ-VAE2)were tested and compared to the traditional singular value decomposition(SVD)method.Results show that the deep-learning-based approaches significantly outperform SVD,achieving higher compression ratios while maintaining or even exceeding the reconstruction quality.Notably,VQ-VAE2 achieves the highest compression ratio of 667:1 with a structural similarity index metric(SSIM)of 0.92,far surpassing the 10:1 compression ratio of SVD with a SSIM of 0.9.The result of this work shows that,unlike traditional approaches,which often rely on linear transformations and can struggle to capture complex,non-linear relationships within geological data,VQ-VAE's use of vector quantization helps in preserving high-resolution details and enhances the model's ability to generalize across varying geological complexities.展开更多
Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learnin...Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative models.They are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft loading.Qualitative and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given features.The CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the dataset.Furthermore,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number distribution.The performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.展开更多
基金supported by the National Natural Science Foundation of China(Nos.42530801,42425208)the Natural Science Foundation of Hubei Province(China)(No.2023AFA001)+1 种基金the MOST Special Fund from State Key Laboratory of Geological Processes and Mineral Resources,China University of Geosciences(No.MSFGPMR2025-401)the China Scholarship Council(No.202306410181)。
文摘Geochemical survey data are essential across Earth Science disciplines but are often affected by noise,which can obscure important geological signals and compromise subsequent prediction and interpretation.Quantifying prediction uncertainty is hence crucial for robust geoscientific decision-making.This study proposes a novel deep learning framework,the Spatially Constrained Variational Autoencoder(SC-VAE),for denoising geochemical survey data with integrated uncertainty quantification.The SC-VAE incorporates spatial regularization,which enforces spatial coherence by modeling inter-sample relationships directly within the latent space.The performance of the SC-VAE was systematically evaluated against a standard Variational Autoencoder(VAE)using geochemical data from the gold polymetallic district in the northwestern part of Sichuan Province,China.Both models were optimized using Bayesian optimization,with objective functions specifically designed to maintain essential geostatistical characteristics.Evaluation metrics include variogram analysis,quantitative measures of spatial interpolation accuracy,visual assessment of denoised maps,and statistical analysis of data distributions,as well as decomposition of uncertainties.Results show that the SC-VAE achieves superior noise suppression and better preservation of spatial structure compared to the standard VAE,as demonstrated by a significant reduction in the variogram nugget effect and an increased partial sill.The SC-VAE produces denoised maps with clearer anomaly delineation and more regularized data distributions,effectively mitigating outliers and reducing kurtosis.Additionally,it delivers improved interpolation accuracy and spatially explicit uncertainty estimates,facilitating more reliable and interpretable assessments of prediction confidence.The SC-VAE framework thus provides a robust,geostatistically informed solution for enhancing the quality and interpretability of geochemical data,with broad applicability in mineral exploration,environmental geochemistry,and other Earth Science domains.
基金co-supported by the Natural Science Basic Research Program of Shaanxi,China(No.2023-JC-QN-0043)the ND Basic Research Funds,China(No.G2022WD).
文摘The aerial deployment method enables Unmanned Aerial Vehicles(UAVs)to be directly positioned at the required altitude for their mission.This method typically employs folding technology to improve loading efficiency,with applications such as the gravity-only aerial deployment of high-aspect-ratio solar-powered UAVs,and aerial takeoff of fixed-wing drones in Mars research.However,the significant morphological changes during deployment are accompanied by strong nonlinear dynamic aerodynamic forces,which result in multiple degrees of freedom and an unstable character.This hinders the description and analysis of unknown dynamic behaviors,further leading to difficulties in the design of deployment strategies and flight control.To address this issue,this paper proposes an analysis method for dynamic behaviors during aerial deployment based on the Variational Autoencoder(VAE).Focusing on the gravity-only deployment problem of highaspect-ratio foldable-wing UAVs,the method encodes the multi-degree-of-freedom unstable motion signals into a low-dimensional feature space through a data-driven approach.By clustering in the feature space,this paper identifies and studies several dynamic behaviors during aerial deployment.The research presented in this paper offers a new method and perspective for feature extraction and analysis of complex and difficult-to-describe extreme flight dynamics,guiding the research on aerial deployment drones design and control strategies.
