检索结果-内蒙古大学图书馆

Achieving deep clustering through the use of variational autoencoders and similarity-based loss

MATHEMATICAL BIOSCIENCES AND ENGINEERING 2022年第10期19卷 10344-10360页

作者： Ma, He Harbin Engn Univ Coll Intelligent Syst Sci & Engn Harbin 150000 Peoples R China

Clustering is an important and challenging research topic in many fields. Although various clustering algorithms have been developed in the past, traditional shallow clustering algorithms cannot mine the underlying structural information of the data. Recent advances have shown that deep clustering can achieve excellent performance on clustering tasks. In this work, a novel variational autoencoder-based deep clustering algorithm is proposed. It treats the Gaussian mixture model as the prior latent space and uses an additional classifier to distinguish different clusters in the latent space accurately. A similarity-based loss function is proposed consisting specifically of the cross-entropy of the predicted transition probabilities of clusters and the Wasserstein distance of the predicted posterior distributions. The new loss encourages the model to learn meaningful cluster-oriented representations to facilitate clustering tasks. The experimental results show that our method consistently achieves competitive results on various data sets.

关键词： clustering deep learning data representation variational autoencoder network architecture

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised soft sensor method for fermentation processes based on physical monotonicity and variational autoencoders

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartA期137卷

作者： Cheng, Xinyue Yu, Zhenhua Wang, Guan Jiang, Qingchao Cao, Zhixing East China Univ Sci & Technol Key Lab Smart Mfg Energy Chem Proc Minist Educ Shanghai 200237 Peoples R China East China Univ Sci & Technol State Key Lab Bioreactor Engn Shanghai 200237 Peoples R China

Data-driven models have shown broad application prospects in soft sensor modeling. However, numerous challenges persist. On the one hand, data-driven soft sensor methods have high requirements on data quality. On the other hand, models relying on limited experimental data often lack physical interpretability. To tackle these challenges, a semi-supervised soft sensor method (PMVAER) for fermentation processes based on physical monotonicity and variational autoencoders (VAEs) is introduced. First, physical monotonicity constraint is incorporated into the loss function of VAEs for regression to ensure that the model's predictions adhere to physical feasibility. Next, considering the disparate sampling frequencies for process and quality variables, this approach is extended to learn from unlabeled data, creating a semi-supervised soft sensor model. The proposed model is validated on simulation and real cases of penicillin fermentation. Comparisons with five other methods verify that the proposed method exhibits exceptional predictive accuracy along with enhanced generalization ability.

关键词： Soft sensor variational autoencoder Fermentation process Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Toward a better monitoring statistic for profile monitoring via variational autoencoders

引用

JOURNAL OF QUALITY TECHNOLOGY 2021年第5期53卷 454-473页

作者： Sergin, Nurettin Dorukhan Yan, Hao Arizona State Univ Ind Engineer Program Tempe AZ USA Arizona State Univ Tempe AZ 85287 USA

variational autoencoders have been recently proposed for the problem of process monitoring. While these works show impressive results over classical methods, the proposed monitoring statistics often ignore the inconsistencies in learned lower-dimensional representations and computational limitations in high-dimensional approximations. In this work, we first manifest these issues and then overcome them with a novel statistic formulation that increases out-of-control detection accuracy without compromising computational efficiency. We demonstrate our results on a simulation study with explicit control over latent variations, and a real-life example of image profiles obtained from a hot steel rolling process.

关键词： Deep learning high-dimensional nonlinear profile latent variable model profile monitoring variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multilevel Anomaly Detection Through variational autoencoders and Bayesian Models for Self-Aware Embodied Agents

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2022年 24卷 1399-1414页

作者： Slavic, Giulia Baydoun, Mohamad Campo, Damian Marcenaro, Lucio Regazzoni, Carlo Univ Genoa DITEN Fac Engn I-16145 Genoa Italy Univ Genoa DITEN I-16145 Genoa Italy

Anomaly detection constitutes a fundamental step in developing self-aware autonomous agents capable of continuously learning from new situations, as it enables to distinguish novel experiences from already encountered ones. This paper combines Dynamic Bayesian Networks (DBNs) and Neural Networks (NNs) and proposes a method for detecting anomalies in video data at different abstraction levels. We use a variational autoencoder (VAE) to reduce the dimensionality of video frames, and Optical Flows between subsequent images, generating a latent space that captures both visual and dynamical information and that is comparable to low-dimensional sensory data (e.g., positioning, steering angle). An Adapted Markov Jump Particle Filter is employed to predict the following frames and detect anomalies in video data. Our method's evaluation is executed using different video data from a semi-autonomous vehicle performing different tasks in a closed environment. Tests on benchmark anomaly detection datasets have additionally been conducted.

