检索结果-内蒙古大学图书馆

Nonlinear quality-related fault detection using combined deep variational information bottleneck and variational autoencoder

引用

ISA TRANSACTIONS 2021年 114卷 444-454页

作者： Tang, Peng Peng, Kaixiang Dong, Jie Univ Sci & Technol Beijing Sch Automat & Elect Engn Key Lab Knowledge Automat Ind Proc Minist Educ Beijing 100083 Peoples R China

Deep learning has gotten much attention in industrial field, many fault detection methods based on deep learning have been developed for nonlinear industrial processes. However, most of them do not take the quality-related faults into account. In order to extract the latent variables which can represent the separated quality-related and unrelated information, this paper proposes a novel deep VIB-VAE algorithm, which combines variational autoencoder (VAE) model and deep variational information bottleneck (VIB). Deep VIB extracts quality-related latent variables by maximizing mutual information between latent variables and process quality while minimizing mutual information between latent variables and observation. VAE is used to learn the quality-unrelated part with above quality-related latent variables as auxiliary information. To monitor and distinguish quality-related and quality-unrelated faults, two monitoring statistics are designed by the two-part latent variables. The reconstruction error by VAE is introduced to improve the performance of fault detection. Finally, the effectiveness of the proposed deep VIB-VAE algorithm is demonstrated by a numerical case and a real hot strip mill process case, respectively. (C) 2021 ISA. Published by Elsevier Ltd. All rights reserved.

关键词： Fault detection Quality-related Deep variational information bottleneck variational autoencoder Hot strip mill process

来源：评论

学校读者我要写书评

暂无评论

Advances Toward the Next Generation Fire Detection: Deep LSTM variational autoencoder for Improved Sensitivity and Reliability

引用

IEEE ACCESS 2021年 9卷 30636-30653页

作者： Xu, Zhaoyi Guo, Yanjie Saleh, Joseph Homer Georgia Inst Technol Sch Aerosp Engn Atlanta GA 30332 USA

Fire detection is a critical component of a building safety monitoring system and remains an important research area with weighty practical relevance. Significant advances have occurred in recent years in building automation, and the operation of buildings has become more complex and requires ever more effective monitoring systems. In this work, we develop a novel fire detection method using deep Long-Short Term Memory (LSTM) neural networks and variational autoencoder (VAE) to meet these increasingly stringent requirements and outperform existing fire detection methods. To evaluate the effectiveness of our method, we develop high-fidelity simulations, and we use datasets from real-world fire and non-fire experiments provided by NIST. We compare and discuss the performance of our proposed fire detection with alternative methods, including the standard LSTM, cumulative sum control chart (CUSUM), exponentially weighted moving average (EWMA), and two currently used fixed-temperature heat detectors. The results using the simulation-based and the real-world experiments are complementary, and they indicate that the LSTM-VAE robustly outperforms the other detection methods with, for example, statistically significant shorter alarm time lags, no missed detection, and no false alarms. The results also identify shortcomings of other detection methods and indicate a clear ranking among them (LSTM-VAE > EWMA > LSTM > CUSUM).

关键词： Fire detection machine learning anomaly detection long short-term memory variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Multimodal variational autoencoder for inverse problems in geophysics: application to a 1-D magnetotelluric problem

引用

GEOPHYSICAL JOURNAL INTERNATIONAL 2023年第3期235卷 2598-2613页

作者： Rodriguez, Oscar Taylor, Jamie M. Pardo, David Basque Ctr Appl Math BCAM Alameda Mazarredo 14 E-48009 Bilbao Spain Univ Basque Country UPV EHU Dept Math E-48940 Leioa Spain CUNEF Univ Dept Quantitat Methods C Pirineos 55 Madrid 28040 Spain Ikerbasque Basque Fdn Sci Plaza Euskadi 5 E-48009 Bilbao Spain

Estimating subsurface properties from geophysical measurements is a common inverse problem. Several Bayesian methods currently aim to find the solution to a geophysical inverse problem and quantify its uncertainty. However, most geophysical applications exhibit more than one plausible solution. Here, we propose a multimodal variational autoencoder model that employs a mixture of truncated Gaussian densities to provide multiple solutions, along with their probability of occurrence and a quantification of their uncertainty. This autoencoder is assembled with an encoder and a decoder, where the first one provides a mixture of truncated Gaussian densities from a neural network, and the second is the numerical solution of the forward problem given by the geophysical approach. The proposed method is illustrated with a 1-D magnetotelluric inverse problem and recovers multiple plausible solutions with different uncertainty quantification maps and probabilities that are in agreement with known physical observations.

