检索结果-内蒙古大学图书馆

GANInSAR: deep generative modeling for Large-Scale InSAR Signal Simulation

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2024年 17卷 5303-5316页

作者： Zhou, Zhongrun Sun, Xinyao Yang, Fei Wang, Zheng Goldsbury, Ryan Cheng, Irene Univ Alberta Comp Sci Edmonton AB T6G 2R3 Canada 3V Geomat Inc RnD Vancouver BC V5Y 0M6 Canada

Interferometric synthetic aperture radar (InSAR) technology is widely used to create digital elevation models and measure dynamics on the Earth's surface, including monitoring ground displacements. The lack of or limited-collected ground-truth data, however, often poses a bottleneck in validating the research outcome, particularly at high precision and resolution levels. To mitigate the gap, we introduce a new deep generative model (DGM) for the simulation of linear deformation rate maps. We demonstrate that our adversarial DGM architecture with carefully designed preprocessing and postprocessing modules performs well for InSAR deformation signal synthesis, even when limited data are available. We also introduce a dimensionality reduction method, based on the distance between the real-world and generated image feature vectors, to address the lack of quantitative evaluation for data simulation. Furthermore, we introduce a hybrid evaluation metric integrating quantitative and qualitative measures, which is more intuitive than the existing methods and makes it easier for domain experts to participate in the evaluation. We compare the results of our model with established methods. The comparison result illustrates the superior performance of our proposed method.

关键词： Deformation generative adversarial networks Atmospheric modeling Deformable models Training Data models Generators deep generative modeling generative adversarial network (GAN) interferometric synthetic aperture radar (InSAR) radar signal processing remote sensing images simulation

来源：评论

学校读者我要写书评

暂无评论

deep generative modeling-based data augmentation with demonstration using the BFBT benchmark void fraction datasets

引用

NUCLEAR ENGINEERING AND DESIGN 2023年 415卷

作者： Alsafadi, Farah Wu, Xu North Carolina State Univ Dept Nucl Engn Burlington Engn Labs 2500 Stinson Dr Raleigh NC 27695 USA

deep learning (DL) has achieved remarkable successes in many disciplines such as computer vision and natural language processing due to the availability of "big data". However, such success cannot be easily replicated in many nuclear engineering problems because of the limited amount of training data, especially when the data comes from high-cost experiments. To overcome such a data scarcity issue, this paper explores the applications of deep generative models (DGMs) that have been widely used for image data generation to scientific data augmentation. DGMs, such as generative adversarial networks (GANs), normalizing flows (NFs), variational autoencoders (VAEs), and conditional VAEs (CVAEs), can be trained to learn the underlying probabilistic distribution of the training dataset. Once trained, they can be used to generate synthetic data that are similar to the training data and significantly expand the dataset size. By employing DGMs to augment TRACE simulated data of the steady-state void fractions based on the NUPEC Boiling Water Reactor Full-size Fine-mesh Bundle Test (BFBT) benchmark, this study demonstrates that VAEs, CVAEs, and GANs have comparable generative performance with similar errors in the synthetic data, with CVAEs achieving the smallest errors. The findings shows that DGMs have a great potential to augment scientific data in nuclear engineering, which proves effective for expanding the training dataset and enabling other DL models to be trained more accurately.

关键词： deep generative modeling generative adversarial networks Normalizing flows Variational autoencoders

来源：评论

学校读者我要写书评

暂无评论

IceBerg: deep generative modeling for Constraint Discovery and Anomaly Detection 20

IceBerg: Deep Generative Modeling for Constraint Discovery a...

引用

20th IEEE Int Symposium on Parallel and Distributed Processing with Applicat / 15th IEEE Int Conf on Social Comp and Networking / 12th IEEE Int Conf on Big Data and Cloud Comp / 12th IEEE Int Conf on Sustainable Comp and Commun

作者： Hu, Wentao Jiang, Dawei Wu, Sai Chen, Ke Chen, Gang Zhejiang Univ Key Lab Big Data Intelligent Comp Zhejiang Prov Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781665464970

Automatic constraint discovery from a relational database is beneficial for domain experts in fraud detection and intelligent auditing. Its objective is to discover a set of inherent constraints underlying the database such that tuples violating them are considered anomalous. In this paper, we propose IceBerg as the first system to simultaneously detect anomalous tuples and discover the associated human-readable constraints. The backbone of IceBerg is a novel generative network, namely KD-VAE, that integrates Kernel Density estimation with Variational AutoEncoder. KD-VAE is expected to learn the distributions of normal tuples. We can perform anomalous data detection by calculating the likelihood that the tuple fits the distributions of normal tuples and abnormality interpretation by comparing the detected anomalous tuples with their generated normal *** empirically compare the proposed method with several state-of-the-art outlier detection methods on 13 real-world datasets. The results show that IceBerg outperforms its competitors in most cases, especially for complex datasets with high-dimensional features.

