检索结果-内蒙古大学图书馆

DHHNN: A Dynamic Hypergraph Hyperbolic Neural Network based on variational autoencoder for multimodal data integration and node classification

引用

INFORMATION FUSION 2025年 119卷

作者： Mei, Zhangyu Bi, Xiao Li, Dianguo Xia, Wen Yang, Fan Wu, Hao Shandong Univ Sch Software Jinan 250100 Shandong Peoples R China Qufu Normal Univ Sch Comp Sci Rizhao 276827 Shandong Peoples R China Shandong Univ Sch Math Jinan 250100 Shandong Peoples R China Shandong Univ Hosp 2 Dept Pediat Surg Jinan 250033 Shandong Peoples R China Shandong Univ Qilu Hosp Dept Neurol Jinan 250012 Shandong Peoples R China Shandong Univ Cheeloo Coll Med Sch Publ Hlth Dept Biostat Jinan 250000 Shandong Peoples R China Shandong Univ Shenzhen Res Inst Shenzhen 518063 Guangdong Peoples R China

In recent years, the integration of hyperbolic geometry with Graph Neural Networks (GNNs) has garnered significant attention due to its effectiveness in capturing complex hierarchical structures, particularly within real-world graphs and scale-free networks. Although hyperbolic neural networks have shown strong performance across various domains, most existing models rely on static graph structures, limiting their adaptability to dynamic data. Previous studies have primarily focused on improving the modeling capacity of hyperbolic space for latent space data during training, often neglecting the preservation of high-order intrinsic features before training. To address this, we propose a novel Dynamic Hypergraph Hyperbolic Neural Network (DHHNN) based on a variational autoencoder for multimodal data integration. This model combines the advantages of hyperbolic geometry, dynamic hypergraphs, and the self-attention mechanism to enhance multimodal data representation learning. DHHNN introduces a dynamic hypergraph framework that continuously adjusts the relationships between hypernodes and hyperedges during training, effectively capturing higher-order dependencies within complex networks. Furthermore, the self-attention mechanism dynamically regulates the dependency levels between hypernodes and hyperedges, enhancing the model's ability to capture long-range dependencies and complex feature interactions. Leveraging the negative curvature of hyperbolic space, DHHNN compactly and accurately represents complex scale-free networks. Experimental results on seven benchmark datasets and latent space visualizations demonstrate that DHHNN provides compact and effective data representation, outperforming existing models and achieving state-of-the-art performance in node classification tasks.

关键词： Hyperbolic hypergraph Dynamic hypergraph variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Attenuation Tomography Using Low-Frequency Ultrasound With variational autoencoder for Thorax Imaging: Experimental Study

引用

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2025年第1期72卷 238-248页

作者： Zhang, Tong Shi, Haokang Lin, Zhichao Cao, Yeyu Guo, Rui Zhang, Haolin Li, Maokun Yang, Fan Xu, Shenheng Tsinghua Univ Beijing Natl Res Ctr Informat Sci & Technol Inst Precis Med Dept Elect Engn Beijing 100084 Peoples R China Johns Hopkins Univ Whiting Sch Engn Dept Comp Sci Baltimore MD 21218 USA Chinese Acad Sci Aerosp Informat Res Inst Beijing Peoples R China

In this paper, we introduce a novel inversion methodology employing the variational autoencoder (VAE) for human thorax attenuation tomography using low-frequency ultrasound. The VAE is trained to assimilate the structural priors of the human thorax, utilizing training samples generated from computed tomography (CT) scans. This approach enables the compression of high-dimensional attenuation distributions into a lower-dimensional latent space. During the inversion process, the latent code is optimized, and then the reconstructed model is generated by the decoder of the VAE. This process can effectively integrate prior information of the domain of interest (DOI) into the inversion through coding and decoding, which would mitigate the ill-posedness of the inverse problem and facilitate better outcomes. Our method demonstrates robust generalization capabilities and noise resilience in numerical simulations, outperforming the conventional pixel-based Gauss-Newton method. Human subject experiment further corroborates the effectiveness of our approach. This is also the first experimental validation of the feasibility of low-frequency ultrasound functional imaging of the human thorax. Although the current study presents certain limitations, it underscores the potential of low-frequency ultrasound in the continuous monitoring of the human respiratory system.

