Real-time 6 Degree-of-Freedom(DoF)pose estimation is of paramount importance for various on-orbit tasks.Benefiting from the development of deep learning,Convolutional Neural Networks(CNNs)in feature extraction has yie...Real-time 6 Degree-of-Freedom(DoF)pose estimation is of paramount importance for various on-orbit tasks.Benefiting from the development of deep learning,Convolutional Neural Networks(CNNs)in feature extraction has yielded impressive achievements for spacecraft pose estimation.To improve the robustness and interpretability of CNNs,this paper proposes a Pose Estimation approach based on Variational Auto-Encoder structure(PE-VAE)and a Feature-Aided pose estimation approach based on Variational Auto-Encoder structure(FA-VAE),which aim to accurately estimate the 6 DoF pose of a target spacecraft.Both methods treat the pose vector as latent variables,employing an encoder-decoder network with a Variational Auto-Encoder(VAE)structure.To enhance the precision of pose estimation,PE-VAE uses the VAE structure to introduce reconstruction mechanism with the whole image.Furthermore,FA-VAE enforces feature shape constraints by exclusively reconstructing the segment of the target spacecraft with the desired shape.Comparative evaluation against leading methods on public datasets reveals similar accuracy with a threefold improvement in processing speed,showcasing the significant contribution of VAE structures to accuracy enhancement,and the additional benefit of incorporating global shape prior features.展开更多
Single nucletide polymorphism(SNP)is an important factor for the study of genetic variation in human families and animal and plant strains.Therefore,it is widely used in the study of population genetics and disease re...Single nucletide polymorphism(SNP)is an important factor for the study of genetic variation in human families and animal and plant strains.Therefore,it is widely used in the study of population genetics and disease related gene.In pharmacogenomics research,identifying the association between SNP site and drug is the key to clinical precision medication,therefore,a predictive model of SNP site and drug association based on denoising variational auto-encoder(DVAE-SVM)is proposed.Firstly,k-mer algorithm is used to construct the initial SNP site feature vector,meanwhile,MACCS molecular fingerprint is introduced to generate the feature vector of the drug module.Then,we use the DVAE to extract the effective features of the initial feature vector of the SNP site.Finally,the effective feature vector of the SNP site and the feature vector of the drug module are fused input to the support vector machines(SVM)to predict the relationship of SNP site and drug module.The results of five-fold cross-validation experiments indicate that the proposed algorithm performs better than random forest(RF)and logistic regression(LR)classification.Further experiments show that compared with the feature extraction algorithms of principal component analysis(PCA),denoising auto-encoder(DAE)and variational auto-encode(VAE),the proposed algorithm has better prediction results.展开更多
Non-intrusive load monitoring(NILM)can infer load profiles for each individual appliance from aggregated power consumption signals without installing extra sub-meters.However,performance of traditional energy disaggre...Non-intrusive load monitoring(NILM)can infer load profiles for each individual appliance from aggregated power consumption signals without installing extra sub-meters.However,performance of traditional energy disaggregation methods deteriorates in complex environments,especially susceptible to the presence of other high power consumption appliances.Practicalities are also limited by diversity of household load patterns and measurement errors.In order to address these problems,a hybrid deep learning model consisting of two steps is proposed in this paper.First,an improved variational autoencoder(VAE)structure is introduced for preliminary energy disaggregation,where the encoder and decoder layers are long short-term networks(LSTM)to extract temporal characteristics of active power signals.Afterward,a post-processing method based on Siamese one-dimensional convolutional neural network(S-1D-CNN)is adopted to remove incorrectly predicted activation segments of target appliances.Experiments are conducted on two public datasets,and results show remarkable improvements on prediction accuracy over other deep learning methods.Both transferability and stability of the proposed model are verified under different working conditions.展开更多
High-dimensional linear mixed models are widely used for longitudinal data analysis,yet their reliance on normality assumptions often limits applicability in psychometric and biomedical settings.To address this,the au...High-dimensional linear mixed models are widely used for longitudinal data analysis,yet their reliance on normality assumptions often limits applicability in psychometric and biomedical settings.To address this,the authors propose a high-dimensional skew-normal linear mixed model and develop a novel variational Baysian method that integrates spike-and-slab Lasso priors for simultaneous parameter estimation and variable selection.To handle dependencies in the joint posterior,the authors propose a variational auto-encoders to extract latent features,and employ a coordinate ascent algorithm to optimize the evidence lower bound(ELBO),circumventing intractable integrals.Model comparison is conducted using the Bayes factor,approximated via the ELBO.The effectiveness of the proposed methodologies is demonstrated through simulation studies and a real-data application.展开更多
Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security.The advent of Genomic Selection heralds a new epoch in breeding,characterized by its capacity to harness whole...Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security.The advent of Genomic Selection heralds a new epoch in breeding,characterized by its capacity to harness whole-genome variation for genomic prediction.This approach transcends the need for prior knowledge of genes associated with specific traits.Nonetheless,the vast dimensionality of genomic data juxtaposed with the relatively limited number of phenotypic samples often leads to the“curse of dimensionality”,where traditional statistical,machine learning,and deep learning methods are prone to overfitting and suboptimal predictive performance.To surmount this challenge,we introduce a unified Variational auto-encoder based Multi-task Genomic Prediction model(VMGP)that integrates self-supervised genomic compression and reconstruction with multiple prediction tasks.This approach provides a robust solution,offering a formidable predictive framework that has been rigorously validated across public datasets for wheat,rice,and maize.Our model demonstrates exceptional capabilities in multi-phenotype and multi-environment genomic prediction,successfully navigating the complexities of cross-population genomic selection and underscoring its unique strengths and utility.Furthermore,by integrating VMGP with model interpretability,we can effectively triage relevant single nucleotide polymorphisms,thereby enhancing prediction performance and proposing potential cost-effective genotyping solutions.The VMGP framework,with its simplicity,stable predictive prowess,and open-source code,is exceptionally well-suited for broad dissemination within plant breeding programs.It is particularly advantageous for breeders who prioritize phenotype prediction yet may not possess extensive knowledge in deep learning or proficiency in parameter tuning.展开更多
The influenza virus changes its antigenicity frequently due to rapid mutations, leading to immune escape and failure of vaccination. Rapid determination of the influenza antigenicity could help identify the antigenic ...The influenza virus changes its antigenicity frequently due to rapid mutations, leading to immune escape and failure of vaccination. Rapid determination of the influenza antigenicity could help identify the antigenic variants in time. Here, we built a stacked auto-encoder (SAE) model for predicting the antigenic variant of human influenza A(H3N2) viruses based on the hemagglutinin (HA) protein sequences. The model achieved an accuracy of 0.95 in five-fold cross-validations, better than the logistic regression model did. Further analysis of the model shows that most of the active nodes in the hidden layer reflected the combined contribution of multiple residues to antigenic variation. Besides, some features (residues on HA protein) in the input layer were observed to take part in multiple active nodes, such as residue 189, 145 and 156, which were also reported to mostly determine the antigenic variation of influenza A(H3N2) viruses. Overall,this work is not only useful for rapidly identifying antigenic variants in influenza prevention, but also an interesting attempt in inferring the mechanisms of biological process through analysis of SAE model, which may give some insights into interpretation of the deep learning展开更多
The Proton Exchange Membrane Fuel Cell(PEMFC)converts the chemical energy of hydrogen fuel directly into electrical energy with broad application prospects.Understanding how current density is distributed in the PEMFC...The Proton Exchange Membrane Fuel Cell(PEMFC)converts the chemical energy of hydrogen fuel directly into electrical energy with broad application prospects.Understanding how current density is distributed in the PEMFC systems is crucial as it is a key factor influencing system performance.However,direct modeling for current distribution may encounter the challenge of dimensional catastrophe owing to the high dimensionality of the data.This paper uses a high-resolution segmented measurement device with 396 points to conduct experimental tests on the current distribution of a PEMFC with reactive area of 406 cm2 during a stepwise increase in load current.The current distribution is modeled based on the test results to learn the mapping relationship between the experimental parameters and the current distribution.The proposed model utilizes a Conditional Variational Auto-Encoder(CVAE)to generate current distributions.The MSE(Mean-Square Error)of the trained CVAE model reaches 9.2×10-5,and the comparison results show that the 222.9A current distribution error has the largest MSE of 6.36×10-4 and a KL Divergence(Kullback-Leibler Divergence)of 9.55×10-4,both of which are at a low level.This model enables the direct determination of the current distribution based on the experimental parameters,thereby establishing a technical foundation for investigating the impact of experimental conditions on fuel cells.This model is also of great significance for research on fuel cell system control strategies and fault diagnosis.展开更多
