检索结果-内蒙古大学图书馆

Cloud-VAE: variational autoencoder with concepts emb e dde d

PATTERN RECOGNITION 2023年 140卷

作者： Liu, Yue Liu, Zitu Li, Shuang Yu, Zhenyao Guo, Yike Liu, Qun Wang, Guoyin Shanghai Univ Sch Comp Engn & Sci Shanghai 200444 Peoples R China Shanghai Engn Res Ctr Intelligent Comp Syst Shanghai 200444 Peoples R China Imperial Coll Dept Comp London SW7 2AZ England Chongqing Univ Posts & Telecommun Chongqing Key Lab Computat Intelligence Chongqing 400065 Peoples R China

variational autoencoder (VAE) has been widely and successfully used in learning coherent latent repre-sentation of data. However, the lack of interpretability in the latent space constructed by the VAE under the prior distribution is still an urgent problem. This paper proposes a VAE with understandable concept embedding named Cloud-VAE, which constructs interpretable latent space by disentangling the latent variables and considering their uncertainty based on cloud model. Firstly, cloud model-based clustering algorithm cast initial constraint of latent space into a prior distribution of concept which can be em-bedded into the latent space of the VAE to disentangle the latent variables. Secondly, reparameterization trick based on forward cloud transformation algorithm is designed to estimate the latent space concept by increasing the randomness of latent variables. Furthermore, variational lower bound of Cloud-VAE is derived to guide the training process to construct concepts of latent space, realizing the mutual mapping between latent space and concept space. Finally, experimental results on 6 benchmark datasets show that Cloud-VAE has good clustering and reconstruction performance, which can explicitly explain the aggre-gation process of the model and discover more interpretable disentangled representations.& COPY;2023 Elsevier Ltd. All rights reserved.

关键词： variational autoencoder Disentangled representation Concept embedded Cloud Model Deep Learning Interpretability

来源：评论

学校读者我要写书评

暂无评论

Latent Space Expanded variational autoencoder for Sentence Generation

引用

IEEE ACCESS 2019年 7卷 144618-144627页

作者： Song, Tianbao Sun, Jingbo Chen, Bo Peng, Weiming Song, Jihua Beijing Normal Univ Coll Informat Sci & Technol Beijing 100875 Peoples R China

Sentence generation is a key task in many natural language processing systems. Models based on a variational autoencoder (VAE) can generate plausible sentences from a continuous latent space. However, the VAE forces the latent distribution of each input sentence to match the same prior, which results in a large overlap among the latent subspaces of different sentences and a limited informative latent space. Therefore, the sentences generated by sampling from a subspace may have little correlation with the corresponding input, and the latent space cannot capture rich useful information from the input sentences, which leads to the failure of the model to generate diverse sentences from the latent space. Additionally, the Kullback-Leibler (KL) divergence collapse problem makes the VAE notoriously difficult to train. In this paper, a latent space expanded VAE (LSE-VAE) model is presented for sentence generation. The model maps each sentence to a continuous latent subspace under the constraint of its own prior distribution, and constrains nearby sentences to map to nearby subspaces. Sentences are dispersed to a large continuous latent space according to sentence similarity, where the latent subspaces of different sentences may be relatively far away from each other and arranged in an orderly manner. The experimental results show that the LSE-VAE improves the reconstruction ability of the VAE, generates plausible and more diverse sentences, and learns a larger informative latent space than the VAE with the properties of continuity and smoothness. The LSE-VAE does not suffer from the KL collapse problem, and it is robust to hyperparameters and much easier to train.

关键词： Latent space natural language processing sentence generation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Loop closure detection of visual SLAM based on variational autoencoder

引用

FRONTIERS IN NEUROROBOTICS 2024年 17卷 1301785页

作者： Song, Shibin Yu, Fengjie Jiang, Xiaojie Zhu, Jie Cheng, Weihao Fang, Xiao Shandong Univ Sci & Technol Dept Coll Elect Engn & Automat Qingdao Peoples R China Yantai Tulan Elect Technol Co Ltd Yantai Peoples R China