关键词： Thorax Ultrasonic imaging Imaging Attenuation Codes Decoding Training Attenuation tomography low-frequency ultrasound respiratory system monitoring thorax functional imaging variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Explainable hybrid tabular variational autoencoder and feature Tokenizer Transformer for depression prediction

引用

EXPERT SYSTEMS WITH APPLICATIONS 2025年 265卷

作者： Tran, Vinh Quang Byeon, Haewon Inje Univ Dept Digital Antiaging Healthcare BK21 Gimhae 50834 South Korea

Recent advancements in machine learning and deep learning have significantly improved the diagnosis, detection, prediction, and prognosis of depressive disorders. However, these methodologies have issues related to generalizability, transparency, data scarcity, privacy concerns, and class imbalance. This study develops a robust and interpretable model for predicting depression in South Korea, addressing these limitations. We employed a hybrid deep learning approach that integrates the Feature Tokenizer Transformer model, specifically designed for tabular data, to effectively tokenize and process categorical and numerical features, alongside synthetic data generated by the tabular variational autoencoder (TVAE). TVAE is an adaptation of variational autoencoders that uses a specialized loss function for tabular data. generated high-quality synthetic data from the Korea National Health and Nutrition Examination Survey (KNHANES) dataset. The efficacy of the TVAE-generated data was validated using non-parametric statistical tests, achieving 86.30% on the Kolmogorov-Smirnov test and 76.65% on the Chi-squared test. Performance evaluation metrics, such as accuracy, recall, F1-score, and AUC, demonstrated our model's effectiveness, yielding an accuracy 0.7783, a recall score of 0.5310, an F1-score of 0.4657, and an AUC of 0.6822, outperforming state-of-the-art models. Additionally, SHapley Additive exPlanations analysis was incorporated to explain feature importance, offering valuable insights for healthcare professionals. This research highlights the potential of deep learning and synthetic data generation techniques to enhance depression prediction, addressing critical challenges such as generalizability, class imbalance, data privacy, and interpretability over existing models.

关键词： variational autoencoder Feature tokenizer Transformer Depression Explainable

来源：评论

学校读者我要写书评

暂无评论

Univariate conditional variational autoencoder for morphogenic pattern design in frontal polymerization-based manufacturing

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2025年 438卷

作者： Liu, Qibang Cai, Pengfei Abueidda, Diab Vyas, Sagar Koric, Seid Gomez-Bombarelli, Rafael Geubelle, Philippe Univ Illinois Natl Ctr Supercomp Applicat Urbana IL 61801 USA Univ Illinois Beckman Inst Adv Sci & Technol Urbana IL 61801 USA Univ Illinois Grainger Coll Engn Dept Aerosp Engn Urbana IL 61801 USA Univ Illinois Grainger Coll Engn Dept Mech Sci & Engn Urbana IL 61801 USA New York Univ Abu Dhabi Civil & Urban Engn Dept Abu Dhabi U Arab Emirates Kansas State Univ Dept Ind & Mfg Syst Engn Manhattan KS 66506 USA MIT Dept Mat Sci & Engn Cambridge MA 02139 USA

Under some initial and boundary conditions, the rapid reaction-thermal diffusion process taking place during frontal polymerization (FP) destabilizes the planar mode of front propagation, leading to spatially varying, complex hierarchical patterns in thermoset polymeric materials. Although modern reaction-diffusion models can predict the patterns resulting from unstable FP, the inverse design of patterns, which aims to retrieve process conditions that produce a desired pattern, remains an open challenge due to the non-unique and non-intuitive mapping between process conditions and manufactured patterns. In this work, we propose a probabilistic generative model named univariate conditional variational autoencoder (UcVAE) for the inverse design of hierarchical patterns in FP-based manufacturing. Unlike the cVAE, which encodes both the design space and the design target, the UcVAE encodes only the design space. In the encoder of the UcVAE, the number of training parameters is significantly reduced compared to the cVAE, resulting in a shorter training time while maintaining comparable performance. Given desired pattern images, the trained UcVAE can generate multiple process condition solutions that produce high-fidelity hierarchical patterns.