This study proposes a robust control strategy for semi-active air suspension systems(SASS)based on entropy theory.The multi-objective optimization of a system can be described as a long-term problem using entropy valu...This study proposes a robust control strategy for semi-active air suspension systems(SASS)based on entropy theory.The multi-objective optimization of a system can be described as a long-term problem using entropy values by innovatively introducing entropy theory.The state marginal probability of the SASS is incorporated into the reward function as the entropy value.This incorporation incentivizes the agent to focus on reducing the entropy value of the system state over a period of time during the exploration process,thereby reducing the degree of coupling between system states.This study also proposes an optimization strategy that introduces a state observer based on a variational auto-encoder.The observer can extract environmental features from historical states and expand the dimension of the state,thereby enhancing the generalization performance of the system under different road excitations.Bench test results show that the algorithm improves ride comfort while ensuring robustness.The root mean square(RMS)of body vertical acceleration decreased by 13.01%,while the RMS of dynamic tyre displacement only increased by 2.36%.展开更多
土木工程结构损伤识别中无监督的阈值方法无需标注数据,然而数据的不确定性导致阈值附近存在识别不准的问题。针对无监督结构损伤识别阈值方法在阈值附近存在误报和漏报的问题,基于深度支持向量数据描述(Deep-SVDD)提出基于超球环描述...土木工程结构损伤识别中无监督的阈值方法无需标注数据,然而数据的不确定性导致阈值附近存在识别不准的问题。针对无监督结构损伤识别阈值方法在阈值附近存在误报和漏报的问题,基于深度支持向量数据描述(Deep-SVDD)提出基于超球环描述的概率性结构损伤识别方法VAEKL-RDDP(Variational AutoEncoder with Kullback-Leibler divergence constrained for hypersphere Ring Data Description Probabilistic damage identification)。该方法以变分自编码器(VAE)为框架,利用KL(Kullback-Leibler)散度约束构造超球环。首先,预训练VAE,以重建结构加速度响应;其次,引入KL散度,以联合训练预训练的VAE编码器与超球环描述方法,从而在加速度数据特征的后验分布中提取可靠分类边界;最后,依据分类边界构造超球环,依托所构造的超球环对结构进行损伤识别,并采用累积概率密度方法评估超球环内数据。在真实的Z24桥结构的渐进性损伤和足尺木亭振动台实验中,与基于自编码器(AE)重建的基线方法相比,VAEKL-RDDP的准确率和召回率分别平均提高了24.9%和36.7%;而相较于Deep-SVDD和扩散模型的插补预测(ImDiffusion)等方法,VAEKL-RDDP的准确率和召回率分别平均提升了20.8%和33.7%,验证了所提方法提高了损伤检测的性能,降低了漏报可能性。展开更多
基金supported by the National Natural Science Foundation of China(No.52272390)the Natural Science Foundation of Heilongjiang Province of China(No.YQ2022A009)the Shanghai Sailing Program,China(No.20YF1417300).
摘要Real-time 6 Degree-of-Freedom(DoF)pose estimation is of paramount importance for various on-orbit tasks.Benefiting from the development of deep learning,Convolutional Neural Networks(CNNs)in feature extraction has yielded impressive achievements for spacecraft pose estimation.To improve the robustness and interpretability of CNNs,this paper proposes a Pose Estimation approach based on Variational Auto-Encoder structure(PE-VAE)and a Feature-Aided pose estimation approach based on Variational Auto-Encoder structure(FA-VAE),which aim to accurately estimate the 6 DoF pose of a target spacecraft.Both methods treat the pose vector as latent variables,employing an encoder-decoder network with a Variational Auto-Encoder(VAE)structure.To enhance the precision of pose estimation,PE-VAE uses the VAE structure to introduce reconstruction mechanism with the whole image.Furthermore,FA-VAE enforces feature shape constraints by exclusively reconstructing the segment of the target spacecraft with the desired shape.Comparative evaluation against leading methods on public datasets reveals similar accuracy with a threefold improvement in processing speed,showcasing the significant contribution of VAE structures to accuracy enhancement,and the additional benefit of incorporating global shape prior features.
基金Lanzhou Talent Innovation and Entrepreneurship Project(No.2020-RC-14)。
摘要Single nucletide polymorphism(SNP)is an important factor for the study of genetic variation in human families and animal and plant strains.Therefore,it is widely used in the study of population genetics and disease related gene.In pharmacogenomics research,identifying the association between SNP site and drug is the key to clinical precision medication,therefore,a predictive model of SNP site and drug association based on denoising variational auto-encoder(DVAE-SVM)is proposed.Firstly,k-mer algorithm is used to construct the initial SNP site feature vector,meanwhile,MACCS molecular fingerprint is introduced to generate the feature vector of the drug module.Then,we use the DVAE to extract the effective features of the initial feature vector of the SNP site.Finally,the effective feature vector of the SNP site and the feature vector of the drug module are fused input to the support vector machines(SVM)to predict the relationship of SNP site and drug module.The results of five-fold cross-validation experiments indicate that the proposed algorithm performs better than random forest(RF)and logistic regression(LR)classification.Further experiments show that compared with the feature extraction algorithms of principal component analysis(PCA),denoising auto-encoder(DAE)and variational auto-encode(VAE),the proposed algorithm has better prediction results.