关键词： Feature extraction Anomaly detection Predictive models Image reconstruction Self-aware Probabilistic logic Data models Anomaly detection kalman filtering particle filtering variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Conservative Policy Construction Using variational autoencoders for Logged Data With Missing Values

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2023年第9期34卷 6368-6378页

作者： Abroshan, Mahed Yip, Kai Hou Tekin, Cem van der Schaar, Mihaela Alan Turing Inst London NW1 2DB England UCL London WC1E 6BT England Bilkent Univ Dept Elect & Elect Engn TR-06800 Ankara Turkey Univ Cambridge Dept Appl Math & Theoret Phys Cambridge CB2 1TN England Univ Calif Los Angeles Los Angeles CA 90095 USA

In high-stakes applications of data-driven decision-making such as healthcare, it is of paramount importance to learn a policy that maximizes the reward while avoiding potentially dangerous actions when there is uncertainty. There are two main challenges usually associated with this problem. First, learning through online exploration is not possible due to the critical nature of such applications. Therefore, we need to resort to observational datasets with no counterfactuals. Second, such datasets are usually imperfect, additionally cursed with missing values in the attributes of features. In this article, we consider the problem of constructing personalized policies using logged data when there are missing values in the attributes of features in both training and test data. The goal is to recommend an action (treatment) when (X) over tilde, a degraded version of X with missing values, is observed. We consider three strategies for dealing with missingness. In particular, we introduce the conservative strategy where the policy is designed to safely handle the uncertainty due to missingness. In order to implement this strategy, we need to estimate posterior distribution p(X vertical bar(X) over tilde) and use a variational autoencoder to achieve this. In particular, our method is based on partial variational autoencoders (PVAEs) that are designed to capture the underlying structure of features with missing values.

关键词： Missing values observational data policy construction variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Mitigating the Impact of Temperature Variations on Ultrasonic Guided Wave-Based Structural Health Monitoring through variational autoencoders

引用

SENSORS 2024年第5期24卷 1494页

作者： Junges, Rafael Lomazzi, Luca Miele, Lorenzo Giglio, Marco Cadini, Francesco Politecn Milan Dept Mech Engn Via Masa n1 I-20156 Milan Italy

Structural health monitoring (SHM) has become paramount for developing cheaper and more reliable maintenance policies. The advantages coming from adopting such process have turned out to be particularly evident when dealing with plated structures. In this context, state-of-the-art methods are based on exciting and acquiring ultrasonic-guided waves through a permanently installed sensor network. A baseline is registered when the structure is healthy, and newly acquired signals are compared to it to detect, localize, and quantify damage. To this purpose, the performance of traditional methods has been overcome by data-driven approaches, which allow processing a larger amount of data without losing diagnostic information. However, to date, no diagnostic method can deal with varying environmental and operational conditions (EOCs). This work aims to present a proof-of-concept that state-of-the-art machine learning methods can be used for reducing the impact of EOCs on the performance of damage diagnosis methods. Generative artificial intelligence was leveraged to mitigate the impact of temperature variations on ultrasonic guided wave-based SHM. Specifically, variational autoencoders and singular value decomposition were combined to learn the influence of temperature on guided waves. After training, the generative part of the algorithm was used to reconstruct signals at new unseen temperatures. Moreover, a refined version of the algorithm called forced variational autoencoder was introduced to further improve the reconstruction capabilities. The accuracy of the proposed framework was demonstrated against real measurements on a composite plate.

关键词： generative artificial intelligence variational autoencoder temperature ultrasonic guided wave

来源：评论

学校读者我要写书评

暂无评论

Using Shapley Values and variational autoencoders to Explain Predictive Models with Dependent Mixed Features

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2022年第1期23卷 1-51页

作者： Olsen, Lars Henry Berge Glad, Ingrid Kristine Jullum, Martin Aas, Kjersti Univ Oslo Dept Math Moltke Moes vei 35Niels Henrik Abels hus N-0851 Oslo Norway Norwegian Comp Ctr Gaustadalleen 23aKristen Nygaards hus N-0373 Oslo Norway

Shapley values are today extensively used as a model-agnostic explanation framework to explain complex predictive machine learning models. Shapley values have desirable theoret-ical properties and a sound mathematical foundation in the field of cooperative game theory. Precise Shapley value estimates for dependent data rely on accurate modeling of the depen-dencies between all feature combinations. In this paper, we use a variational autoencoder with arbitrary conditioning (VAEAC) to model all feature dependencies simultaneously. We demonstrate through comprehensive simulation studies that our VAEAC approach to Shapley value estimation outperforms the state-of-the-art methods for a wide range of settings for both continuous and mixed dependent features. For high-dimensional settings, our VAEAC approach with a non-uniform masking scheme significantly outperforms competing meth-ods. Finally, we apply our VAEAC approach to estimate Shapley value explanations for the Abalone data set from the UCI Machine Learning Repository.