基金National Natural Science Foundation of China(61976209,62020106015,U21A20388)in part by the CAS International Collaboration Key Project(173211KYSB20190024)in part by the Strategic Priority Research Program of CAS(XDB32040000)。
文摘Traditional electroencephalograph(EEG)-based emotion recognition requires a large number of calibration samples to build a model for a specific subject,which restricts the application of the affective brain computer interface(BCI)in practice.We attempt to use the multi-modal data from the past session to realize emotion recognition in the case of a small amount of calibration samples.To solve this problem,we propose a multimodal domain adaptive variational autoencoder(MMDA-VAE)method,which learns shared cross-domain latent representations of the multi-modal data.Our method builds a multi-modal variational autoencoder(MVAE)to project the data of multiple modalities into a common space.Through adversarial learning and cycle-consistency regularization,our method can reduce the distribution difference of each domain on the shared latent representation layer and realize the transfer of knowledge.Extensive experiments are conducted on two public datasets,SEED and SEED-IV,and the results show the superiority of our proposed method.Our work can effectively improve the performance of emotion recognition with a small amount of labelled multi-modal data.
文摘In this study,the hourly directions of eight banking stocks in Borsa Istanbul were predicted using linear-based,deep-learning(LSTM)and ensemble learning(Light-GBM)models.These models were trained with four different feature sets and their performances were evaluated in terms of accuracy and F-measure metrics.While the first experiments directly used the own stock features as the model inputs,the second experiments utilized reduced stock features through Variational AutoEncoders(VAE).In the last experiments,in order to grasp the effects of the other banking stocks on individual stock performance,the features belonging to other stocks were also given as inputs to our models.While combining other stock features was done for both own(named as allstock_own)and VAE-reduced(named as allstock_VAE)stock features,the expanded dimensions of the feature sets were reduced by Recursive Feature Elimination.As the highest success rate increased up to 0.685 with allstock_own and LSTM with attention model,the combination of allstock_VAE and LSTM with the attention model obtained an accuracy rate of 0.675.Although the classification results achieved with both feature types was close,allstock_VAE achieved these results using nearly 16.67%less features compared to allstock_own.When all experimental results were examined,it was found out that the models trained with allstock_own and allstock_VAE achieved higher accuracy rates than those using individual stock features.It was also concluded that the results obtained with the VAE-reduced stock features were similar to those obtained by own stock features.
文摘In modern industry,process monitoring plays a significant role in improving the quality of process conduct.With the higher dimensional of the industrial data,the monitoring methods based on the latent variables have been widely applied in order to decrease the wasting of the industrial database.Nevertheless,these latent variables do not usually follow the Gaussian distribution and thus perform unsuitable when applying some statistics indices,especially the T^(2) on them.Variational AutoEncoders(VAE),an unsupervised deep learning algorithm using the hierarchy study method,has the ability to make the latent variables follow the Gaussian distribution.The partial least squares(PLS)are used to obtain the information between the dependent variables and independent variables.In this paper,we will integrate these two methods and make a comparison with other methods.The superiority of this proposed method will be verified by the simulation and the Trimethylchlorosilane purification process in terms of the multivariate control charts.
基金Supported by National Natural Science Foundation of China(41804126,41604107).