摘要Non-intrusive load monitoring(NILM)can infer load profiles for each individual appliance from aggregated power consumption signals without installing extra sub-meters.However,performance of traditional energy disaggregation methods deteriorates in complex environments,especially susceptible to the presence of other high power consumption appliances.Practicalities are also limited by diversity of household load patterns and measurement errors.In order to address these problems,a hybrid deep learning model consisting of two steps is proposed in this paper.First,an improved variational autoencoder(VAE)structure is introduced for preliminary energy disaggregation,where the encoder and decoder layers are long short-term networks(LSTM)to extract temporal characteristics of active power signals.Afterward,a post-processing method based on Siamese one-dimensional convolutional neural network(S-1D-CNN)is adopted to remove incorrectly predicted activation segments of target appliances.Experiments are conducted on two public datasets,and results show remarkable improvements on prediction accuracy over other deep learning methods.Both transferability and stability of the proposed model are verified under different working conditions.
基金supported by the National Natural Science Foundation of China under Grant No.12271472the General Program of the National Social Science Fund of China under Grant No.25BTJ043Fundamental and Interdisciplinary Disciplines Break-through Plan of the Ministry of Education of China under Grant No.JYB2025XDXM904。
摘要High-dimensional linear mixed models are widely used for longitudinal data analysis,yet their reliance on normality assumptions often limits applicability in psychometric and biomedical settings.To address this,the authors propose a high-dimensional skew-normal linear mixed model and develop a novel variational Baysian method that integrates spike-and-slab Lasso priors for simultaneous parameter estimation and variable selection.To handle dependencies in the joint posterior,the authors propose a variational auto-encoders to extract latent features,and employ a coordinate ascent algorithm to optimize the evidence lower bound(ELBO),circumventing intractable integrals.Model comparison is conducted using the Bayes factor,approximated via the ELBO.The effectiveness of the proposed methodologies is demonstrated through simulation studies and a real-data application.
基金supported by the National Key Research and Development Program of China(No.2024YFD1201500)the Key Research and Development Program of Jiangsu Province,China(No.BE2022337,BE2023302,and BE2023315)the National Innovation Center for Digital Seed Industry,Beijing,China,100097.
摘要Plant breeding stands as a cornerstone for agricultural productivity and the safeguarding of food security.The advent of Genomic Selection heralds a new epoch in breeding,characterized by its capacity to harness whole-genome variation for genomic prediction.This approach transcends the need for prior knowledge of genes associated with specific traits.Nonetheless,the vast dimensionality of genomic data juxtaposed with the relatively limited number of phenotypic samples often leads to the“curse of dimensionality”,where traditional statistical,machine learning,and deep learning methods are prone to overfitting and suboptimal predictive performance.To surmount this challenge,we introduce a unified Variational auto-encoder based Multi-task Genomic Prediction model(VMGP)that integrates self-supervised genomic compression and reconstruction with multiple prediction tasks.This approach provides a robust solution,offering a formidable predictive framework that has been rigorously validated across public datasets for wheat,rice,and maize.Our model demonstrates exceptional capabilities in multi-phenotype and multi-environment genomic prediction,successfully navigating the complexities of cross-population genomic selection and underscoring its unique strengths and utility.Furthermore,by integrating VMGP with model interpretability,we can effectively triage relevant single nucleotide polymorphisms,thereby enhancing prediction performance and proposing potential cost-effective genotyping solutions.The VMGP framework,with its simplicity,stable predictive prowess,and open-source code,is exceptionally well-suited for broad dissemination within plant breeding programs.It is particularly advantageous for breeders who prioritize phenotype prediction yet may not possess extensive knowledge in deep learning or proficiency in parameter tuning.
