检索结果-内蒙古大学图书馆

A novel wasserstein autoencoder-enhanced thermo-mechanical coupled reduced-order model for high pressure turbine blades life monitoring

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2025年 152卷

作者： Wang, Rongqiao Chen, Ruoqi Zhao, Yan Shen, Tianbao Chen, Gaoxiang Hu, Dianyin Jiang, Zhimin Wang, Xuemin Beihang Univ Sch Energy & Power Engn Beijing 100191 Peoples R China Beijing Key Lab Aeroengine Struct & Strength Beijing 100191 Peoples R China Collaborat Innovat Ctr Adv Aeroengine Beijing 100191 Peoples R China Beihang Univ Res Inst Aeroengine Beijing 100191 Peoples R China China AECC Sichuan Gas Turbine Estab Chengdu 610000 Peoples R China

To facilitate effective assessment of loads (e.g., temperature and stress) and life management of high-pressure turbine (HPT) blades, a wasserstein autoencoder (WAE)-enhanced thermodynamically coupled reduced-order model (ROM) is proposed in this paper. The advanced ROM for the nonlinear thermomechanical coupling fields is developed by introducing the deep learning model of WAE in the proper orthogonal decomposition (POD) method. The proposed method improves the prediction accuracy of loads in locally focused regions and generalization performance. The accuracy and efficiency of this method are validated through 30 sets of validation conditions. Results indicate that the proposed approach achieves higher accuracy and better generalization performance than traditional POD-based methods, with errors maintained within 10. Additionally, computational speed is improved by nearly 1400 times compared to conventional numerical methods. The WAE-enhanced ROM is applied for load and life assessment of the HPT blades throughout their service life. The evaluation time for a single aeroengine performance parameter is 1.7 s, and for a single flight evaluation, it is 67 s, which highlights the effectiveness of the proposed method in enabling the assessment of the loads and remaining life of HPT blades.

关键词： High-pressure turbine blade Reduced order model wasserstein autoencoder Loading calculation Lifetime monitoring

来源：评论

学校读者我要写书评

暂无评论

wasserstein autoencoder Based End-to-End Learning Strategy of Geometric Shaping for an OAM Mode Division Multiplexing IM/DD Transmission

Wasserstein Autoencoder Based End-to-End Learning Strategy o...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Cheng, Zhaohui Gao, Ran Xu, Qi Wang, Fei Cui, Yi Xin, Xiangjun School of Information and Electronics Beijing Institute of Technology Beijing China Beijing University of Posts and Telecommunications Beijing Key Laboratory of Space-Ground Interconnection and Convergence Beijing China

We propose a wasserstein autoencoder based end-to-end geometric shaping scheme for IM/DD OAM-MDM optical fiber communication system. Compared with traditional autoencoder, the BER decreased by up to 28% and 33% with t... 详细信息

ISBN: (纸本)9798350312614

关键词： geometric shaping machine learning orbital angular momentum wasserstein autoencoder

来源：评论

学校读者我要写书评

暂无评论

Accelerating the discovery of anticancer peptides targeting lung and breast cancers with the wasserstein autoencoder model and PSO algorithm

引用

BRIEFINGS IN BIOINFORMATICS 2022年第5期23卷 bbac320-bbac320页

作者： Yang, Lijuan Yang, Guanghui Bing, Zhitong Tian, Yuan Huang, Liang Niu, Yuzhen Yang, Lei Chinese Acad Sci Inst Modern Phys Lanzhou Peoples R China Lanzhou Univ Sch Phys & Technol Lanzhou 730000 Gansu Peoples R China Shandong Univ Technol Sch Life Sci Shandong Prov Res Ctr Bioinformat Engn & Tech Zibo Shandong Peoples R China

In the development of targeted drugs, anticancer peptides (ACPs) have attracted great attention because of their high selectivity, low toxicity and minimal non-specificity. In this work, we report a framework of ACPs generation, which combines wasserstein autoencoder (WAE) generative model and Particle Swarm Optimization (PSO) forward search algorithm guided by attribute predictive model to generate ACPs with desired properties. It is well known that generative models based on Variational autoencoder (VAE) and Generative Adversarial Networks (GAN) are difficult to be used for de novo design due to the problems of posterior collapse and difficult convergence of training. Our WAE-based generative model trains more successfully (lower perplexity and reconstruction loss) than both VAE and GAN-based generative models, and the semantic connections in the latent space of WAE accelerate the process of forward controlled generation of PSO, while VAE fails to capture this feature. Finally, we validated our pipeline on breast cancer targets (HIF-1) and lung cancer targets (VEGR, ErbB2), respectively. By peptide-protein docking, we found candidate compounds with the same binding sites as the peptides carried in the crystal structure but with higher binding affinity and novel structures, which may be potent antagonists that interfere with these target-mediated signaling.