文摘Supervised machine learning algorithms have been widely used in seismic exploration processing,but the lack of labeled examples complicates its application.Therefore,we propose a seismic labeled data expansion method based on deep variational Autoencoders(VAE),which are made of neural networks and contains two partsEncoder and Decoder.Lack of training samples leads to overfitting of the network.We training the VAE with whole seismic data,which is a data-driven process and greatly alleviates the risk of overfitting.The Encoder captures the ability to map the seismic waveform Y to latent deep features z,and the Decoder captures the ability to reconstruct high-dimensional waveform Yb from latent deep features z.Later,we put the labeled seismic data into Encoders and get the latent deep features.We can easily use gaussian mixture model to fit the deep feature distribution of each class labeled data.We resample a mass of expansion deep features z* according to the Gaussian mixture model,and put the expansion deep features into the decoder to generate expansion seismic data.The experiments in synthetic and real data show that our method alleviates the problem of lacking labeled seismic data for supervised seismic facies analysis.
基金Supported by the National Natural Science Foundation of China(61210007).
文摘Learning disentangled representation of data is a key problem in deep learning.Specifically,disentangling 2D facial landmarks into different factors(e.g.,identity and expression)is widely used in the applications of face reconstruction,face reenactment and talking head et al..However,due to the sparsity of landmarks and the lack of accurate labels for the factors,it is hard to learn the disentangled representation of landmarks.To address these problem,we propose a simple and effective model named FLD-VAE to disentangle arbitrary facial landmarks into identity and expression latent representations,which is based on a Variational Autoencoder framework.Besides,we propose three invariant loss functions in both latent and data levels to constrain the invariance of representations during training stage.Moreover,we implement an identity preservation loss to further enhance the representation ability of identity factor.To the best of our knowledge,this is the first work to end-to-end disentangle identity and expression factors simultaneously from one single facial landmark.
文摘Future 6G communications will open up opportunities for innovative applications,including Cyber-Physical Systems,edge computing,supporting Industry 5.0,and digital agriculture.While automation is creating efficiencies,it can also create new cyber threats,such as vulnerabilities in trust and malicious node injection.Denialof-Service(DoS)attacks can stop many forms of operations by overwhelming networks and systems with data noise.Current anomaly detection methods require extensive software changes and only detect static threats.Data collection is important for being accurate,but it is often a slow,tedious,and sometimes inefficient process.This paper proposes a new wavelet transformassisted Bayesian deep learning based probabilistic(WT-BDLP)approach tomitigate malicious data injection attacks in 6G edge networks.The proposed approach combines outlier detection based on a Bayesian learning conditional variational autoencoder(Bay-LCVariAE)and traffic pattern analysis based on continuous wavelet transform(CWT).The Bay-LCVariAE framework allows for probabilistic modelling of generative features to facilitate capturing how features of interest change over time,spatially,and for recognition of anomalies.Similarly,CWT allows emphasizing the multi-resolution spectral analysis and permits temporally relevant frequency pattern recognition.Experimental testing showed that the flexibility of the Bayesian probabilistic framework offers a vast improvement in anomaly detection accuracy over existing methods,with a maximum accuracy of 98.21%recognizing anomalies.
文摘Anomaly detection is one of the many challenging areas in cybersecurity.The anomaly can occur in many forms,such as fraudulent credit card transactions,network intrusions,and anomalous imageries or documents.One of the most common challenges in anomaly detection is the obscurity of the normal state and the lack of anomalous samples.Traditionally,this problem is tackled by using resampling techniques or choosing models that approximate the distribution of the normal states.Variational AutoEncoder(VAE)has been studied in anomaly detections despite being more suitable in generative tasks.This study aims to explore the usage of VAE in credit card anomaly detection and evaluate latent space sampling techniques.In this study,we evaluate the usage of the convolutional network-based VAE model on a credit card transaction dataset.We train two VAE models,one with a large number of normal data and one with a small number of anomalous data.We compare the performance of both VAE models and evaluate the latent space of both VAE models by rescaling them with reconstruction error vectors.We also compare the effectiveness of the VAE model with other anomaly detection models when they are trained on imbalanced dataset.