关键词： deep generative modeling Constraint Discovery Intelligent Auditing Anomaly Detection Databases

来源：评论

学校读者我要写书评

暂无评论

Performance-Based generative Design for Parametric modeling of Engineering Structures Using deep Conditional generative Models

引用

AUTOMATION IN CONSTRUCTION 2023年 156卷

作者： Bucher, Martin Juan Jose Kraus, Michael Anton Rust, Romana Tang, Siyu Swiss Fed Inst Technol Stefano Franscini Pl CH-8093 Zurich Switzerland

Parametric modeling, generative Design, and Performance-Based Design have gained increasing attention in the AEC field as a way to create a wide range of design variants while focusing on performance attributes rather than building codes. However, the relationships between design parameters and performance attributes are often very complex, resulting in a highly iterative and unguided process. In this paper, we argue that a more goal-oriented design process is enabled by an inverse formulation that starts with performance attributes instead of design parameters. A deep Conditional generative Design workflow is proposed that takes a set of performance attributes and partially defined design features as input and produces a complete set of design parameters as output. A model architecture based on a Conditional Variational Autoencoder is presented along with different approximate posteriors, and evaluated on four different case studies. Compared to Genetic Algorithms, our method proves superior when utilizing a pre-trained model.

关键词： deep generative modeling Performance-based design generative design Variational autoencoder deep generative design Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

ZEB2 is a master switch controlling the tumor-associated macrophage program

引用

Cancer Cell 2025年

作者： Sheban, Fadi Phan, Truong San Xie, Ken Ingelfinger, Florian Gur, Chamutal Shapir Itai, Yuval Blecher-Gonen, Ronnie Yu, Chunsong Avellino, Roberto Chalan, Paulina Freitag, Kiara Yofe, Ido Yutkin, Vladimir Boyeau, Pierre Ergen, Can Hong, Justin Mazuz, Kfir Liu, Yuxiao Chen, Kangming Dahan, Rony Kortylewski, Marcin Yosef, Nir Weiner, Assaf Amit, Ido Department of Systems Immunology Weizmann Institute of Science Rehovot 7610001 Israel Department of Medicine Hadassah Medical Center Faculty of Medicine Hebrew University of Jerusalem Jerusalem Israel The Crown Genomics Institute of the Nancy and Stephen Grand Israel National Center for Personalized Medicine Weizmann Institute of Science Rehovot 7610001 Israel Department of Immuno-Oncology Beckman Research Institute City of Hope Los Angeles CA United States Department of Urology Hadassah Medical Center Faculty of Medicine Hebrew University of Jerusalem Jerusalem Israel Department of Electrical Engineering and Computer Sciences University of California Berkeley Berkeley CA United States Center for Computational Biology University of California Berkeley Berkeley CA United States Department of Computer Science Columbia University New York NY United States Nanjing GenScript Biotech Co. Ltd Jiangning Science Park Jiangsu Nanjing 211100 China

Tumor-associated macrophages (TAMs) are key mediators of tumor immune evasion. However, their regulatory circuits and checkpoints are partially understood. Here, we generated a TAM regulatory network by integrating human tumors single-cell RNA sequencing (scRNA-seq) data with a dedicated CRISPR screen. Using a deep generative model, we constructed a gene perturbation network linking individual candidates with prototypical TAM functions. We identified Zeb2 as the master regulator of TAM programs, orchestrating suppression of type-I interferon response and antigen presentation alongside activation of immune suppression programs. Genetic ablation of ZEB2 reprograms TAM function and identity on the chromatin, RNA, and protein levels. In macrophage-rich human tumors, ZEB2 expression is associated with poor prognosis. Selective Zeb2 in vivo targeting reprograms TAMs and mobilizes systemic T cell responses, achieving robust tumor clearance. Overall, our study generates a detailed roadmap of TAM gene circuits and identifies ZEB2 as a master switch with therapeutic potential. © 2025 Elsevier Inc.

