检索结果-内蒙古大学图书馆

Case2vec: joint variational autoencoder for case text embedding representation

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2021年第9期12卷 2517-2528页

作者： Song, Ran Gao, Shengxiang Yu, Zhengtao Zhang, Yafei Zhou, Gaofeng Kunming Univ Sci & Technol Fac Informat Engn & Automat Kunming 650500 Yunnan Peoples R China Kunming Univ Sci & Technol Yunnan Key Lab Artificial Intelligence Kunming 650500 Yunnan Peoples R China

The embedding representation of the case text represent text as vector which consist information of original texts abundantly. Text embedding representation usually uses text statistical features or content features alone. However, case texts have characteristics that include similar structure, repeated words, and different text lengths. And the statistical feature or content feature cannot represent case text efficiently. In this paper, we propose a joint variational autoencoder (VAE) to represent case text embedding representation. We consider the statistical features and content features of case texts together, and use VAE to align the two features into the same space. We compare our representations with existing methods in terms of quality, relationship, and efficiency. The experiment results show that our method has achieved good results, which have higher performance than the model using single feature.

关键词： Embedding representation Statistical feature Content feature variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Non-Invasive Detection of Rotor Inter-Turn Short Circuit of a Hydrogenerator Using AI-Based variational autoencoder

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2024年第1期60卷 28-37页

作者： Ibrahim, Rony Zemouri, Ryad Kedjar, Bachir Merkhouf, Arezki Tahan, Antoine Al-Haddad, Kamal Lafleur, Francois Ecole Technol Super Montreal PQ H3C 1K3 Canada Ctr Rech Hydroquebec Varennes PQ J3X 1S1 Canada

This article presents a non-intrusive technique for detecting the rotor inter-turn short circuit (RITSC) of a hydrogenerator using an artificial intelligence (AI) based variational autoencoder (VAE). The technique is applied to a large hydrogenerator of 74 MVA and 76 poles, to test its health monitoring and classification potential. The model is trained and validated based on the acquisition of real vibratory data collected in situ from a healthy machine. The frequency pattern of the fault in the vibration signal is obtained based on finite element methods (FEM). Then, to test the sensitivity of the model in early fault detection, the signature is injected into another set of real healthy vibration signals, and the results are compared to those obtained using the traditional vibration monitoring technique. Furthermore, clustering in the latent space of the model is explored. The obtained results prove the ability of this technique and its potential in detecting anomalies at earlier stages as well as its capacity to cluster different degrees of severity of the fault in a 3D user-friendly space.

关键词： Vibrations Circuit faults Monitoring Finite element analysis Stator windings Integrated circuit modeling Atmospheric modeling Diagnosis fault detection hydrogenerators monitoring non-invasive rotor inter-turn short circuit variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Infer-AVAE: An attribute inference model based on adversarial variational autoencoder

引用

NEUROCOMPUTING 2022年第0期483卷 105-115页

作者： Zhou, Yadong Ding, Zhihao Liu, Xiaoming Shen, Chao Tong, Lingling Guan, Xiaohong Xi An Jiao Tong Univ Fac Elect & Informat Engn MOE KLINNS Lab Xian 710049 Shaanxi Peoples R China Natl Comp Network Emergency Response Tech Team Beijing Peoples R China Tsinghua Univ Ctr Intelligent & Networked Syst Beijing 100084 Peoples R China Tsinghua Univ TNLIST Lab Beijing 100084 Peoples R China