基金supported by the Shenzhen Science and Technology Program(Nos.KQTD20200820113106007 and SGDX20201103095603009)the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDB38050100)+4 种基金the Shenzhen Key Laboratory of Intelligent Bioinformatics(No.ZDSYS20220422103800001)the Shenzhen Basic Research Fund(No.RCYX20200714114734194)the Key Research and Development Project of Guangdong Province(No.2021B0101310002)the National Natural Science Foundation of China(Nos.U22A2041 and 62272449)the Youth Innovation Promotion Association(No.Y2021101).
文摘Autism Spectrum Disorder(ASD)is a highly disabling mental disease that brings significant impairments of social interaction ability to the patients,making early screening and intervention of ASD critical.With the development of the machine learning and neuroimaging technology,extensive research has been conducted on machine classification of ASD based on structural Magnetic Resonance Imaging(s-MRI).However,most studies involve with datasets where participants'age are above 5 and lack interpretability.In this paper,we propose a machine learning method for ASD classification in children with age range from 0.92 to 4.83 years,based on s-MRI features extracted using Contrastive Variational AutoEncoder(CVAE).78 s-MRIs,collected from Shenzhen Children's Hospital,are used for training CVAE,which consists of both ASD-specific feature channel and common-shared feature channel.The ASD participants represented by ASD-specific features can be easily discriminated from Typical Control(TC)participants represented by the common-shared features.In case of degraded predictive accuracy when data size is extremely small,a transfer learning strategy is proposed here as a potential solution.Finally,we conduct neuroanatomical interpretation based on the correlation between s-MRI features extracted from CVAE and surface area of different cortical regions,which discloses potential biomarkers that could help target treatments of ASD in the future.
基金supported by the Yangtze River Delta Science and Technology Innovation Community Joint Research Project (2022CSJGG0800)the Shanghai Science and Technology Project (22510761000)
文摘Federated Learning(FL) heralds a paradigm shift in the training of artificial intelligence(AI) models by fostering collaborative model training while safeguarding client data privacy. In sectors where data sensitivity and AI model security are of paramount importance, such as fintech and biomedicine, maintaining the utility of models without compromising privacy is crucial with the growing application of AI technologies. Therefore, the adoption of FL is attracting significant attention. However, traditional FL methods are susceptible to Deep Leakage from Gradients(DLG) attacks, and typical defensive strategies in current research, such as secure multi-party computation and diferential privacy, often lead to excessive computational costs or significant decreases in model accuracy. To address DLG attacks in FL, this study introduces VAEFL, an innovative FL framework that incorporates Variational Autoencoders(VAEs) to enhance privacy protection without undermining the predictive prowess of the models. VAEFL strategically partitions the model into a private encoder and a public decoder. The private encoder, remaining local, transmutes sensitive data into a latent space fortified for privacy, while the public decoder and classifier, through collaborative training across clients, learn to derive precise predictions from the encoded data. This bifurcation ensures that sensitive data attributes are not disclosed, circumventing gradient leakage attacks and simultaneously allowing the global model to benefit from the diverse knowledge of client datasets. Comprehensive experiments demonstrate that VAEFL not only surpasses standard FL benchmarks in privacy preservation but also maintains competitive performance in predictive tasks. VAEFL thus establishes a novel equilibrium between data privacy and model utility, ofering a secure and efficient FL approach for the sensitive application of FL in the financial domain.
文摘The generation and optimization of simulation data for electrical machines remain challenging,largely due to the complexities of magneto-staticfinite element analysis.Traditional methodologies are not only resource-intensive,but also time-consuming.Deep learning models can be used to shortcut these calculations.However,challenges arise when considering the unique parameter sets specific to each machine topology.Building on two recent studies(Parekh et al.in IEEE Trans.Magn.58(9):1-4,2022;Parekh et al.,Deep learning based meta-modeling for multi-objective technology optimization of electrical machines,2023,arXiv:2306.09087),that utilized a variational autoencoder to cohesively map diverse topologies into a singular latent space for subsequent optimization,this paper proposes a refined architecture and optimization workflow.Our modifications aim to streamline and enhance the robustness of both the training and optimization processes,and compare the results with the variational autoencoder architecture proposed recently.
