检索结果-内蒙古大学图书馆

convolutional autoencoders, clustering, and POD for low-dimensional parametrization of flow equations

COMPUTERS & MATHEMATICS WITH APPLICATIONS 2024年 175卷 49-61页

作者： Heiland, Jan Kim, Yongho Otto Von Guericke Univ Dept Math Univ Pl 2 D-39106 Magdeburg Germany Max Planck Inst Dynam Complex Tech Syst Sandtorstr 1 D-39106 Magdeburg Germany

Simulations of large-scale dynamical systems require expensive computations and large amounts of storage. Low- dimensional representations of high-dimensional states such as in reduced order models deriving from, say, Proper Orthogonal Decomposition (POD) trade in a reduced model complexity against accuracy and can be a solution to lessen the computational burdens. However, for really low-dimensional parametrizations of the states as they may be needed for example for controller design, linear methods like the POD come to their natural limits so that nonlinear approaches will be the methods of choice. In this work, we propose a convolutional autoencoder (CAE) consisting of a nonlinear encoder and an affine linear decoder and consider a deep clustering model where a CAE is integrated with k-means clustering for improved encoding performance. The proposed set of methods is compared to the standard POD approach in three scenarios: single- and double-cylinder wakes modeled by incompressible Navier-Stokes equations and flow setup described by viscous Burgers' equations.

关键词： convolutional autoencoders Clustering Linear parameter varying (LPV) systems Model order reduction

来源：评论

学校读者我要写书评

暂无评论

convolutional autoencoders and Clustering for Low-dimensional Parametrization of Incompressible Flows 25th

Convolutional Autoencoders and Clustering for Low-dimensiona...

引用

25th International Symposium on Mathematical Theory of Networks and Systems (MTNS)

作者： Heiland, Jan Kim, Yongho Max Planck Inst Dynam Complex Tech Syst Magdeburg Germany Otto von Guericke Univ Dept Math Magdeburg Germany

The design of controllers for general nonlinear PDE models is a difficult task because of the high dimensionality of the partially discretized equations. It has been observed that the embedding of nonlinear systems into the class of linear parameter varying systems (LPV) gives way to apply linear theory and methods from numerical linear algebra for controller design. The feasibility of the LPV approach hinges on the dimension of the inherent parametrization. In this work we propose and evaluate combinations of convolutional neural networks and clustering algorithms for very low-dimensional parametrizations of incompressible Navier-Stokes equations. Copyright (C) 2022 The Authors.

关键词： convolutional autoencoders clustering linear parameter-varying (LPV) systems model reduction incompressible flows

来源：评论

学校读者我要写书评

暂无评论

Attention-based convolutional autoencoders for 3D-Variational Data Assimilation

引用

COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING 2020年 372卷 113291-113291页

作者： Mack, Julian Arcucci, Rossella Molina-Solana, Miguel Guo, Yi-Ke Imperial Coll London Data Sci Inst London England Univ Granada Dept Comp Sci & AI Granada Spain

We propose a new 'Bi-Reduced Space' approach to solving 3D Variational Data Assimilation using convolutional autoencoders. We prove that our approach has the same solution as previous methods but has significantly lower computational complexity;in other words, we reduce the computational cost without affecting the data assimilation accuracy. We tested our proposal with data from a real-world application: a pollution model of a site in Elephant and Castle (London, UK) and found that we could (1) reduce the size of the background covariance matrix representation by O(10(3)), and (2) increase our data assimilation accuracy with respect to existing reduced space methods. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Variational Data Assimilation Attention networks convolutional autoencoders

来源：评论

学校读者我要写书评

暂无评论

VECTOR: Very deep convolutional autoencoders for non-resonant background removal in broadband coherent anti-Stokes Raman scattering

引用

JOURNAL OF RAMAN SPECTROSCOPY 2022年第6期53卷 1081-1093页

作者： Wang, Zhengwei O' Dwyer, Kevin Muddiman, Ryan Ward, Tomas Camp, Charles H., Jr. Hennelly, Bryan M. Trinity Coll Dublin Sch Comp Sci & Stat Dublin Ireland Maynooth Univ Dept Elect Engn Maynooth Kildare Ireland Dublin City Univ Insight Ctr Data Analyt Sch Comp Dublin Ireland NIST Biosyst & Biomat Div Gaithersburg MD 20899 USA