Loop closure detection is an important module for simultaneous localization and mapping (SLAM). Correct detection of loops can reduce the cumulative drift in positioning. Because traditional detection methods rely on handicraft features, false positive detections can occur when the environment changes, resulting in incorrect estimates and an inability to obtain accurate maps. In this research paper, a loop closure detection method based on a variational autoencoder (VAE) is proposed. It is intended to be used as a feature extractor to extract image features through neural networks to replace the handicraft features used in traditional methods. This method extracts a low-dimensional vector as the representation of the image. At the same time, the attention mechanism is added to the network and constraints are added to improve the loss function for better image representation. In the back-end feature matching process, geometric checking is used to filter out the wrong matching for the false positive problem. Finally, through numerical experiments, the proposed method is demonstrated to have a better precision-recall curve than the traditional method of the bag-of-words model and other deep learning methods and is highly robust to environmental changes. In addition, experiments on datasets from three different scenarios also demonstrate that the method can be applied in real-world scenarios and that it has a good performance.

关键词： visual SLAM loop closure detection variational autoencoder attention mechanism loss function

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection for multivariate times series through the multi-scale convolutional recurrent variational autoencoder

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期231卷

作者： Xie, Tianming Xu, Qifa Jiang, Cuixia Hefei Univ Technol Sch Management Hefei 230009 Anhui Peoples R China Minist Educ Key Lab Proc Optimizat & Intelligent Decis making Hefei Peoples R China

To realize the anomaly detection for industrial multi-sensor data, we develop a novel multi-scale convolutional recurrent variational autoencoder (MSCRVAE) model. It is a hybrid of convolutional autoencoder and convolutional long short-term memory with variational autoencoder (ConvLSTM-VAE). The ConvLSTM-VAE part helps the MSCRVAE model not only capture the spatial and temporal dependence of data but also learn robust high-level representations by estimating the distributions of latent variables. Moreover, a typical loss function that combines the characteristics of both autoencoder and variational autoencoder is designed for the MSCRVAE model. The experimental results on three public data illustrate the superiority of the MSCRVAE model in anomaly detection with the best average F1-score up to 0.90. The interquartile range of the boxplots on the public data also proves the robustness of the MSCRVAE model. We also illustrate the role of the two components in the loss function by exploring their changes during training. What is more, on the private data, the MSCRVAE model also performs well and the residual matrices provide reasonable interpretations to the anomaly detection results.

关键词： Anomaly detection Multi-sensor data Multivariate time series Inner correlation variational autoencoder Multi-scale convolutional recurrent variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Exploration of optimal microstructure and mechanical properties in continuous microstructure space using a variational autoencoder

引用

MATERIALS & DESIGN 2021年 202卷

作者： Kim, Yongju Park, Hyung Keun Jung, Jaimyun Asghari-Rad, Peyman Lee, Seungchul Kim, Jin You Jung, Hwan Gyo Kim, Hyoung Seop Pohang Univ Sci & Technol POSTECH Dept Mat Sci & Engn Pohang 37673 South Korea Korea Inst Mat Sci Dept Virtual Mat Proc Chang Won 51508 South Korea Pohang Univ Sci & Technol POSTECH Ctr High Entropy Alloys Pohang 37673 South Korea Pohang Univ Sci & Technol POSTECH Dept Mech Engn Pohang 37673 South Korea POSCO Tech Res Lab Energy & Shipbldg Steel Res Grp Pohang 790785 South Korea Pohang Univ Sci & Technol POSTECH Grad Inst Ferrous Technol Pohang 37673 South Korea

Data-driven approaches enable a deep understanding of microstructure and mechanical properties of materials and greatly promote one's capability in designing new advanced materials. Deep learning-based image process-ing outperforms conventional image processing techniques with unsupervised learning. This study employs a variational autoencoder (VAE) to generate a continuous microstructure space based on synthetic microstructural images. The structure-property relationships are explored using a computational approach with microstructure quantification, dimensionality reduction, and finite element method (FEM) simulations. The FEM of representa-tive volume element (RVE) with a microstructure-based constitutive model model is proposed for predicting the overall stress-strain behavior of the investigated dual-phase steels. Then, Gaussian process regression (GPR) is used to make connections between the latent space point and the ferrite grain size as inputs and mechanical properties as outputs. The GPR with VAE successfully predicts the newly generated microstructures with target mechanical properties with high accuracy. This work demonstrates that a variety of microstructures can be can-didates for designing the optimal material with target properties in a continuous manner. (c) 2021 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).