关键词： Magnetotellurics Inverse theory Numerical modelling Probabilistic forecasting Statistical methods variational autoencoder Multimodal Models

来源：评论

学校读者我要写书评

暂无评论

Bearing fault diagnosis based on variational autoencoder and non-local block wide kernel convolutional neural network

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE 2024年第14期238卷 7322-7340页

作者： Jiang, Li Guo, Silong Guo, Shunsheng Zhuang, Kejia Li, Yibing Wuhan Univ Technol Sch Mech & Elect Engn Wuhan Peoples R China Wuhan Univ Technol Hubei Digital Mfg Key Lab Wuhan Peoples R China Wuhan Univ Technol Sch Mech & Elect Engn Hubei Digital Mfg Key Lab Wuhan 430070 Peoples R China

At present, convolutional neural network (CNN) is widely applied to bearing fault diagnosis However, the diagnosis performance will descend under the strong noise condition in the real industrial environment. Therefore, a denoising method named non-local block wide kernel CNN (NLBWCNN) is proposed based on wide convolution kernel and non-local block. Additionally, the data in the mechanical fault state is less than that in the health state in actual industrial production, which leads to the data imbalance problem. However, the fault classifier based on CNN needs a large amount of balanced data to train. Otherwise, it will not be fully trained, and thus its generalization ability will be affected. As a result, a method called VAE-NLBWCNN (variational autoencoder and NLBWCNN) is proposed for diagnosing bearing faults. The method employs variational autoencoder balanced the fault data. And then, the NLBWCNN is utilized to denoise and classify the fault data. The proposed VAE-NLBWCNN method is validated on three bearing datasets. The comparative experiments demonstrate that the proposed method can effectively expand unbalanced data and achieve the best performance in various noise conditions.

关键词： Bearing fault diagnosis data imbalance noise reduction convolutional neural network variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Rule-Based Outlier Detection with a Modified variational autoencoder for Enhancing Data Accuracy in Wireless Sensor Networks

引用

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS 2023年第6期25卷 2187-2202页

作者： Jothi, S. Arul Venkatesan, R. Santhi, V. PSG Coll Technol Dept Comp Sci & Engn Coimbatore 641004 India

In wireless sensor networks (WSNs), a number of outlier detection (OD) methods have been established over time to identify data that do not match the rest of the data. These data are anomalies, outliers, or irregularities because they result from hostile attacks or sensor node malfunctions. OD is difficult due to the classification process and the challenges in feature development. The limitations of conventional OD include insufficient feature learning, noise, excessive dimensionality, and a lack of training data. Unsupervised outlier detection (UOD) in WSNs is a new research area that has been ascertained to perform exceptionally well in terms of detection accuracy. The fact that prior knowledge of abnormal data is unknown, i.e., the ground truth of data is unknown for the classification of outlier instances, is a substantial barrier in UOD. This made it possible for researchers to examine flexible deep learning methods for domain-specific UOD, like variational autoencoder (VAE). In order to achieve an appropriate categorization of anomalous data, this research suggests using a Modified variational autoencoder (ModVAE) model with a rule-based approach. In the first stage of the proposed system, an adaptive VAE model is developed to produce modified latent space vector samples suitable for reproducing the data with reasonable reconstruction loss, and in the second stage, fuzzy rules are generated to precisely classify abnormal data with fewer false positives. The suggested model's efficiency is demonstrated with experiments done using benchmark datasets. The experimental results show improved performance when compared with other approaches available in the literature.

