检索结果-内蒙古大学图书馆

Intelligent optimization of stiffener unit cell via variational autoencoder-based feature extraction

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION 2023年第1期66卷 1-24页

作者： Liu, Dachuan Hao, Peng Xu, Tengfei Zhu, Yingjie Liu, Xuanxiu Wang, Bo Li, Gang Dalian Univ Technol Dept Engn Mech State Key Lab Struct Anal Ind Equipment Key Lab Digital Twin Ind Equipment Dalian 116023 Liaoning Peoples R China China Acad Launch Vehicle Technol Beijing 100076 Peoples R China

Grid-stiffened structures are widely used in industrial equipment, where the layout of stiffener unit cells is critical in the structural performance. However, owing to the lack of design techniques, existing stiffener unit cell designs are often achieved only by comparative selection among several common cell configurations. In this study, a deep learning-based intelligent optimization framework for the stiffener unit cell of grid-stiffened panels was proposed. First, a database containing nearly 10,000 stiffener unit cells was generated by traversal while considering the manufacturability. Feature extraction was then performed on the generated database using a variational autoencoder and mapped to a 16-dimensional continuous latent design space according to geometric features. Subsequently, in this latent space, a Gaussian process model was established, and the maximum expected improvement criterion was utilized to drive the model update and optimization search, thus realizing data-driven optimization for the stiffener unit cell of grid-stiffened panels. In three typical numerical examples, compared with the best of the traditional stiffener unit cells, the obtained optimal designs were improved by 25.61%, 25.88%, and 10.66%, respectively, demonstrating the effectiveness of this method as an alternative stiffener unit cell design method. Furthermore, this study also indicates the significant potential of geometric feature extraction and further structural layout optimization via deep learning.

关键词： Grid-stiffened panel Stiffener unit cell variational autoencoder Intelligent optimization

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Hierarchical variational autoencoder for Predicting Breast Cancer

引用

IEEE ACCESS 2024年 12卷 195658-195670页

作者： Sreelekshmi, V. Pavithran, K. Nair, Jyothisha J. Amrita Vishwa Vidyapeetham Amrita Sch Comp Dept Comp Sci & Engn Amritapuri 690525 India Amrita Inst Med Sci Dept Med Oncol Kochi 682041 Kerala India

Breast cancer continues to be a major health concern worldwide. Early and accurate prediction is crucial for effective treatment and improving survival rates. Computer Aided Diagnosis system serves as an invaluable tool for radiologists, aiming to reduce diagnostic errors and enhance the accuracy of diagnosis. These systems incorporate various processing techniques, including pre-processing, segmentation, feature extraction, and classification. Moreover, deep learning methods frequently suffer from sub optimal performance and demand substantial computational resources. This study focuses on developing an automated classification model for mammography images to aid in breast cancer diagnosis. Our proposed model initiates with noise removal using median filters, followed by the removal of the pectoral muscle in images through the Canny-edge detection method. On these preprocessed images, we applied data augmentation using a two-point crossover technique, addressing issues of small datasets and class imbalances common in medical image analysis. The images then undergo multi-scale representation via the fourth-order complex diffusion algorithm. Feature extraction is conducted on these multi-scaled images using a Hierarchical variational Auto-encoders and then classified using a Support Vector Machine. Employing fourth-order complex diffusion for initial multi-scale representation significantly enhances the accuracy of feature extraction resulting in robust classification performance. The training process involves two different datasets like MIAS and the KAU-BCMD. Test results for the KAU-BCMD dataset include: accuracy of 99.80%, Area Under the Curve of 99.30%, F1-score of 99.20%, balanced accuracy of 99.80%, and Matthews correlation coefficient of 99.20%. For the MIAS dataset, test results show accuracy of 99.30%, Area Under the Curve of 99.10%, F1-score of 98.30%, balanced accuracy of 99.00%, and Matthews correlation coefficient of 99.00%. Our validation results clearl

关键词： Feature extraction Breast cancer Muscles Accuracy Data augmentation Mammography Image segmentation Noise Convolutional neural networks Classification algorithms convolutional neural network data augmentation edge detection multi-scale representation variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Non-Parallel Whisper-to-Normal Speaking Style Conversion Using Auxiliary Classifier variational autoencoder