关键词： Microstructure-based modeling Deep learning variational autoencoder Gaussian process regression Dual-phase steel

来源：评论

学校读者我要写书评

暂无评论

Efficient integration of perceptual variational autoencoder into dynamic latent scale generative adversarial network

引用

EXPERT SYSTEMS 2024年第10期41卷

作者： Cho, Jeongik Krzyzak, Adam Concordia Univ Dept Comp Sci & Software Engn Montreal PQ Canada

Dynamic latent scale GAN is an architecture-agnostic encoder-based generative model inversion method. This paper introduces a method to efficiently integrate perceptual VAE into dynamic latent scale GAN to improve the performance of dynamic latent scale GAN. When dynamic latent scale GAN is trained with a normal i.i.d. latent random variable and the latent encoder is integrated into the discriminator, a sum of a predicted latent random variable of real data and a scaled normal noise follows the normal i.i.d. random variable. Since this random variable is paired with real data and follows the latent random variable, it can be used for both VAE and GAN training. Furthermore, by considering the intermediate layer output of the discriminator as the feature encoder output, the VAE can be trained to minimise the perceptual reconstruction loss. The forward propagation & backpropagation for minimising this perceptual reconstruction loss can be integrated with those of GAN training. Therefore, the proposed method does not require additional computations compared to typical GAN or dynamic latent scale GAN. Integrating perceptual VAE to dynamic latent scale GAN improved the generative and inversion performance of the model.

关键词： deep generative model deep learning feature learning generative adversarial networks generative model inversion representation learning unsupervised learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Unsupervised heat balance indicator construction based on variational autoencoder and its application to aluminum electrolysis process monitoring

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartA期127卷

作者： Wang, Jie Xie, Shiwen Xie, Yongfang Chen, Xiaofang Cent South Univ Sch Automat Changsha 410083 Hunan Peoples R China

Heat balance plays a significant role in reflecting the health state of aluminum electrolysis process (AEP). However, current methods hardly take into consideration the quantitative Heat Balance Indicator (HBI) construction by using the unlabeled data. In addition, it is limited to construct HBI by learning the complex relationship between degraded features and large-scale HBI labels in a supervised manner, because the labeled data are scarce and annotations are expensive in practice. To quantitatively construct HBI by using the unlabeled data, this paper proposes an unsupervised HBI construction method based on variational autoencoder (VAE). Firstly, we propose fuzzy evaluation strategy to estimate the tendency of cell temperature to highlight the trend of heat balance. Rather than simply using the latent features, we extract the feature representation of the heat balance state considering not only the latent features but also the reconstruction error. Finally, HBI is constructed by calculating the distance between the features representation of normal heat balance and degraded state. The applications of heat balance monitoring in a real-world aluminum electrolysis plant are performed to verify its effectiveness. The experimental results demonstrate that our proposed HBI construction method can better represent heat balance state of AEP, the average fault detection rate can achieve 80% for the monitoring electrolytic cells, increasing by more than 3% compared with these traditional monitoring statistics.

关键词： Heat Balance Indicator Fuzzy evaluation variational autoencoder Aluminum electrolysis process

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Cluster variational autoencoder Model for Monitoring the Multimode Blast Furnace System

引用

PROCESSES 2023年第9期11卷 2580页

作者： Chen, Chenyu Cai, Jinhui China Jiliang Univ Coll Metrol & Measurement Engn Hangzhou 310018 Peoples R China

Efficient monitoring of the blast furnace system is crucial for maintaining high production efficiency and ensuring product quality. This article introduces a hybrid cluster variational autoencoder model for monitoring the blast furnace ironmaking process which exhibits multimode behaviors. In contrast to traditional approaches, this method utilizes neural networks to learn data features and effectively handles the diverse feature types observed in different production modes. Through the utilization of a clustering process within the hidden layer of the variational autoencoder, the proposed technique facilitates efficient fault detection in the context of multimodal blast furnace data. Based on the variational autoencoder model, this study further establishes a unified monitoring index and defines a method for computing the control limits. The application of the model to real blast furnace data reveals its proficiency in accurately identifying faults across diverse modes;compared with the probabilistic principal component analysis based on the local nearest neighbor standardization method and the recursive probabilistic principal component analysis, the model shows a reduction in false positives by up to 10.3% and a substantial reduction of 19.2% in the missed detection rate. This method achieves a remarkable false detection rate of only 0.2% and 0 instances of missed detection.