基金supported by the National Natural Science Foundation of China (Grant Nos.61370035 and 31361163004)Tsinghua University Initiative Scientific Research Program
文摘Single-cell RNA sequencing(scRNA-seq) is a powerful technique to analyze the transcriptomic heterogeneities at the single cell level. It is an important step for studying cell subpopulations and lineages, with an effective low-dimensional representation and visualization of the original scRNA-Seq data. At the single cell level, the transcriptional fluctuations are much larger than the average of a cell population, and the low amount of RNA transcripts will increase the rate of technical dropout events. Therefore, scRNA-seq data are much noisier than traditional bulk RNA-seq data. In this study, we proposed the deep variational autoencoder for scRNA-seq data(VASC), a deep multi-layer generative model, for the unsupervised dimension reduction and visualization of scRNA-seq data. VASC can explicitly model the dropout events and find the nonlinear hierarchical feature representations of the original data. Tested on over 20 datasets, VASC shows superior performances in most cases and exhibits broader dataset compatibility compared to four state-of-the-art dimension reduction and visualization methods. In addition, VASC provides better representations for very rare cell populations in the 2D visualization. As a case study, VASC successfully re-establishes the cell dynamics in pre-implantation embryos and identifies several candidate marker genes associated with early embryo development. Moreover, VASC also performs well on a 10× Genomics dataset with more cells and higher dropout rate.
基金the financial support from the Chilean National Research and Development Agency(Agencia Nacional de Investigación y Desarrollo,ANID)through Fondo Nacional de Desarrollo Científico y Tecnológico(FONDECYT)Regular 1240503Fondo de Valorización de la Investigación(FOVI)230030 projectsthe financial support from the ANID through FONDECYT Reg-ular 1240501.
文摘In the face of the unrelenting challenge posed by earthquakes-a natural hazard of unpredictable nature with a legacy of significant loss of life,destruction of infrastructure,and profound economic and social impacts-the scientific community has pursued advancements in earthquake early warning systems(EEWSs).These systems are vital for pre-emptive actions and decision-making that can save lives and safeguard critical infrastructure.This study proposes and validates a domain-informed deep learning-based EEWS called the hybrid earthquake early warning framework for estimating response spectra(HEWFERS),which represents a significant leap forward in the capabilities to predict ground shaking intensity in real-time,aligning with the United Nations’disaster risk reduction goals.HEWFERS ingeniously integrates a domain-informed variational autoencoder for physics-based latent variable(LV)extraction,a feed-forward neural network for on-site prediction,and Gaussian process regression for spatial prediction.Adopting explainable artificial intelligence-based Shapley explanations further elucidates the predictive mechanisms,ensuring stakeholder-informed decisions.By conducting an extensive analysis of the proposed framework under a large database of approximately 14000 recorded ground motions,this study offers insights into the potential of integrating machine learning with seismology to revolutionize earthquake preparedness and response,thus paving the way for a safer and more resilient future.
基金Financial support from the Fundamental Research Funds for the Central Universities(ZJ2022-003,JG2022-27,J2020-060,and J2021-060)Sichuan Province Engineering Technology Research Center of General Aircraft Maintenance(GAMRC2021YB08)the Young Scientists Fund of the National Natural Science Foundation of China(No.52105417)is acknowledged.