Rapid label-free spectroscopy of biological and chemical specimen via molecular vibration through means of broadband coherent anti-Stokes Raman scattering (B-CARS) could serve as a basis for a robust diagnostic platform for a wide range of applications. A limiting factor of CARS is the presence of a non-resonant background (NRB) signal, endemic to the technique. This background is multiplicative with the chemically resonant signal, meaning the perturbation it generates cannot be accounted for simply. Although several numerical approaches exist to account for and remove the NRB, they generally require some estimate of the NRB in the form of a separate measurement. In this paper, we propose a deep neural network architecture called Very dEep convolutional autoencoders (VECTOR), which retrieves the analytical Raman-like spectrum from CARS spectra through training of simulated noisy CARS spectra, without the need for an NRB reference measurement. VECTOR is composed of an encoder and a decoder. The encoder aims to compress the input to a lower dimensional latent representation without losing critical information. The decoder learns to reconstruct the input from the compressed representation. We also introduce skip connection that bypass from the encoder to the decoder, which benefits the reconstruction performance for deeper networks. We conduct abundant experiments to compare our proposed VECTOR to previous approaches in the literature, including the widely applied Kramers-Kronig method, as well as two another recently proposed methods that also use neural networks.

关键词： coherent anti-Stokes Raman scattering (CARS) coherent Raman spectroscopy convolutional autoencoders deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Forecasting of blast furnace gas utilisation rate via convolutional autoencoders and K-nearest neighbour methods

引用

IRONMAKING & STEELMAKING 2024年第10期51卷 1075-1087页

作者： Huang, Qingyun Liu, Zenghao Luo, Mingshuai He, Jiansheng Lv, Xuewei Chongqing Univ Sci & Technol Sch Met & Mat Engn Chongqing Peoples R China Chongqing Univ Sch Mat Sci & Engn Chongqing Peoples R China

Gas utilisation rate (GUR) is an essential parameter to characterise the level of energy utilisation efficiency and operation status of blast furnaces (BFs). In the present study, data collected from a BF plant with vanadium-titanium magnetite were subjected to correlation and distribution analyses. Based on the operation cycle of the BF, production parameters from the preceding eight consecutive hours were selected as input parameters for the model. convolutional autoencoders (CAEs) were employed to extract coded features from the selected data, serving as indirect inputs to the prediction model. Subsequently, K-nearest neighbour (KNN) was utilised to establish a mapping relationship between the coded features and GUR, facilitating forecasting for the subsequent 3 hours. Additionally, a hybrid approach incorporating both supervised and unsupervised training methods was utilised to facilitate GUR prediction, and the performance of the CAE-KNN model was re-validated using data from the remaining sections of the plant. The hit rate of predictions is no less than 96% as the permissible error was within 1.5%.

关键词： blast furnace gas utilisation rate vanadium-titanium magnetite KNN convolutional autoencoders unsupervised learning supervised learning

来源：评论

学校读者我要写书评

暂无评论

DeepFall: Non-Invasive Fall Detection with Deep Spatio-Temporal convolutional autoencoders

引用

JOURNAL OF HEALTHCARE INFORMATICS RESEARCH 2020年第1期4卷 50-70页

作者： Nogas, Jacob Khan, Shehroz S. Mihailidis, Alex Univ Toronto Toronto ON Canada Univ Hlth Network Toronto Rehabil Inst Toronto ON Canada

Human falls rarely occur;however, detecting falls is very important from the health and safety perspective. Due to the rarity of falls, it is difficult to employ supervised classification techniques to detect them. Moreover, in these highly skewed situations, it is also difficult to extract domain-specific features to identify falls. In this paper, we present a novel framework, DeepFall, which formulates the fall detection problem as an anomaly detection problem. The DeepFall framework presents the novel use of deep spatio-temporal convolutional autoencoders to learn spatial and temporal features from normal activities using non-invasive sensing modalities. We also present a new anomaly scoring method that combines the reconstruction score of frames across a temporal window to detect unseen falls. We tested the DeepFall framework on three publicly available datasets collected through non-invasive sensing modalities, thermal camera and depth cameras, and show superior results in comparison with traditional autoencoder methods to identify unseen falls.

关键词： Fall detection convolutional autoencoders Spatio-temporal Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

convolutional autoencoders and Clustering for Low-dimensional Parametrization of Incompressible Flows

引用

IFAC-PapersOnLine 2022年第30期55卷 430-435页

作者： Jan Heil Yongho Kim

关键词： convolutional autoencoders clustering linear parameter-varying (LPV) systems model reduction incompressible flows

来源：评论

学校读者我要写书评

暂无评论

NON-RIGID 2D-3D REGISTRATION USING convolutional autoencoders 17

NON-RIGID 2D-3D REGISTRATION USING CONVOLUTIONAL AUTOENCODER...