关键词： cancer immunology cancer immunotherapy CRISPR deep generative modeling regulatory network single cell genomics systems immunolgy TAM reprogramming tumor-associated macrophage Zeb2

来源：评论

学校读者我要写书评

暂无评论

deep generative Methods for Producing Forecast Trajectories in Power Systems 20

Deep Generative Methods for Producing Forecast Trajectories ...

引用

20th International Conference on the European Energy Market (EEM)

作者： Weill, Nathan Dumas, Jonathan RTE R&D Immeuble Window 7CPl Dome F-92073 La Def France

ISBN: (纸本)9798350381757;9798350381740

With the expansion of renewables in the electricity mix, power grid variability will increase;hence, the system needs to be robust to guarantee its security. To anticipate the design of new tools and processes, Transmission System Operators (TSOs) must conduct analyses to simulate the future operation of power systems. Then, these simulations are used as inputs in decision-making processes. In this context, we investigate using deep learning models to generate energy production and load forecast trajectories. We adapt autoregressive networks and normalizing flows to capture the spatiotemporal correlations in these multivariate time series, demonstrating their effectiveness against the current copula-based statistical approach. We conduct extensive experiments on the French TSO RTE wind forecast data and compare the different models with ad hoc evaluation metrics for time series generation.

关键词： Autoregressive models deep generative modeling Energy forecasting Multivariate time series

来源：评论

学校读者我要写书评

暂无评论

AUGMENTING MOLECULAR deep generative MODELS WITH TOPOLOGICAL DATA ANALYSIS REPRESENTATIONS 47

AUGMENTING MOLECULAR DEEP GENERATIVE MODELS WITH TOPOLOGICAL...

引用

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Schiff, Yair Chenthamarakshan, Vijil Hoffman, Samuel C. Ramamurthy, Karthikeyan Natesan Das, Payel IBM Res TJ Watson Res Ctr Yorktown Hts NY 10598 USA

ISBN: (纸本)9781665405409

deep generative models have emerged as a powerful tool for learning useful molecular representations and designing novel molecules with desired properties, with applications in drug discovery and material design. However, most existing deep generative models are restricted due to lack of spatial information. Here we propose augmentation of deep generative models with topological data analysis (TDA) representations, known as persistence images, for robust encoding of 3D molecular geometry. We show that the TDA augmentation of a character-based Variational Auto-Encoder (VAE) outperforms state-of-the-art generative neural nets in accurately modeling the structural composition of the QM9 benchmark. Generated molecules are valid, novel, and diverse, while exhibiting distinct electronic property distribution, namely higher sample population with small HOMO-LUMO gap. These results demonstrate that TDA features indeed provide crucial geometric signal for learning abstract structures, which is non-trivial for existing generative models operating on string, graph, or 3D point sets to capture.

关键词： deep generative modeling variational auto-encoder molecular design topological data analysis

来源：评论

学校读者我要写书评

暂无评论

deep learning and knowledge-based methods for computer-aided molecular design-toward a unified approach: State-of-the-art and future directions

引用

COMPUTERS & CHEMICAL ENGINEERING 2020年 141卷 107005-107005页

作者： Alshehri, Abdulelah S. Gani, Rafiqul You, Fengqi Cornell Univ Robert Frederick Smith Sch Chem & Biomol Engn Ithaca NY 14853 USA King Saud Univ Coll Engn Dept Chem Engn POB 800 Riyadh 11421 Saudi Arabia PSE Speed Co Skyttemosen 6 DK-3450 Allerod Denmark

The optimal design of compounds through manipulating properties at the molecular level is often the key to considerable scientific advances and improved process systems performance. This paper highlights key trends, challenges, and opportunities underpinning the Computer-Aided Molecular Design (CAMD) problems. A brief review of knowledge-driven property estimation methods and solution techniques, as well as corresponding CAMD tools and applications, are first presented. In view of the computational challenges plaguing knowledge-based methods and techniques, we survey the current state-of-the-art applications of deep learning to molecular design as a fertile approach towards overcoming computational limitations and navigating uncharted territories of the chemical space. The main focus of the survey is given to deep generative modeling of molecules under various deep learning architectures and different molecular representations. Further, the importance of benchmarking and empirical rigor in building deep learning models is spotlighted. The review article also presents a detailed discussion of the current perspectives and challenges of knowledge-based and data-driven CAMD and identifies key areas for future research directions. Special emphasis is on the fertile avenue of hybrid modeling paradigm, in which deep learning approaches are exploited while leveraging the accumulated wealth of knowledge-driven CAMD methods and tools. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Computer-aided molecular design Product design Process design deep generative modeling deep learning