引用

IEEE ACCESS 2023年 11卷 44590-44599页

作者： Seki, Shogo Kameoka, Hirokazu Kaneko, Takuhiro Tanaka, Kou NTT Corp NTT Commun Sci Labs Atsugi Kanagawa 2430198 Japan

This paper is concerned with non-parallel whisper-to-normal speaking-style conversion (W2N-SC), which converts whispered speech into normal speech without using parallel training data. Most relevant to this task is voice conversion (VC), which converts one speaker's voice to another. However, the W2N-SC task differs from the regular VC task in three main respects. First, unlike normal speech, whispered speech contains little or no pitch information. Second, whispered speech usually has significantly less energy than normal speech and is therefore more susceptible to external noise. Third, in the actual usage scenario of W2N-SC, users may suddenly switch voice modes from whispered to normal speech, or vice versa, meaning that the speaking-style of input speech cannot be assumed in advance. To clarify whether existing VC techniques can successfully handle these task-specific concerns and how they should be modified to better address them, we consider a variational autoencoder (VAE)-based VC method as a baseline and examine what modifications to this method would be effective for the current task. Specifically, we study the effects of 1) a self-supervised training scheme called filling-in-frames (FIF);2) data augmentation (DA) using noisy speech samples;and 3) an architecture that allows for any-to-many conversions. Through experimental evaluation of the W2N-SC and speaker conversion tasks, we confirmed that, especially in the W2N-SC task, the version incorporating the above modifications works better than the baseline VC model applied as is.

关键词： Task analysis Training Decoding Speech Noise measurement Training data Generators Voice conversion whisper-to-normal speaking style conversion variational autoencoder self-supervised learning data augmentation

来源：评论

学校读者我要写书评

暂无评论

Chiller fault diagnosis based on improved variational autoencoder and co-training framework: A case study of insufficient samples

引用

JOURNAL OF BUILDING ENGINEERING 2024年 88卷

作者： Lu, Cheng Ma, Xiang Yan, Ke China Jiliang Univ Coll Informat Engn Hangzhou 310018 Peoples R China Hunan Univ Mech & Elect Engn Changsha 410006 Peoples R China

Implementing efficient automatic fault diagnosis is critical for saving energy and minimizing financial losses in the heating ventilation air-conditioning (HVAC) systems of commercial buildings. However, the limited quantity and weak features of fault samples acquired during HVAC operations hinder the effectiveness of conventional machine learning -based fault diagnosis methodologies. This paper proposes a method based on an improved conditional variational autoencoder (MCVAE) and co -training (CT) ideology to address the issue of insufficient training samples. Initially, we employ MCVAE to synthesize an extensive dataset of chiller fault samples from the original training dataset. Subsequently, the beneficial samples for training our fault diagnostic classifier, namely high -quality samples, are selected from the generated dataset using the CT -based framework. Finally, the selected high -quality samples are merged into the original training dataset to train the ultimate fault classifiers. Experimental results demonstrate that our proposed method outperforms in effectiveness and efficiency compared to recently published methods. For instance, in the case of fault level 1 compared to the suboptimal model, our approach exhibits improvements of 2.41% when each type has 5 fault samples.

关键词： Fault diagnosis variational autoencoder Chiller Data augmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Nonnegative Matrix Factorization Using a variational autoencoder With Application to Single-Cell RNA Sequencing Data

引用

IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS 2023年第2期20卷 883-893页

作者： Jee, Dong Jun Kong, Yixin Chun, Hyonho Korea Adv Inst Sci & Technol Dept Math Sci KR-34141 Daejeon South Korea Boston Univ Dept Math & Stat Boston MA 02134 USA

Single-cell RNA sequencing is used to analyze the gene expression data of individual cells, thereby adding to existing knowledge of biological phenomena. Accordingly, this technology is widely used in numerous biomedical studies. Recently, the variational autoencoder has emerged and has been adopted for the analysis of single-cell data owing to its high capacity to manage large-scale data. Many different variants of the variational autoencoder have been applied, and have yielded superior results. However, because it is nonlinear, the model does not provide parameters that can be used to explain the underlying biological patterns. In this paper, we propose an interpretable nonnegative matrix factorization method that decomposes parameters into those shared across cells and those that are cell-specific. Effective nonlinear dimension reduction was achieved via a variational autoencoder applied to the cell-specific parameters. In addition to achieving nonlinear dimension reduction, our model could estimate the cell-type-specific gene expression. To improve the estimation accuracy, we introduced log-regularization, which reflects the single-cell property. Overall, our approach displayed excellent performance in a simulation study and in real data analyses, while maintaining good biological interpretability.