引用

IEEE 17th International Symposium on Biomedical Imaging (ISBI)

作者： Li, Peixin Pei, Yuru Guo, Yuke Ma, Gengyu Xu, Tianmin Zha, Hongbin Peking Univ Dept Machine Intelligence Key Lab Machine Percept MOE Beijing Peoples R China Luoyang Inst Sci & Technol Luoyang Peoples R China uSens Inc San Jose CA USA Peking Univ Stomatol Hosp Sch Stomatol Beijing Peoples R China

ISBN: (纸本)9781538693308

In this paper, we propose a novel neural network-based framework for the non-rigid 2D-3D registration of the lateral cephalogram and the volumetric cone-beam CT (CBCT) images. The task is formulated as an embedding problem, where we utilize the statistical volumetric representation and embed the X-ray image to a code vector regarding the non-rigid volumetric deformations. In particular, we build a deep ResNet-based encoder to infer the code vector from the input X-ray image. We design a decoder to generate digitally reconstructed radiographs (DRRs) from the non-rigidly deformed volumetric image determined by the code vector. The parameters of the encoder are optimized by minimizing the difference between synthetic DRRs and input X-ray images in an unsupervised way. Without geometric constraints from multi-view X-ray images, we exploit structural constraints of the multi-scale feature pyramid in similarity analysis. The training process is unsupervised and does not require paired 2D X-ray images and 3D CBCT images. The system allows constructing a volumetric image from a single X-ray image and realizes the 2D-3D registration between the lateral cephalograms and CBCT images.

关键词： Non-rigid 2D-3D registration convolutional autoencoders multi-scale feature pyramid

来源：评论

学校读者我要写书评

暂无评论

Acoustic Anomaly Detection Using convolutional autoencoders in Industrial Processes 14th

Acoustic Anomaly Detection Using Convolutional Autoencoders ...

引用

14th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO)

作者： Duman, Taha Berkay Bayram, Baris Ince, Gokhan Istanbul Tech Univ Fac Comp & Informat Engn Istanbul Turkey

ISBN: (纸本)9783030200558;9783030200541

In the industrial plants, detection of abnormal events during the processes is a difficult task for human operators who need to monitor the production. In this work, the main aim is to detect anomalies in the industrial processes by an intelligent audio based solution for the new generation of factories. Therefore, this paper presents a convolutional Autoencoder (CAE) based end-to-end unsupervised Acoustic Anomaly Detection (AAD) system to be used in the context of industrial plants and processes. In this research, a new industrial acoustic dataset has been created by gathering the audio data obtained from a number of videos of industrial processes, recorded in factories involving industrial tools and processes. Due to the fact that the anomalous events in real life are rather rare and the creation of these events is highly costly, anomaly event sounds are superimposed to regular factory soundscape by using different Signal-to-Noise Ratio (SNR) values. To show the effectiveness of the proposed system, the performances of the feature extraction and the AAD are evaluated. The comparison has been made between CAE, One-Class Support Vector Machine (OCSVM), and a hybrid approach of them (CAE-OCSVM) under various SNRs for different anomaly and process sounds. The results showed that CAE with the end-to-end strategy outperforms OCSVM while the respective results are close to the results of hybrid approach.

关键词： Anomaly detection Industrial processes convolutional autoencoders One-Class Support Vector Machine Signal-to-Noise Ratio Audio feature extraction

来源：评论

学校读者我要写书评

暂无评论

Delamination detection in aerospace composite panels using convolutional autoencoders 15

Delamination detection in aerospace composite panels using c...

引用

Conference on Health Monitoring of Structural and Biological Systems XV

作者： Rautela, Mahindra Monaco, Ernesto Gopalakrishnan, Srinivasan Indian Inst Sci Dept Aerosp Engn Bangalore Karnataka India Univ Naples Federico II Dept Ind Engn Naples Italy

ISBN: (数字)9781510640160

ISBN: (纸本)9781510640160

Modern aerospace structures demand lightweight design procedures and require scheduled maintenance intervals. Supervised deep learning strategies can allow reliable damage detection provided a large amount of data is available to train. These learning algorithms may face problems in the absence of possible damage scenarios in the training dataset. This class imbalance problem in supervised deep learning may curtail the learning process and can possess issues related to generalization on unseen examples. On the other hand, unsupervised deep learning algorithms like autoencoders can handle such situations in the absence of labeled data. In this study, an aerospace composite panel is interrogated with a circular array of piezoelectric transducers using ultrasonic guided waves in a round-robin fashion. The time-series signals are collected for both the healthy and unhealthy state of the structure and transformed into a time-frequency dataset using continuous wavelet transformation. A convolutional autoencoder algorithm trained on healthy signals is used to identify anomalies in the form of delamination in the structure. The proposed methodology can successfully identify delamination in the structure with good accuracy.

关键词： Delamination detection Structural health monitoring Guided waves Unsupervised learning convolutional autoencoders

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：