关键词： Abnormal data Fuzzy inference system Unsupervised outlier detection variational autoencoder Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Nc-vae: normalised conditional diverse variational autoencoder guided de novo molecule generation

引用

JOURNAL OF SUPERCOMPUTING 2024年第14期80卷 21207-21228页

作者： Bhadwal, Arun Singh Kumar, Kamal Natl Inst Technol Comp Sci & Engn Srinagar 246174 Uttarakhand India Univ Petr & Energy Studies UPES Comp Sci & Engn Dehra Dun 248007 Uttarakhand India IGDTUW Informat Technol Delhi 110006 India

This work proposes a novel approach for drug molecule design using data-assisted techniques. This approach leverages a generation-based framework to expedite the drug discovery process, aiming to identify candidate molecules suitable for production while minimizing development timelines and regulatory hurdles. The core of the proposed method is a conditional variational autoencoder (CVAE) for molecule generation, employing NCSMILES string representation. The framework involves three key stages: (1) molecule generation using the CVAE, (2) filtering based on a scoring function, and (3) identification of the optimal molecule from the generated pool. To enhance the latent space representation, we incorporate molecule properties alongside conditional selection criteria. The performance of the proposed scheme is comprehensively evaluated on standard benchmark datasets using various metrics, including validity, diversity, usefulness, and novelty. The method demonstrates superior performance compared to existing state-of-the-art approaches, attributable to several key improvements, including intermediary optimizations and condition-based selection.

关键词： variational autoencoder De novo molecule generation SMILES Machine learning Diversity

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Deep Learning based variational autoencoder Model for COVID-19 Diagnosis and Classification

引用

PATTERN RECOGNITION LETTERS 2021年 151卷 267-274页

作者： Mansour, Romany F. Escorcia-Gutierrez, Jose Gamarra, Margarita Gupta, Deepak Castillo, Oscar Kumar, Sachin New Valley Univ Dept Math Fac Sci El Kharga 72511 Egypt Univ Autonoma Caribe Elect & Telecommun Program Barranquilla Colombia Univ Costa Dept Computat Sci & Elect CUC Barranquilla Colombia Maharaja Agrasen Inst Technol Dept Comp Sci & Engn Delhi India Tijuana Inst Technol Tijuana Mexico South Ural State Univ Dept Comp Sci Chelyabinsk Russia

At present times, COVID-19 has become a global illness and infected people has increased exponentially and it is difficult to control due to the non-availability of large quantity of testing kits. Artificial intelligence (AI) techniques including machine learning (ML), deep learning (DL), and computer vision (CV) approaches find useful for the recognition, analysis, and prediction of COVID-19. Several ML and DL techniques are trained to resolve the supervised learning issue. At the same time, the potential measure of the unsupervised learning technique is quite high. Therefore, unsupervised learning techniques can be designed in the existing DL models for proficient COVID-19 prediction. In this view, this paper introduces a novel unsupervised DL based variational autoencoder (UDL-VAE) model for COVID-19 detection and classification. The UDL-VAE model involved adaptive Wiener filtering (AWF) based preprocessing technique to enhance the image quality. Besides, Inception v4 with Adagrad technique is employed as a feature extractor and unsupervised VAE model is applied for the classification process. In order to verify the superior diagnostic performance of the UDL-VAE model, a set of experimentation was carried out to highlight the effective outcome of the UDL-VAE model. The obtained experimental values showcased the effectual results of the UDL-VAE model with the higher accuracy of 0.987 and 0.992 on the binary and multiple classes respectively. (c) 2021 Elsevier B.V. All rights reserved.

关键词： COVID-19 Deep learning Unsupervised learning variational autoencoder Image classification

来源：评论

学校读者我要写书评

暂无评论

FVAE: a regularized variational autoencoder using the Fisher criterion

引用

APPLIED INTELLIGENCE 2022年第14期52卷 16869-16885页

作者： Lai, Jie Wang, Xiaodan Xiang, Qian Li, Rui Song, Yafei Air Force Engn Univ Coll Air & Missile Def Xian 710051 Peoples R China 61932 Troop PLA Beijing 100071 Peoples R China