User attributes, such as gender and education, face severe incompleteness in social networks. Attribute inference aims to infer users' missing attribute labels based on observed data to make this valuable data usable for downstream tasks like user profiling and personalized recommendation. Recently, variational autoencoder (VAE), an end-to-end deep generative model, has shown promising performance by handling the problem in a semi-supervised way. However, VAEs can easily suffer from over-fitting and over-smoothing when applied to attribute inference. Specifically, VAE implemented with multi-layer perceptron (MLP) can only reconstruct input data but fail to infer missing parts. While using the trending graph neural networks (GNNs) as encoder has the problem that GNNs aggregate redundant information from the neighborhood and generate indistinguishable user representations, known as over-smoothing. In this paper, we propose an attribute Inference model based on Adversarial VAE (Infer-AVAE) to cope with these issues. Specifically, to overcome over-smoothing, Infer-AVAE unifies MLP and GNNs in the encoder to learn positive and negative latent representations respectively. Meanwhile, an adversarial network is trained to distinguish the two representations, and GNNs are trained to aggregate less noise for more robust representations through adversarial training. Finally, to relieve over-fitting, mutual information constraint is introduced as a regularizer for the decoder to make better use of auxiliary information in representations and generate outputs not limited by observations. We evaluate our model on four real world social network datasets, and experimental results demonstrate that our model averagely outperforms baselines by 7.0% in accuracy. (c) 2022 Elsevier B.V. All rights reserved.

关键词： Social network Attribute inference Graph neural network variational autoencoder Adversarial training Mutual information

来源：评论

学校读者我要写书评

暂无评论

Designing Multi-Task Convolutional variational autoencoder for Radio Tomographic Imaging

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2022年第1期69卷 219-223页

作者： Wu, Hongzhuang Ma, Xiaoli Liu, Songyong China Univ Min & Technol Sch Mechatron Engn Xuzhou 221116 Jiangsu Peoples R China Georgia Inst Technol Sch Elect & Comp Engn Atlanta GA 30332 USA

Radio tomographic imaging (RTI) emerges to model the environment and detect the passive targets by a wireless network. In this work, the received signal strength (RSS) measurements are collected from an uncalibrated network, and a multi-task convolutional variational autoencoder model is proposed to realize RTI. The presented model is trained end-to-end to denoise the RSS measurements, reconstruct the static tomographic images, estimate the parameters of the wireless network, and classify the measurement noise level, simultaneously. The multi-task variational learning strategy is able to improve the generalization of the model. Numerical experiments demonstrate the efficacy of our RTI method.

关键词： Wireless networks Image reconstruction Noise level Convolution Calibration Attenuation Tomography Radio tomographic imaging variational autoencoder convolutional neural network multi-task learning

来源：评论

学校读者我要写书评

暂无评论

引用

BMC BIOINFORMATICS 2023年第1期24卷 1-19页

作者： Kim, Gwangwoo Chun, Hyonho Korea Adv Inst Sci & Technol KAIST Grad Sch Data Sci Daejeon South Korea Korea Adv Inst Sci & Technol KAIST Dept Math Sci Daejeon South Korea

BackgroundDeep generative models naturally become nonlinear dimension reduction tools to visualize large-scale datasets such as single-cell RNA sequencing datasets for revealing latent grouping patterns or identifying outliers. The variational autoencoder (VAE) is a popular deep generative method equipped with encoder/decoder structures. The encoder and decoder are useful when a new sample is mapped to the latent space and a data point is generated from a point in a latent space. However, the VAE tends not to show grouping pattern clearly without additional annotation information. On the other hand, similarity-based dimension reduction methods such as t-SNE or UMAP present clear grouping patterns even though these methods do not have encoder/decoder *** bridge this gap, we propose a new approach that adopts similarity information in the VAE framework. In addition, for biological applications, we extend our approach to a conditional VAE to account for covariate effects in the dimension reduction step. In the simulation study and real single-cell RNA sequencing data analyses, our method shows great performance compared to existing state-of-the-art methods by producing clear grouping structures using an inferred encoder and decoder. Our method also successfully adjusts for covariate effects, resulting in more useful dimension *** method is able to produce clearer grouping patterns than those of other regularized VAE methods by utilizing similarity information encoded in the data via the highly celebrated UMAP loss function.