关键词： multimode blast furnace system process monitoring variational autoencoder Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

A novel network core structure extraction algorithm utilized variational autoencoder for community detection

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年 222卷

作者： Fei, Rong Wan, Yuxin Hu, Bo Li, Aimin Li, Qian Xian Univ Technol Sch Comp Sci & Engn Xian Shaanxi Peoples R China Shaanxi Key Lab Network Comp & Secur Technol Xian Shaanxi Peoples R China Hangzhou HollySys Automat Co Ltd Hangzhou Zhejiang Peoples R China

Community detection technologies have the general research significance in complex networks, in which the topology information of network is worthy to be the focus for its widely application. It is the definition of community structure that the connection of nodes in the community is dense with the connection of nodes outside the community is sparse, which is corresponding to the core structure in the complex real networks is represented by a compact and dense set of connected nodes. While all the notes in the network are considered by the traditional topology, it is hard to extract the core structure with the continuous, exponential growth of community networks. In this paper, a novel network core structure extraction algorithm utilized variational autoencoder for community detection(CSEA) is proposed for finding the community structure more accurately. Firstly, the K-truss algorithm is used to find the core structure information in the network, and the similarity matrix is generated by similarity mapping combined with local information. Secondly, the variational autoencoder is used to extract and reduce the dimension of the similarity matrix containing the core structure of the network, and the low-dimensional feature matrix is obtained. Finally, the K-means clustering algorithm is utilized to obtain the community structure information. We compare CSEA algorithm with 18 different types of community detection algorithms using 4 evaluation metrics on 19 complex real networks. By extensively evaluating our algorithm on large real-world datasets, we show that CSEA algorithm has an excellent community division effect in dense complex real networks, especially in small and medium-sized networks, and it can accurately divide the complex real networks with unknown community structure. Simultaneously, CSEA algorithm also reveals some efficiency advantage in its on-line test.

关键词： Community detection Complex networks Core structure variational autoencoder Clustering

来源：评论

学校读者我要写书评

暂无评论

Improvement of thermal comfort for underground space: Data enhancement using variational autoencoder

引用

BUILDING AND ENVIRONMENT 2022年第PartA期207卷 108457-108457页

作者： Qiao, Renlu Li, Xiangyu Gao, Shuo Ma, Xiwen Tongji Univ 1239 Siping Rd Shanghai Peoples R China Beijing Univ Technol Fac Architecture Civil & Transportat Engn Beijing Peoples R China Univ Oxford 11a Mansfield Rd Oxford OX1 3SZ England Jackson & Ryan Architects 2370 Rice BlvdSte 210 Houston TX 77005 USA

The proportion of buildings occupying underground space has increased with three-dimensional urban development. Thermal comfort is crucial to the design of underground spaces and plays an important role in the optimization of building environment controls. Owing to limitations in recording various practical environmental parameters, it is difficult to access large data and further to establish an accurate forecasting model for the thermal comfort of an underground space. This paper addresses the problem from the perspective of data enhancement. A model for generating underground space data based on a variational autoencoder is proposed. The model maps data of the thermal comfort of an underground space to a highly compressed latent layer space and generates data in an unsupervised manner. The forecasting models were trained using the generated data, resulting in accuracy improvements of 41.34%-45.31%. Hence, the proposed generative model can learn effective real data features. The results also demonstrate that the adjustment of ventilation is more effective than the adjustment of the temperature and relative humidity in improving the thermal comfort of an underground space. The findings of this research will provide better thermal comfort evaluation for the operational management of building environment in underground spaces.

关键词： Underground space Thermal comfort Data augmentation variational autoencoder Forecasting model

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：