关键词： Frontal polymerization Manufacturing Inverse design variational autoencoder Deep learning Deep generative model

来源：评论

学校读者我要写书评

暂无评论

Dual-granularity multi-instance multi-label learning with variational autoencoder

引用

KNOWLEDGE-BASED SYSTEMS 2025年 316卷

作者： Wang, Meixia Zhao, Yuhai Wang, Yejiang Huang, Miaomiao Liu, Xuze Wang, Xingwei Northeastern Univ Sch Comp Sci & Engn Shenyang 110819 Peoples R China

Multi-instance multi-label learning (MIML) is a weakly supervised approach that models relationships between complex objects and multiple labels, where each object is represented as a bag of instances. A key advantage of MIML is its ability to perform both bag-level and instance-level multi-label predictions, relying solely on bag-level labels. However, a significant performance gap persists between instance-level MIML algorithms and fully supervised learning approaches due to the lack of instance-level labels. Existing MIML algorithms address this challenge by treating bag labels as ambiguous and attempting to reduce supervision imprecision. Moreover, they often assume that instances are independent and identically distributed (i.i.d.) and rely on prior knowledge to learn label correlations, which is impractical in real-world scenarios. To address these challenges, we propose MIMLVAE, a novel dual-granularity MIML algorithm based on a variational autoencoder. MIMLVAE employs a graph attention network to dynamically capture label correlations and instance dependencies, eliminating the i.i.d. assumption and prior knowledge. By treating all instances within a bag equally, it infers effective bag-level and instance-level representations for dual-granularity prediction. At the same time, the label encoder captures label-specific prototype representations, facilitating prototype-based classification at both the bag and instance levels without requiring label disambiguation. Furthermore, MIMLVAE integrates Gaussian mixture model into the shared latent space of features and labels, mitigating posterior collapse and over-regularization. Experiments on six standard MIML datasets demonstrate that MIMLVAE significantly outperforms state-of-the-art methods in both bag-level and instance-level multi-label classification tasks.

关键词： variational autoencoder Correlation learning Prototype classifier

来源：评论

学校读者我要写书评

暂无评论

Detecting and clustering structural damages using modal information and variational autoencoder with triple loss

引用

STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 2025年

作者： Huang, Shieh-Kung Li, You-Jing Lin, Yi-Xun Natl Chung Hsing Univ Dept Civil Engn 145 Xingda Rd Taichung 40227 Taiwan

Among vibration-based structural health monitoring (SHM), methods based on modal analysis are the most popular and efficient ones for assessing the inherent states of structures. The primary techniques involve tracking changes in modal parameters regularly during the monitoring period. Numerous studies have utilized both modal frequencies and mode shapes for damage detection, as mode shapes help identify damage locations, and the combination is more robust against environmental effects. Obviously, recent advances in machine learning (ML) and artificial intelligence (AI) have revolutionized SHM based on modal analysis. This study aims to develop a clustering technique using variational autoencoder (VAE) for classifying structural damages. To fully expand the entangled spaces that may arise from lower-dimensional representation, the loss function incorporates triplet loss (known as triplet VAE or tVAE) while preserving all dimensions in the encoded space. The proposed approach is thoroughly developed and evaluated using both numerical simulations and experimental investigations of multistory building structures. The effectiveness of detecting changes via VAE-based and tVAE-based modal clustering has been demonstrated under the consideration of environmental variations and uncertainties. Additionally, a procedure is suggested for the field applications and the proposed approach's capability for structural inspection during long-term monitoring is showcased using a practical scenario.