关键词： anticancer peptides wasserstein autoencoder Particle Swarm Optimization peptide-protein docking drug design

来源：评论

学校读者我要写书评

暂无评论

Pixel-Wise wasserstein autoencoder for Highly Generative Dehazing

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2021年 30卷 5452-5462页

作者： Kim, Guisik Park, Sung Woo Kwon, Junseok Chung Ang Univ Sch Comp Sci & Engn Seoul 06974 South Korea

We propose a highly generative dehazing method based on pixel-wise wasserstein autoencoders. In contrast to existing dehazing methods based on generative adversarial networks, our method can produce a variety of dehazed images with different styles. It significantly improves the dehazing accuracy via pixel-wise matching from hazy to dehazed images through 2-dimensional latent tensors of the wasserstein autoencoder. In addition, we present an advanced feature fusion technique to deliver rich information to the latent space. For style transfer, we introduce a mapping function that transforms existing latent spaces to new ones. Thus, our method can produce highly generative haze-free images with various tones, illuminations, and moods, which induces several interesting applications, including low-light enhancement, daytime dehazing, nighttime dehazing, and underwater image enhancement. Experimental results demonstrate that our method quantitatively outperforms existing state-of-the-art methods for synthetic and real-world datasets, and simultaneously generates highly generative haze-free images, which are qualitatively diverse.

关键词： Tensors Image enhancement Lighting Network architecture Estimation Channel estimation Transforms Dehazing wasserstein autoencoder image enhancement

来源：评论

学校读者我要写书评

暂无评论

Learning Disentangled Representations with the wasserstein autoencoder 1

引用

21st Joint European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD)

作者： Gaujac, Benoit Feige, Ilya Barber, David UCL London England

ISBN: (数字)9783030865238

ISBN: (纸本)9783030865238;9783030865221

Disentangled representation learning has undoubtedly benefited from objective function surgery. However, a delicate balancing act of tuning is still required in order to trade off reconstruction fidelity versus disentanglement. Building on previous successes of penalizing the total correlation in the latent variables, we propose TCWAE (Total Correlation wasserstein autoencoder). Working in the WAE paradigm naturally enables the separation of the total-correlation term, thus providing disentanglement control over the learned representation, while offering more flexibility in the choice of reconstruction cost. We propose two variants using different KL estimators and analyse in turn the impact of having different ground cost functions and latent regularization terms. Extensive quantitative comparisons on data sets with known generative factors shows that our methods present competitive results relative to state-of-the-art techniques. We further study the trade off between disentanglement and reconstruction on more-difficult data sets with unknown generative factors, where the flexibility of the WAE paradigm leads to improved reconstructions.

关键词： wasserstein autoencoder Variational autoencoder Generative modelling Representation learning Disentanglement learning

来源：评论

学校读者我要写书评

暂无评论

引用

IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Yao, Linying Zhong, Jingbin Zhang, Xiaofeng Luo, Linhao Harbin Inst Technol Sch Comp Sci Shenzhen Peoples R China Tencent Inc Shenzhen Peoples R China

ISBN: (纸本)9781665419246

Recommender systems for implicit data, e.g., browsing data, have attracted more and more research efforts. Most existing approaches assume the implicit data is i.i.d. which ignores the fact that the real-world data is generally correlated with each other. To cope with this issue, this paper proposes the correlated wasserstein autoencoders (CWAEs) model to capture data correlation to enhance recommendation peformance. Particularly in the proposed approach, we first formulate correlated data via an undirected acyclic graph and then generalize the undirected acyclic graph to an acyclic graph by averaging all its' maximum acyclic subgraphs. To further enhance model performance, we introduce negative sampling strategy. Experiments are evaluated on Epinions dataset. The widely adopted evaluation criteria, i.e., CRR and NCRR, are adopted to evaluate both baseline models and our proposed approach. Experimental results have demonstrated the superiority of the proposed models.

关键词： wasserstein autoencoder Implicit data recommender system

来源：评论

学校读者我要写书评

暂无评论

Deterministic autoencoder using wasserstein loss for tabular data generation

引用

NEURAL NETWORKS 2025年 185卷 107208页

作者： Wang, Alex X. Nguyen, Binh P. Victoria Univ Wellington Sch Math & Stat Wellington 6012 New Zealand Ho Chi Minh City Open Univ Fac Informat Technol 97 Vo Van TanDist 3 Ho Chi Minh City 70000 Vietnam

Tabular data generation is a complex task due to its distinctive characteristics and inherent complexities. While Variational autoencoders have been adapted from the computer vision domain for tabular data synthesis, their reliance on non-deterministic latent space regularization introduces limitations. The stochastic nature of Variational autoencoders can contribute to collapsed posteriors, yielding suboptimal outcomes and limiting control over the latent space. This characteristic also constrains the exploration of latent space interpolation. To address these challenges, we present the Tabular wasserstein autoencoder (TWAE), leveraging the deterministic encoding mechanism of wasserstein autoencoders. This characteristic facilitates a deterministic mapping of inputs to latent codes, enhancing the stability and expressiveness of our model's latent space. This, in turn, enables seamless integration with shallow interpolation mechanisms like the synthetic minority over-sampling technique (SMOTE) within the data generation process via deep learning. Specifically, TWAE is trained once to establish a low-dimensional representation of real data, and various latent interpolation methods efficiently generate synthetic latent points, achieving a balance between accuracy and efficiency. Extensive experiments consistently demonstrate TWAE's superiority, showcasing its versatility across diverse feature types and dataset sizes. This innovative approach, combining WAE principles with shallow interpolation, effectively leverages SMOTE's advantages, establishing TWAE as a robust solution for complex tabular data synthesis.