关键词： Deep learning-based nonlinear dimension reduction variational autoencoder Uniform manifold approximation and projection Single-cell RNA sequencing data Covariate effect

来源：评论

学校读者我要写书评

暂无评论

Gaussian Mixture variational autoencoder for Semi-Supervised Topic Modeling

引用

IEEE ACCESS 2020年 8卷 106843-106854页

作者： Zhou, Cangqi Ban, Hao Zhang, Jing Li, Qianmu Zhang, Yinghua Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Peoples R China Nanjing Univ Sci & Technol Sch Cyber Sci & Engn Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Informat Dept Nanjing 210094 Peoples R China SenseDeal Intelligent Technol Co Ltd Beijing 100084 Peoples R China

Topic models are widely explored for summarizing a corpus of documents. Recent advances in variational autoencoder (VAE) have enabled the development of black-box inference methods for topic modeling in order to alleviate the drawbacks of classical statistical inference. Most existing VAE based approaches assume a unimodal Gaussian distribution for the approximate posterior of latent variables, which limits the flexibility in encoding the latent space. In addition, the unsupervised architecture hinders the incorporation of extra label information, which is ubiquitous in many applications. In this paper, we propose a semi-supervised topic model under the VAE framework. We assume that a document is modeled as a mixture of classes, and a class is modeled as a mixture of latent topics. A multimodal Gaussian mixture model is adopted for latent space. The parameters of the components and the mixing weights are encoded separately. These weights, together with partially labeled data, also contribute to the training of a classifier. The objective is derived under the Gaussian mixture assumption and the semi-supervised VAE framework. Modules of the proposed framework are appropriately designated. Experiments performed on three benchmark datasets demonstrate the effectiveness of our method, comparing to several competitive baselines.

关键词： Computational modeling Gaussian mixture model Standards Data models Gaussian distribution Training Topic model variational autoencoder semi-supervised learning Gaussian mixture model deep generative learning

来源：评论

学校读者我要写书评

暂无评论

Mixture autoregressive and spectral attention network for multispectral image compression based on variational autoencoder

引用

VISUAL COMPUTER 2024年第9期40卷 6295-6318页

作者： Kong, Fanqiang Ren, Guanglong Hu, Yunfang Li, Dan Hu, Kedi Nanjing Univ Aeronaut & Astronaut Coll Astronaut Nanjing 210016 Jiangsu Peoples R China Jiaozuo Baili United Pigment Co LTD Jiaozuo 454450 Henan Peoples R China

Multispectral images, with their unique three-dimensional characteristics, require specialized spatial-spectral feature extraction modules to achieve superior compression results. Current end-to-end compression frameworks underperform compared to advanced coding algorithms, primarily due to insufficient spectral feature extraction at high bit rates and challenges in guiding entropy coding. To address these issues, this paper proposes the Mixture Autoregressive Spectral Attention Network (MARSA-Net), featuring two attention mechanisms: Coor-Spec and LD-CAM, and an autoregressive component. Our evaluation on real datasets from satellites demonstrates MARSA-Net's superiority over traditional algorithms, including H.266/VVC, underlining its potential in multispectral image compression. This research contributes to improved compression methods and extends our understanding of spectral feature extraction in multispectral imagery.

关键词： Hierarchical prior model Learnt multispectral image compression Spectral attention variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Automated defect detection in nanomaterial-coated-fabrics using variational autoencoder

引用

JOURNAL OF ENGINEERED FIBERS AND FABRICS 2024年 19卷

作者： Tram, Nguyen Ngoc Jooyong, Kim Soongsil Univ Dept Smart Wearables Engn Seoul South Korea Soongsil Univ Dept Organ Mat & Fiber Engn Seoul South Korea

This paper introduces an unsupervised method for detecting regions with a high density of nanomaterials on coated fabric using variational autoencoder, a generative model capable of learning dominant features of the input data and generating similar outputs. The model was applied to images of cotton fabric coated with commercial single-walled carbon nanotubes (SW-CNT) to learn their features. Morphological and electrical properties of the coated samples were initially investigated to identify high-density particle regions. Subsequently, an experiment evaluated the performance of these samples in a specific smart textile application, establishing ground truth for defect localization in each fabric image. Image post-processing techniques were then employed to accurately detect defective regions in test images. The proposed method achieved a recognition rate of 93.2% and the highest Intersection over Union (IoU) of 0.923. This study demonstrates a promising approach for defect identification in coated fabrics, advancing smart textile technology.