关键词： structural health monitoring damage evaluation modal parameter machine learning variational autoencoder triplet loss

来源：评论

学校读者我要写书评

暂无评论

Autonomous in-situ defect detection and correction in additive-lathe 3D printing process using variational autoencoder model

引用

ADDITIVE MANUFACTURING 2025年 98卷

作者： Lee, Seung-Mun Park, Suk-Hee Pusan Natl Univ Sch Mech Engn Busan 46241 South Korea

Additive-lathe three-dimensional (3D) printing systems, employing the material extrusion (MEX) process, deposit material layer by layer on a rotating mandrel-type bed. During this process, high layer heights can lead to defects due to unstable extrusion caused by increased extrusion rates. These defects, if not addressed, progressively worsen, deteriorating both the mechanical properties and surface finish quality of the printed parts. This study introduces a comprehensive system that integrates a machine learning model to autonomously detect and correct these defects in real-time. A variational autoencoder (VAE) model, using an unsupervised learning approach trained on defect-free images, was implemented for defect detection. The anomaly scores generated by the VAE model classify the types of defects, facilitating the application of targeted feedback controls such as filling, ironing, and speed adjustments for subsequent printing. These feedback mechanisms effectively prevent and correct defects during the printing process, enhancing the surface finish and structural quality of the printed parts. Enhancements in mechanical properties were verified through compression tests, demonstrating the capability of the developed system to improve the reliability of the additive-lathe MEX process and mitigate productivity losses associated with printing failures.

关键词： Material extrusion Deep learning variational autoencoder Process monitoring Feedback system

来源：评论

学校读者我要写书评

暂无评论

Inverse design of non-parametric acoustic metamaterials via transfer-learned dual variational autoencoder with latent space-based data augmentation

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 151卷

作者： Ko, Keon Cho, Min Woo Song, Kyungjun Park, Dong Yong Park, Sang Min Pusan Natl Univ Sch Mech Engn 63-2 Busan Univ Ro Busan 46241 South Korea Korea Inst Ind Technol Adv Mobil Components Grp 320 Techno sunhwan Ro Yuga South Korea

A ventilated acoustic resonator (VAR), a class of acoustic metamaterial, offers an effective noise reduction solution in urban environments, where ventilation is essential. The significant non-linearity between the VAR structure and the corresponding acoustic response poses substantial challenges to the inverse design of VAR through analytical approaches. Although deep learning has been employed to address the inverse design of such structures, conventional deep learning-based inverse design methods are constrained to parameter-defined structures, which exhibit limited design flexibility, thereby hindering the achievement of highly accurate inverse design. To address this challenge, we propose a novel inverse design framework for non-parametric VAR, composed of a dual-variational autoencoder (Dual-VAE) and iterative transfer learning method. Dual-VAE consists of structure variational autoencoder and acoustic response variational autoencoder with their latent space aligned to facilitate accurate inverse design of non-parametric VAR structures exhibiting the target acoustic response. The iterative transfer learning method is employed to enhance the inverse design performance of the Dual-VAE by progressively augmenting the initial training dataset, which consists solely of parametric VAR structures, with generated non-parametric VAR structures. The transfer-learned Dual-VAE demonstrated approximately a 32.27 % reduction in mean squared error with the target acoustic response compared to the Dual-VAE trained solely on the initial parametric VAR dataset. We present a novel approach to the inverse design of complex structures with high non-linearity by introducing the inverse design framework, demonstrating exceptional performance in generating non-parametric structures that achieve target performance.