关键词： Dimensionality reduction Matrix decomposition Neural networks Data models Decoding Analytical models Sequential analysis Deep neural networks nonlinear dimension reduction nonnegative matrix factorization single -cell RNA sequencing data variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Connections with Robust PCA and the Role of Emergent Sparsity in variational autoencoder Models

引用

JOURNAL OF MACHINE LEARNING RESEARCH 2018年第1期19卷 1573-1614页

作者： Dai, Bin Wang, Yu Aston, John Hua, Gang Wipf, David Tsinghua Univ Inst Adv Study Beijing Peoples R China Univ Cambridge Dept Pure Math & Math Stat Cambridge England Microsoft Res Redmond WA USA Microsoft Res Beijing Peoples R China

variational autoencoders (VAE) represent a popular, flexible form of deep generative model that can be stochastically fit to samples from a given random process using an information-theoretic variational bound on the true underlying distribution. Once so-obtained, the model can be putatively used to generate new samples from this distribution, or to provide a low-dimensional latent representation of existing samples. While quite effective in numerous application domains, certain important mechanisms which govern the behavior of the VAE are obfuscated by the intractable integrals and resulting stochastic approximations involved. Moreover, as a highly non-convex model, it remains unclear exactly how minima of the underlying energy relate to original design purposes. We attempt to better quantify these issues by analyzing a series of tractable special cases of increasing complexity. In doing so, we unveil interesting connections with more traditional dimensionality reduction models, as well as an intrinsic yet underappreciated propensity for robustly dismissing sparse outliers when estimating latent manifolds. With respect to the latter, we demonstrate that the VAE can be viewed as the natural evolution of recent robust PCA models, capable of learning nonlinear manifolds of unknown dimension obscured by gross corruptions.

关键词： variational autoencoder Deep Generative Model Robust PCA

来源：评论

学校读者我要写书评

暂无评论

UNSUPERVISED ADAPTATION FOR HIGH-DIMENSIONAL WITH LIMITED-SAMPLE DATA CLASSIFICATION USING variational autoencoder

引用

COMPUTING AND INFORMATICS 2021年第1期40卷 1-28页

作者： Mahmud, Mohammad Sultan Huang, Joshua Zhexue Fu, Xianghua Ruby, Rukhsana Wu, Kaishun Shenzhen Univ Coll Comp Sci & Software Engn Shenzhen 518060 Peoples R China Shenzhen Univ Natl Engn Lab Big Data Syst Comp Technol Shenzhen 518060 Peoples R China

High-dimensional with limited-sample size (HDLSS) datasets exhibit two critical problems: (1) Due to the insufficiently small-sample size, there is a lack of enough samples to build classification models. Classification models with a limited-sample may lead to overfitting and produce erroneous or meaningless results. (2) The 'curse of dimensionality' phenomena is often an obstacle to the use of many methods for solving the high-dimensional with limited-sample size problem and reduces classification accuracy. This study proposes an unsupervised framework for high-dimensional limited-sample size data classification using dimension reduction based on variational autoencoder (VAE). First, the deep learning method variational autoencoder is applied to project high-dimensional data onto lower-dimensional space. Then, clustering is applied to the obtained latent-space of VAE to find the data groups and classify input data. The method is validated by comparing the clustering results with actual labels using purity, rand index, and normalized mutual information. Moreover, to evaluate the proposed model strength, we analyzed 14 datasets from the Arizona State University Digital Repository. Also, an empirical comparison of dimensionality reduction techniques shown to conclude their applicability in the high-dimensional with limited-sample size data settings. Experimental results demonstrate that variational autoencoder can achieve more accuracy than traditional dimensionality reduction techniques in high-dimensional with limited-sample-size data analysis.