文摘To overcome the challenges of limited experimental data and improve the accuracy of empirical formulas,we propose a low-cycle fatigue(LCF)life prediction model for nickel-based superalloys using a data augmentation method.This method utilizes a variational autoencoder(VAE)to generate low-cycle fatigue data and form an augmented dataset.The Pearson correlation coefficient(PCC)is employed to verify the similarity of feature distributions between the original and augmented datasets.Six machine learning models,namely random forest(RF),artificial neural network(ANN),support vector machine(SVM),gradient-boosted decision tree(GBDT),eXtreme Gradient Boosting(XGBoost),and Categorical Boosting(CatBoost),are utilized to predict the LCF life of nickel-based superalloys.Results indicate that the proposed data augmentation method based on VAE can effectively expand the dataset,and the mean absolute error(MAE),root mean square error(RMSE),and R-squared(R^(2))values achieved using the CatBoost model,with respective values of 0.0242,0.0391,and 0.9538,are superior to those of the other models.The proposed method reduces the cost and time associated with LCF experiments and accurately establishes the relationship between fatigue characteristics and LCF life of nickel-based superalloys.
基金the National Natural Science Foundation of China(22178243 and 22038008).
文摘Direct coal liquefaction products offer a considerable quantity of cycloalkanes, which are the valuable candidates for making the high energy density fuels. The creation of such fuels depends on designing molecular structures and calculating their properties, which can be expedited with computer-aided techniques. In this study, a dataset containing 367 fuel molecules was constructed based on the analysis of direct coal liquefied oil. Three convolutional neural network property prediction models have been created based on molecular structure-physical and chemical property data from the library. All the models have good fitting ability with R2 values above 0.97. Then, a variational autoencoder generation model has been established using the molecular structures from the library, focusing on the structure of saturated cycloalkanes. The structure-property prediction model was then applied to the newly generated molecules, assessing their density, volumetric calorific value, and melting point. As a result, 70000 novel molecular structures were generated, and 25 molecular structures meeting the criteria for high energy density fuels were identified. The established variational autoencoder model in this study effectively assimilates the structural information from the sample set and autonomously generates novel high energy density fuels, which is difficult to achieve in traditional experimental methods.
基金This work was supported by the National Research Foundation of Korea(NRF)grant funded by the Korean government(MSIT)(No.2021R1A2C2011391)was supported by the Institute of Information&communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.2021-0-01806Development of security by design and security management technology in smart factory).
文摘Contemporary attackers,mainly motivated by financial gain,consistently devise sophisticated penetration techniques to access important information or data.The growing use of Internet of Things(IoT)technology in the contemporary convergence environment to connect to corporate networks and cloud-based applications only worsens this situation,as it facilitates multiple new attack vectors to emerge effortlessly.As such,existing intrusion detection systems suffer from performance degradation mainly because of insufficient considerations and poorly modeled detection systems.To address this problem,we designed a blended threat detection approach,considering the possible impact and dimensionality of new attack surfaces due to the aforementioned convergence.We collectively refer to the convergence of different technology sectors as the internet of blended environment.The proposed approach encompasses an ensemble of heterogeneous probabilistic autoencoders that leverage the corresponding advantages of a convolutional variational autoencoder and long short-term memory variational autoencoder.An extensive experimental analysis conducted on the TON_IoT dataset demonstrated 96.02%detection accuracy.Furthermore,performance of the proposed approach was compared with various single model(autoencoder)-based network intrusion detection approaches:autoencoder,variational autoencoder,convolutional variational autoencoder,and long short-term memory variational autoencoder.The proposed model outperformed all compared models,demonstrating F1-score improvements of 4.99%,2.25%,1.92%,and 3.69%,respectively.
基金The financial support from the Fundamental Research Funds for Higher Education Institutions of Heilongjiang Province(Grant No.145209126)the Research and Innovation Platform Project(Grant No.145309314)is acknowledged.