关键词： Inverse design Latent space variational autoencoder Transfer learning Acoustic metamaterials Non-parametric structures

来源：评论

学校读者我要写书评

暂无评论

A generative design method of airfoil based on conditional variational autoencoder

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 139卷

作者： Wang, Xu Qian, Weiqi Zhao, Tun Chen, Hai He, Lei Sun, Haisheng Tian, Yuan China Aerodynam Res & Dev Ctr Computat Aerodynam Inst Mianyang 621000 Peoples R China Chengdu Aeronaut Polytech Chengdu 610100 Peoples R China China Aerodynam Res & Dev Ctr Low Speed Aerodynam Inst Mianyang 621000 Peoples R China

The challenges in multi-objective and multi-dimensional optimization design of airfoils, marked by prolonged optimization cycles and low accuracy, call for an efficient solution to expedite airfoil design. This study presents an innovative airfoil generative design model based on a conditional variational autoencoder (CVAE). Initially, to overcome the limitation of insufficient training data, the model leverages the variational autoencoder (VAE) to learn the spatial distribution of University of Illinois at Urbana-Champaign (UIUC) airfoils, enabling the generation of a diverse set of airfoils with similar distributions. Subsequently, two CVAE-based airfoil generation models, the airfoil freedom design model and the airfoil precision design model, are proposed, which can realize diverse airfoil design under different conditions, such as shape and aerodynamic conditions. Furthermore, two measurements of roughness and diversity are introduced to evaluate the quality of the generated airfoils. The impact of different conditions and network parameters on the model's generation performance is thoroughly analyzed. Results indicate that our proposed model achieves a 65% lower error compared to physics-guided conditional Wasserstein generative adversarial networks (PG-cWGAN) when generating airfoils that satisfy a specific lift coefficient and a 99.99% lower error compared to airfoil pressure distributions generative adversarial networks (Airfoil-Cp-GAN) when generating airfoils that satisfy specific pressure distributions. This method introduces amore creative and accurate approach for aircraft designers in the realm of airfoil design. The code used for this paper is available at https://***/liujun39/airfoilvae.

关键词： Deep learning Generative model variational autoencoder Conditional variational autoencoder Airfoil design

来源：评论

学校读者我要写书评

暂无评论

Electrical resistivity tomography inversion combining deep variational autoencoder and stochastic adaptive sampling

引用

GEOPHYSICS 2025年第2期90卷 E41-E50页

作者： Pereira, Joao Lino Azevedo, Leonardo Univ Lisbon Inst Super Tecn CERENA DER Lisbon Portugal

Geophysical methods, such as electrical resistivity tomography (ERT), can be used to image near-surface electrical resistivity, as field measurements depend on subsurface porosity, water saturation, and fluid salinity. ERT has been widely applied to investigate mineral and groundwater resources and in archaeological, environmental, and engineering studies. The prediction of subsurface electrical conductivity from ERT data requires solving a geophysical inverse problem. For near-surface characterization studies, this is often accomplished with deterministic inverse methods. These methods linearize the problem around an initial solution, and their smoothness depends on an imposed a priori spatial regularization term. Depending on this parameterization, these methodologies might struggle to capture the natural variability of the subsurface. Moreover, deterministic solutions have limited capabilities for uncertainty assessment. In contrast, stochastic inverse methods can assess uncertainties by predicting multiple model realizations that fit the recorded ERT data similarly. However, they are often more computationally expensive than deterministic solutions. Deep-learning algorithms based on deep generative models have been used to reparameterize model and data spaces into low- dimensional domains and efficiently solve geophysical inverse problems. However, within this context, uncertainty assessment is challenging. We develop a deep convolutional variational autoencoder (VAE) coupled with stochastic adaptive optimization to perform stochastic ERT inversion. Geostatistical simulations of electrical resistivity are used as the training data set of the VAE. After training, the VAE generates electrical resistivity models that reproduce the statistics and spatial continuity patterns of the training data set. Then, the VAE latent space is iteratively perturbed and updated with adaptive stochastic sampling based on the misfit between observed and predicted ERT data. Our method

关键词： ERT inversion variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：