摘要The influenza virus changes its antigenicity frequently due to rapid mutations, leading to immune escape and failure of vaccination. Rapid determination of the influenza antigenicity could help identify the antigenic variants in time. Here, we built a stacked auto-encoder (SAE) model for predicting the antigenic variant of human influenza A(H3N2) viruses based on the hemagglutinin (HA) protein sequences. The model achieved an accuracy of 0.95 in five-fold cross-validations, better than the logistic regression model did. Further analysis of the model shows that most of the active nodes in the hidden layer reflected the combined contribution of multiple residues to antigenic variation. Besides, some features (residues on HA protein) in the input layer were observed to take part in multiple active nodes, such as residue 189, 145 and 156, which were also reported to mostly determine the antigenic variation of influenza A(H3N2) viruses. Overall,this work is not only useful for rapidly identifying antigenic variants in influenza prevention, but also an interesting attempt in inferring the mechanisms of biological process through analysis of SAE model, which may give some insights into interpretation of the deep learning
基金sponsored by Science and Technology Program of Sichuan Province(2024ZDZX0035 and 2024ZHCG0072)。
摘要The Proton Exchange Membrane Fuel Cell(PEMFC)converts the chemical energy of hydrogen fuel directly into electrical energy with broad application prospects.Understanding how current density is distributed in the PEMFC systems is crucial as it is a key factor influencing system performance.However,direct modeling for current distribution may encounter the challenge of dimensional catastrophe owing to the high dimensionality of the data.This paper uses a high-resolution segmented measurement device with 396 points to conduct experimental tests on the current distribution of a PEMFC with reactive area of 406 cm2 during a stepwise increase in load current.The current distribution is modeled based on the test results to learn the mapping relationship between the experimental parameters and the current distribution.The proposed model utilizes a Conditional Variational Auto-Encoder(CVAE)to generate current distributions.The MSE(Mean-Square Error)of the trained CVAE model reaches 9.2×10-5,and the comparison results show that the 222.9A current distribution error has the largest MSE of 6.36×10-4 and a KL Divergence(Kullback-Leibler Divergence)of 9.55×10-4,both of which are at a low level.This model enables the direct determination of the current distribution based on the experimental parameters,thereby establishing a technical foundation for investigating the impact of experimental conditions on fuel cells.This model is also of great significance for research on fuel cell system control strategies and fault diagnosis.
基金supported by the Science Fund of the State Key Laboratory of Advanced Design and Manufacturing Technology for Vehicle(Grant No.82315002).
摘要This study proposes a robust control strategy for semi-active air suspension systems(SASS)based on entropy theory.The multi-objective optimization of a system can be described as a long-term problem using entropy values by innovatively introducing entropy theory.The state marginal probability of the SASS is incorporated into the reward function as the entropy value.This incorporation incentivizes the agent to focus on reducing the entropy value of the system state over a period of time during the exploration process,thereby reducing the degree of coupling between system states.This study also proposes an optimization strategy that introduces a state observer based on a variational auto-encoder.The observer can extract environmental features from historical states and expand the dimension of the state,thereby enhancing the generalization performance of the system under different road excitations.Bench test results show that the algorithm improves ride comfort while ensuring robustness.The root mean square(RMS)of body vertical acceleration decreased by 13.01%,while the RMS of dynamic tyre displacement only increased by 2.36%.
摘要土木工程结构损伤识别中无监督的阈值方法无需标注数据,然而数据的不确定性导致阈值附近存在识别不准的问题。针对无监督结构损伤识别阈值方法在阈值附近存在误报和漏报的问题,基于深度支持向量数据描述(Deep-SVDD)提出基于超球环描述的概率性结构损伤识别方法VAEKL-RDDP(Variational AutoEncoder with Kullback-Leibler divergence constrained for hypersphere Ring Data Description Probabilistic damage identification)。该方法以变分自编码器(VAE)为框架,利用KL(Kullback-Leibler)散度约束构造超球环。首先,预训练VAE,以重建结构加速度响应;其次,引入KL散度,以联合训练预训练的VAE编码器与超球环描述方法,从而在加速度数据特征的后验分布中提取可靠分类边界;最后,依据分类边界构造超球环,依托所构造的超球环对结构进行损伤识别,并采用累积概率密度方法评估超球环内数据。在真实的Z24桥结构的渐进性损伤和足尺木亭振动台实验中,与基于自编码器(AE)重建的基线方法相比,VAEKL-RDDP的准确率和召回率分别平均提高了24.9%和36.7%;而相较于Deep-SVDD和扩散模型的插补预测(ImDiffusion)等方法,VAEKL-RDDP的准确率和召回率分别平均提升了20.8%和33.7%,验证了所提方法提高了损伤检测的性能,降低了漏报可能性。