关键词： HDLSS problem dimensionality reduction unsupervised framework variational autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

Class-biased sarcasm detection using BiLSTM variational autoencoder-based synthetic oversampling (vol 27, pg 5603, 2023)

引用

SOFT COMPUTING 2023年第9期27卷 5621-5621页

作者： Chatterjee, Sankhadeep Bhattacharjee, Saranya Ghosh, Kushankur Das, Asit Kumar Banerjee, Soumen Indian Inst Engn Sci & Technol Dept Comp Sci & Technol Howrah India Univ Engn & Management Dept Comp Sci & Engn Kolkata India Univ Alberta Dept Comp Sci Edmonton AB Canada Budge Budge Inst Technol Dept Elect & Commun Engn Kolkata 700137 West Bengal India

Recent research works have established the importance of sarcasm detection in the domain of sentiment analysis. Automatic sarcasm detection using social media data is a challenging task in the presence of imbalanced classes. Real-life social media data often suffer from this problem of class imbalance resulting in dramatical degradation of the performance of classification models attempting to detect sarcasm. Motivated by this, in the current article, a Bi-LSTM variational autoencoder model has been proposed to alleviate the problem of imbalanced classes in social media datasets targeted to train sarcasm detection models. The proposed BVA model is trained with a large corpus of sarcastic and non-sarcastic tweets to obtain the most suitable latent space representation of the same. These inherently class-biased latent vectors are then oversampled using synthetic minority oversampling techniques. The quality of the proposed method is established by training and testing a set of well-known classifiers in terms of precision, recall, F1-score, AUC, and G-mean. Extensive experiments reveal that the proposed BVA model combined with oversampling techniques can improve classifier performance for sarcasm detection to a greater extent.

关键词： Sarcasm detection Social media Synthetic minority oversampling variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Detection of Structural Damage Using variational autoencoder and a One-Class Support Vector Machine

引用

IEEE ACCESS 2023年 11卷 67098-67112页

作者： Pollastro, Andrea Testa, Giusiana Bilotta, Antonio Prevete, Roberto Univ Naples Federico II Dept Elect Engn & Informat Technol Naples Italy Univ Naples Federico II Dept Struct Engn & Architecture Naples Italy

In recent years, Artificial Neural Networks (ANNs) have been introduced in Structural Health Monitoring (SHM) systems. A semi-supervised method with a data-driven approach allows the ANN training on data acquired from an undamaged structural condition to detect structural damages. In standard approaches, after the training stage, a decision rule is manually defined to detect anomalous data. However, this process could be made automatic using machine learning methods. This paper proposes a semi-supervised method with a data-driven approach to detect structural anomalies. The methodology consists of: 1) a variational autoencoder (VAE) to approximate undamaged data distribution and 2) a One-Class Support Vector Machine (OC-SVM) to discriminate different health conditions using damage-sensitive features extracted from VAE's signal reconstruction. The method is applied to a scale steel structure that was tested in nine damage scenarios by IASC-ASCE Structural Health Monitoring Task Group.

关键词： Feature extraction Monitoring Standards Support vector machines Data models Bridges Anomaly detection Semisupervised learning Biomedical monitoring Machine learning Semi-supervised damage detection structural health monitoring variational autoencoder one-class support vector machines machine learning

来源：评论

学校读者我要写书评

暂无评论

Constructing Dynamic Topic Models Based on variational autoencoder and Factor Graph

引用

IEEE ACCESS 2018年 6卷 53102-53111页

作者： Gou, Zhinan Han, Lixin Sun, Ling Zhu, Jun Yan, Hong Hohai Univ Coll Comp & Informat Nanjing 211100 Jiangsu Peoples R China Nanjing Univ Sci & Technol Zijin Coll Coll Comp Sci Nanjing 210023 Jiangsu Peoples R China City Univ Hong Kong Dept Elect Engn Hong Kong Hong Kong Peoples R China

Topic models are widely used in various fields of machine learning and statistics. Among them, the dynamic topic model (DTM) is the most popular time-series topic model for the dynamic representations of text corpora. A major challenge is that the posterior distribution of DTM requires a complex reasoning process with the high cost of computing time in modeling, and even a tiny change of model requires restructuring. For these reasons, the variability and generality of DTM is so poor that DTM is difficult to be carried out. In this paper, we introduce a new method for constructing DTM based on variational autoencoder and factor graphs. This model uses re-parameterization of the variational lower bound to generate a lower bound estimator which is optimized by standard stochastic gradient descent method directly. At the same time, the optimization process is simplified by integrating the dynamic factor graph in the state space to achieve a better model. The experimental dataset uses a journal paper corpus that mainly focuses on natural language processing and spans twenty-five years (1984-2009) from DBLP. Experiment results indicate that the proposed method is effective and feasible by comparing several state-of-the-art baselines.

关键词： Dynamic topic model variational autoencoder factor graph 2-layer neural network

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：