文摘As the popularity and dependence on the Internet increase,DDoS(distributed denial of service)attacks seriously threaten network security.By accurately distinguishing between different types of DDoS attacks,targeted defense strategies can be formulated,significantly improving network protection efficiency.DDoS attacks usually manifest as an abnormal increase in network traffic,and their diverse types of attacks,along with a severe data imbalance,make it difficult for traditional classification methods to effectively identify a small number of attack types.To solve this problem,this paper proposes a DDoS recognition method CVWGG(Conditional Variational Autoencoder-Wasserstein Generative Adversarial Network-gradient penalty-Gated Recurrent Unit)for unbalanced data,which generates less noisy data and high data quality compared with existing methods.CVWGG mainly includes unbalanced data processing for CVWG,feature extraction,and classification.CVWGG uses the CVAE(Conditional Variational Autoencoder)to improve the WGAN(Wasserstein Generative Adversarial Network)and introduces a GP(gradient penalty)term to design the loss function to generate balanced data,which enhances the learning ability and stability of the data.Subsequently,the GRU(Gated Recurrent Units)are used to capture the temporal features and patterns of the data.Finally,the logsoftmax function is used to differentiate DDoS attack categories.Using PyCharm and Python 3.10 for programming and evaluating performance with metrics such as accuracy and precision,the results show that the method achieved accuracy rates of 96.0%and 97.3%on two datasets,respectively.Additionally,comparison and ablation experiment results demonstrate that CVWGG effectively mitigates the imbalance between DDoS attack categories,significantly improves the classification accuracy of different types of attacks and provides a valuable reference for network security defense.
基金supported by ConocoPhillips through the DataDriven Intelligent Engineering and Characterization(DICE)research group.
文摘Geological model compression is crucial for making large and complex models more manageable.By reducing the size of these models,compression techniques enable efficient storage,enhance computational efficiency,making it feasible to perform complex simulations and analyses in a shorter time.This is particularly important in applications such as reservoir management,groundwater hydrology,and geological carbon storage,where large geomodels with millions of grid cells are common.This study presents a comprehensive overview of previous work on geomodel compression and introduces several autoencoder-based deep-learning architectures for low-dimensional representation of modified Bruggefield geomodels.The compression and reconstruction efficiencies of autoencoders(AE),variational autoencoders(VAE),vector-quantized variational autoencoders(VQ-VAE),and vector-quantized variational autoencoders 2(VQ-VAE2)were tested and compared to the traditional singular value decomposition(SVD)method.Results show that the deep-learning-based approaches significantly outperform SVD,achieving higher compression ratios while maintaining or even exceeding the reconstruction quality.Notably,VQ-VAE2 achieves the highest compression ratio of 667:1 with a structural similarity index metric(SSIM)of 0.92,far surpassing the 10:1 compression ratio of SVD with a SSIM of 0.9.The result of this work shows that,unlike traditional approaches,which often rely on linear transformations and can struggle to capture complex,non-linear relationships within geological data,VQ-VAE's use of vector quantization helps in preserving high-resolution details and enhances the model's ability to generalize across varying geological complexities.
基金co-supported by the National Key Project of China(No.GJXM92579)the National Natural Science Foundation of China(Nos.92052203,61903178 and61906081)。
文摘Inverse design has long been an efficient and powerful design tool in the aircraft industry.In this paper,a novel inverse design method for supercritical airfoils is proposed based on generative models in deep learning.A Conditional Variational Auto Encoder(CVAE)and an integrated generative network CVAE-GAN that combines the CVAE with the Wasserstein Generative Adversarial Networks(WGAN),are conducted as generative models.They are used to generate target wall Mach distributions for the inverse design that matches specified features,such as locations of suction peak,shock and aft loading.Qualitative and quantitative results show that both adopted generative models can generate diverse and realistic wall Mach number distributions satisfying the given features.The CVAE-GAN model outperforms the CVAE model and achieves better reconstruction accuracies for all the samples in the dataset.Furthermore,a deep neural network for nonlinear mapping is adopted to obtain the airfoil shape corresponding to the target wall Mach number distribution.The performances of the designed deep neural network are fully demonstrated and a smoothness measurement is proposed to quantify small oscillations in the airfoil surface,proving the authenticity and accuracy of the generated airfoil shapes.