As a deep generative model, the variational autoencoder (VAE) is widely applied to solve problems of insufficient samples and imbalanced labels. In the VAE, the distribution of latent variables affects the quality of the generated samples. To obtain discriminative latent variables and generated samples, a Fisher variational autoencoder (FVAE) based on the Fisher criterion is proposed in this study. The FVAE introduces the Fisher criterion into the VAE by adding the Fisher regularization term to the loss function, aiming to maximize the between-class distance and minimize the within-class distance of latent variables. Different from the unsupervised learning of the VAE, the FVAE requires class labels to calculate the Fisher regularization loss so that the learned latent variables and generated samples have sufficient category information to complete classification tasks. Experiments on benchmark datasets show that the learned latent variables of the FVAE are more discriminative and that the generated samples are more efficient in improving the performance of various classifiers than the VAE, beta-variational autoencoder (beta-VAE), conditional variational autoencoder (CVAE), Denoising variational autoencoder (DVAE) and information maximizing variational autoencoder (IM-VAE).

关键词： variational autoencoder Deep generative model Fisher criterion Regularization Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Disentangled variational autoencoder for Social Recommendation

引用

NEURAL PROCESSING LETTERS 2024年第3期56卷 159-159页

作者： Zhang, Yongshuai Huang, Jiajin Yang, Jian Beijing Univ Technol Fac Informat Technol Beijing Peoples R China Beijing Int Collaborat Base Brain Informat & Wisdo Beijing Peoples R China

Social recommendation aims to improve the recommendation performance by learning user interest and social representations from users' interaction records and social relations. Intuitively, these learned representations entangle user interest factors with social factors because users' interaction behaviors and social relations affect each other. A high-quality recommender system should provide items to a user according to his/her interest factors. However, most existing social recommendation models aggregate the two kinds of representations indiscriminately, and this kind of aggregation limits their recommendation performance. In this paper, we develop a model called Disentangled variational autoencoder for Social Recommendation (DVSR) to disentangle interest and social factors from the two kinds of user representations. Firstly, we perform a preliminary analysis of the entangled information on three popular social recommendation datasets. Then, we present the model architecture of DVSR, which is based on the variational autoencoder (VAE) framework. Besides the traditional method of training VAE, we also use contrastive estimation to penalize the mutual information between interest and social factors. Extensive experiments are conducted on three benchmark datasets to evaluate the effectiveness of our model.

关键词： Social recommendation Disentangled representation learning variational autoencoder Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Parallel Interaction Spatiotemporal Constrained variational autoencoder for Soft Sensor Modeling

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2022年第8期18卷 5190-5198页

作者： Zhu, Xiuli Damarla, Seshu Kumar Hao, Kuangrong Huang, Biao Coll Informat Sci & Technol Shanghai 201620 Peoples R China Donghua Univ Engn Res Ctr Digitized Text & Apparel Technol Shanghai 201620 Peoples R China Univ Alberta Dept Chem & Mat Engn Edmonton AB T6G 2V4 Canada

Data-driven soft sensors have been widely used in industrial processes for over two decades. Industrial processes often exhibit nonlinear and time-varying behavior due to complex physical and chemical mechanisms, feedback control, and dynamic noise. Lately, variational autoencoder (VAE) has arisen as one of the most prevalent methods for unsupervised learning of intricate distributions. Despite being successful in deep feature extraction and uncertain data modeling, it still suffers from instability and reconstruction error due to random sampling in the latent subspace representation of original input space. In this article, to deal with those limitations, constrained VAE (CVAE) is proposed by utilizing input sample information. Enthused by parallel interaction mechanism between the ventral and dorsal stream of the human brain in object recognition, parallel interaction spatial-temporal CVAE (PIST-CVAE) is proposed to extract spatial and temporal features from input samples. Lower dimensional nonlinear features extracted from PIST-CVAE are used to build the soft sensor. The effectiveness of CVAE and PIST-CVAE is demonstrated in an industrial case study, a polyester polymerization process. The obtained results demonstrate that CVAE is able to reconstruct inputs with higher accuracy and the proposed PIST-CVAE-based soft sensor yields more accurate estimations for the melt viscosity index of the polymerization process.

关键词： Feature extraction Convolution Logic gates Informatics Polymers Mathematical model Kernel Convolutional neural network (CNN) constrained variational autoencoder (VAE) long short-term memory (LSTM) parallel interaction mechanism polyester polymerization process 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：