关键词： Defect detection deep learning generative model variational autoencoder SWCNT smart textiles

来源：评论

学校读者我要写书评

暂无评论

Self-supervised variational autoencoder towards recommendation by nested contrastive learning

引用

APPLIED INTELLIGENCE 2023年第15期53卷 18887-18897页

作者： Wang, Jing Wu, Jun Jia, Caiyan Zhang, Zhifei Beijing Jiaotong Univ Sch Comp & Informat Technol Beijing Peoples R China Minist Educ Engn Res Ctr Integrat & Applicat Digital Learning Beijing Peoples R China

Recommendation methods predicting potential items for user has evolved from linear factor models to non-linear factor deep learning models. Deep generative model, especially variational autoencoder(VAE), has been used in a wide range of recommendation systems such as MultVAE and RecVAE. Despite effectiveness, we argue that they suffer from two limitations: (1)sparse and noisy user-item interactions will affect the performance of VAE-based recommendation models;and (2)incorporating simple priors,e.g.,isotropic Gaussian, in VAE couldn't extract personalized user preference,as user's preference may be highly complex. In this paper, we propose a Nested Self-supervised variational autoencoder (NSVAE) model for recommendation to enhance generalization and accuracy of VAE-based recommendation models. Besides using VAE for predicting user interests, NSVAE supplements supervised task of recommendation with nested self-supervised task, which consider both partial and entire preference. Nested self-supervised task is composed of inside and outside pretext tasks. Inside pretext task aligns the representations learned from different views, where views contain user partial preference, and outside pretext task discriminates entire preference from other user. Recommendation task and pretext tasks can be seamlessly integrated and enhance each other. Extensive experiment results on three real-world benchmarks validate the superiority of our NSVAE model to state-of-the-art VAE-based recommendation models.

关键词： Recommender systems Self-supervised learning variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

A mechanical fault diagnosis model with semi-supervised variational autoencoder based on long short-term memory network

引用

NONLINEAR DYNAMICS 2024年第1期113卷 459-478页

作者： Qu, Yuanyuan Li, Tao Fu, Shichen Wang, Zhisheng Chen, Jian Zhang, Yupeng China Univ Min & Technol Beijing Sch Mech & Elect Engn Ding 11Xueyuan Rd Beijing 100083 Peoples R China

Condition monitoring and accurate fault diagnosis are always concerned for stable operating of mechanical equipment. The fault diagnosis based on supervised deep learning has been proved to be effective by their powerful capacities in feature extracting, but usually requiring large number of labeled data. Faced with the actual situation that labeled samples are often in short, data are imbalanced in category etc., accurate fault diagnosis based on deep learning is still challenging, so does to explore and explain the evolution of complex faults. A mechanical fault diagnosis model with Semi-Supervised variational autoencoder based on Long Short-Term Memory network (LSTM-SSVAE) is proposed in this paper. Through semi-supervised learning, LSTM-SSVAE uses unlabeled data to enhance the extraction of discriminant features of data, which make the model less dependent on only labeled data while giving improved fault diagnosis accuracy. The LSTM networks are applied as the encoder and decoder innovatively, and regularization constraints are added in loss function, to improve the clustering effect of the intermediate hidden variables, so that to achieve effective feature extraction and state detection. Based on open datasets, experimental results show that with the same number of labeled samples, the fault diagnosis accuracy obtained by using LSTM-SSVAE is higher than other typical semi-supervised learning models. Based on actual vibration data of working equipment in coal mining, the feasibility of clustering analysis of intermediate hidden variables also proves that the LSTM-SSVAE model is recommendable for fault evolution analysis and is potential for operating conditions prediction of mechanical equipment.

关键词： variational autoencoder Long short-term memory network Semi-supervised learning Fault diagnosis Clustering analysis

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：