来源：评论

学校读者我要写书评

暂无评论

Diffusion Models in Vision: A Survey

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第9期45卷 10850-10869页

作者： Croitoru, Florinel-Alin Hondru, Vlad Ionescu, Radu Tudor Shah, Mubarak Univ Bucharest Dept Comp Sci Bucharest 030018 Romania Univ Cent Florida Ctr Res Comp Vis CRCV Dept Comp Sci Orlando FL 32816 USA

Denoising diffusion models represent a recent emerging topic in computer vision, demonstrating remarkable results in the area of generative modeling. A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage. In the forward diffusion stage, the input data is gradually perturbed over several steps by adding Gaussian noise. In the reverse stage, a model is tasked at recovering the original input data by learning to gradually reverse the diffusion process, step by step. Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens, i.e., low speeds due to the high number of steps involved during sampling. In this survey, we provide a comprehensive review of articles on denoising diffusion models applied in vision, comprising both theoretical and practical contributions in the field. First, we identify and present three generic diffusion modeling frameworks, which are based on denoising diffusion probabilistic models, noise conditioned score networks, and stochastic differential equations. We further discuss the relations between diffusion models and other deep generative models, including variational auto-encoders, generative adversarial networks, energy-based models, autoregressive models and normalizing flows. Then, we introduce a multi-perspective categorization of diffusion models applied in computer vision. Finally, we illustrate the current limitations of diffusion models and envision some interesting directions for future research.

关键词： Computational modeling Mathematical models Noise reduction Data models Computer vision Training Task analysis Denoising diffusion models deep generative modeling Index Terms diffusion models image generation noise conditioned score networks score-based models

来源：评论

学校读者我要写书评

暂无评论

ProtWave-VAE: Integrating Autoregressive Sampling with Latent-Based Inference for Data-Driven Protein Design

引用

ACS SYNTHETIC BIOLOGY 2023年第12期12卷 3544-3561页

作者： Praljak, Niksa Lian, Xinran Ranganathan, Rama Ferguson, Andrew L. Univ Chicago Grad Program Biophys Sci Chicago IL 60637 USA Univ Chicago Dept Chem Chicago IL 60637 USA Univ Chicago Ctr Phys Evolving Syst Chicago IL 60637 USA Univ Chicago Dept Biochem & Mol Biol Chicago IL 60637 USA Univ Chicago Pritzker Sch Mol Engn Chicago IL 60637 USA

deep generative models (DGMs) have shown great success in the understanding and data-driven design of proteins. Variational autoencoders (VAEs) are a popular DGM approach that can learn the correlated patterns of amino acid mutations within a multiple sequence alignment (MSA) of protein sequences and distill this information into a low-dimensional latent space to expose phylogenetic and functional relationships and guide generative protein design. Autoregressive (AR) models are another popular DGM approach that typically lacks a low-dimensional latent embedding but does not require training sequences to be aligned into an MSA and enable the design of variable length proteins. In this work, we propose ProtWave-VAE as a novel and lightweight DGM, employing an information maximizing VAE with a dilated convolution encoder and an autoregressive WaveNet decoder. This architecture blends the strengths of the VAE and AR paradigms in enabling training over unaligned sequence data and the conditional generative design of variable length sequences from an interpretable, low-dimensional learned latent space. We evaluated the model's ability to infer patterns and design rules within alignment-free homologous protein family sequences and to design novel synthetic proteins in four diverse protein families. We show that our model can infer meaningful functional and phylogenetic embeddings within latent spaces and make highly accurate predictions within semisupervised downstream fitness prediction tasks. In an application to the C-terminal SH3 domain in the Sho1 transmembrane osmosensing receptor in baker's yeast, we subject ProtWave-VAE-designed sequences to experimental gene synthesis and select-seq assays for the osmosensing function to show that the model enables synthetic protein design, conditional C-terminus diversification, and engineering of the osmosensing function into SH3 paralogues.

关键词： deep generative modeling protein design syntheticbiology

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：