关键词： Explainable artificial intelligence prediction explanation Shapley values variational autoencoder feature dependence

来源：评论

学校读者我要写书评

暂无评论

Recurrent variational autoencoders for Learning Nonlinear Generative Models in the Presence of Outliers

引用

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING 2018年第6期12卷 1615-1627页

作者： Wang, Yu Dai, Bin Hua, Gang Aston, John Wipf, David Univ Cambridge Dept Pure Math & Stat Cambridge CB2 1TN England Tsinghua Univ Beijing 100084 Peoples R China Microsoft Res Redmond WA 98052 USA

This paper explores two useful modifications of the recent variational autoencoder (VAE), a popular deep generative modeling framework that dresses traditional autoencoders with probabilistic attire. The first involves a specially-tailored form of conditioning that allows us to simplify the VAE decoder structure while simultaneously introducing robustness to outliers. In a related vein, a second, complementary alteration is proposed to further build invariance to contaminated or dirty samples via a data augmentation process that amounts to recycling. In brief, to the extent that the VAE is legitimately a representative generative model, then each output from the decoder should closely resemble an authentic sample, which can then be resubmitted as a novel input ad infinitum. Moreover, this can be accomplished via special recurrent connections without the need for additional parameters to be trained. We evaluate these proposals on multiple practical outlier-removal and generative modeling tasks involving nonlinear low-dimensional manifolds, demonstrating considerable improvements over existing algorithms.

关键词： Deep generative models variational autoencoder robust PCA outlier removal variational Bayesian model deep learning

来源：评论

学校读者我要写书评

暂无评论

A process monitoring and fault isolation framework based on variational autoencoders and branch and bound method

引用

JOURNAL OF THE FRANKLIN INSTITUTE 2022年第2期359卷 1667-1691页

作者： Tang, Peng Peng, Kaixiang Jiao, Ruihua Univ Sci & Technol Beijing Sch Automat & Elect Engn Key Lab Knowledge Automat Ind Proc Minist Educ Beijing 100083 Peoples R China Peng Cheng Lab Dept Math & Theories 2 Xingke 1st St Nanshan Shenzhen Peoples R China AVIC Xian Aviat Brake Technol Co Ltd Xian 710065 Peoples R China

Nonlinear characteristic widely exists in industrial processes. Many approaches based on kernel methods and machine learning have been developed for nonlinear process monitoring. However, the fault isolation for nonlinear processes has rarely been studied in previous works. In this paper, a process monitoring and fault isolation framework is proposed for nonlinear processes using variational autoen-coder (VAE) model. First, based on the probability graph model of VAE, a uniform monitoring index can be calculated by the probability density of observation variables. Then, the fault variables are estimated with normal variables by a missing value estimation method. The optimal fault variable set can be searched by branch and bound (BAB) algorithm. The proposed method can resolve the "smearing effects" problem existing in traditional fault isolation methods. Finally, a numerical case and a hot strip mill process case are used to verified the proposed method. (C) 2021 The Franklin Institute. Published by Elsevier Ltd. All rights reserved.

关键词： Process monitoring Fault isolation variational autoencoder Missing value estimation Branch and bound

来源：评论

学校读者我要写书评

暂无评论

Leveraging variational autoencoders for Parameterized MMSE Estimation

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2024年 72卷 3731-3744页

作者： Baur, Michael Fesl, Benedikt Utschick, Wolfgang Tech Univ Munich TUM Sch Computat Informat & Technol D-80333 Munich Germany

In this manuscript, we propose to use a variational autoencoder-based framework for parameterizing a conditional linear minimum mean squared error estimator. The variational autoencoder models the underlying unknown data distribution as conditionally Gaussian, yielding the conditional first and second moments of the estimand, given a noisy observation. The derived estimator is shown to approximate the minimum mean squared error estimator by utilizing the variational autoencoder as a generative prior for the estimation problem. We propose three estimator variants that differ in their access to ground-truth data during the training and estimation phases. The proposed estimator variant trained solely on noisy observations is particularly noteworthy as it does not require access to ground-truth data during training or estimation. We conduct a rigorous analysis by bounding the difference between the proposed and the minimum mean squared error estimator, connecting the training objective and the resulting estimation performance. Furthermore, the resulting bound reveals that the proposed estimator entails a bias-variance tradeoff, which is well-known in the estimation literature. As an example application, we portray channel estimation, allowing for a structured covariance matrix parameterization and low-complexity implementation. Nevertheless, the proposed framework is not limited to channel estimation but can be applied to a broad class of estimation problems. Extensive numerical simulations first validate the theoretical analysis of the proposed variational autoencoder-based estimators and then demonstrate excellent estimation performance compared to related classical and machine learning-based state-of-the-art estimators.

关键词： Estimation Training Inverse problems Data models Bayes methods Noise measurement Vectors Parameter estimation variational autoencoder conditional mean estimator generative model inverse problem

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：