关键词： Deep neural networks Tabular data synthesis Latent space interpolation Generative AI wasserstein autoencoder

来源：评论

学校读者我要写书评

暂无评论

wasserstein autoencoders for collaborative filtering

引用

NEURAL COMPUTING & APPLICATIONS 2021年第7期33卷 2793-2802页

作者： Zhang, Xiaofeng Zhong, Jingbin Liu, Kai Harbin Inst Technol Shenzhen Sch Comp Sci Shenzhen Peoples R China Ping An Life Shenzhen Peoples R China

The recommender systems have long been studied in the literature. The collaborative filtering is one of the most widely adopted recommendation techniques which is usually applied to the explicit data, e.g., rating scores. However, the implicit data, e.g., click data, is believed to be able to discover user's latent preferences. Consequently, a number of research attempts have been made toward this issue. To the best of our knowledge, this paper is the first attempt to adapt the wasserstein autoencoders to collaborative filtering problem. Particularly, we propose a new loss function by introducing an L-1 regularization term to learn a sparse low-rank representation form to represent latent variables. Then, we carefully design (1) a new cost function to minimize the data reconstruction error, and (2) the appropriate distance metrics for the calculation of KL divergence between the learned distribution of latent variables and the underlying true data distribution. Rigorous experiments are performed on three widely adopted datasets. Both the state-of-the-art approaches, e.g., Mult-VAE and Mult-DAE, and the baseline models are evaluated on these datasets. The promising experimental results demonstrate that the proposed approach is superior to the compared approaches with respect to evaluation criteria Recall@R and NDCG@R.

关键词： wasserstein autoencoder Collaborative filtering Implicit data

来源：评论

学校读者我要写书评

暂无评论

wasserstein autoencoders with Mixture of Gaussian Priors for Stylized Text Generation 24th

Wasserstein Autoencoders with Mixture of Gaussian Priors for...

引用

24th Annual International Conference on Text, Speech, and Dialogue (TSD)

作者： Ghabussi, Amirpasha Mou, Lili Vechtomova, Olga Univ Waterloo Waterloo ON N2L 3G1 Canada Univ Alberta Alberta Machine Intelligence Inst Amii Edmonton AB T6G 2R3 Canada

ISBN: (纸本)9783030835262;9783030835279

Probabilistic autoencoders are effective for text generation. However, they are unable to control the style of generated text, despite the training samples explicitly labeled with different styles. We present a wasserstein autoencoder with a Gaussian mixture prior for style-aware sentence generation. Our model is trained on a multi-class dataset and generates sentences in the style of the desired class. It is also capable of interpolating multiple classes. Moreover, we can train our model on relatively small datasets. While a regular WAE or VAE cannot generate diverse sentences with few training samples, our approach generates diverse sentences and preserves the style of the desired classes.

关键词： wasserstein autoencoder Stylized text generation Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Cycling topic graph learning for neural topic modeling

引用

KNOWLEDGE-BASED SYSTEMS 2025年 310卷

作者： Liu, Yanyan Gong, Zhiguo Univ Macau State Key Lab Internet Things Smart City Macau 999078 Peoples R China Univ Macau Guangdong Macau Joint Lab Adv & Intelligent Comp Macau 999078 Peoples R China Univ Macau Dept Comp & Informat Sci Macau 999078 Peoples R China

Topic models aim to discover a set of latent topics in a textual corpus. Graph Neural Networks (GNNs) have been recently utilized in Neural Topic Models (NTMs) due to their strong capacity to model document representations with the text graph. Most of the previous works construct the text graph by considering documents and words as nodes and document embeddings are learned through the topology structure of the text graph. However, while conducting graph learning on topic modeling, sorely considering document- word propagation will lose the guidance of topic relevance and the graph propagation cannot reflect the true relationship at the topic level which will result in inaccurate topic extraction. To address the above-mentioned issue, we propose a novel neural topic model based on Cycling Topic Graph Learning (CyTGL). Specifically, we design a novel three-party topic graph for document-topic-word to incorporate topic propagation into graph-based topic models. In the three-party topic graph, the topic layer is latent and we recursively extract the topic layer through the learning process. Leveraging this topic graph, we employ topic attention message passing to propagate topical information to enhance the document representations. What is more, the topic layer in the three-party graph can be regarded as the prior knowledge that offers guidance for the process of topic extraction. Crucially, the hierarchical relationships in the three-party graph are maintained during the learning process. We conduct experiments on several widely used datasets and the results show our proposed approach outperforms state-of-the-art topic models.

关键词： Neural topic model Graph neural networks wasserstein autoencoder Graph attention networks

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

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

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：