检索结果-内蒙古大学图书馆

convolutional variational autoencoder-based feature learning for automatic tea clone recognition

JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES 2022年第6期34卷 3332-3342页

作者： Zilvan, Vicky Ramdan, Ade Heryana, Ana Krisnandi, Dikdik Suryawati, Endang Yuwana, R. Sandra Kusumo, R. Budiarianto S. Pardede, Hilman F. Indonesian Inst Sci Res Ctr Informat Bandung 40135 Indonesia

It is common to have various clones from cross-seedlings or unintended planting by the farmers in a tea plantation. Since each tea clone has distinctive features such as quality, resistance to diseases, etc., visual inspections are usually conducted on the plantations to segment areas with different tea clones within the plantation to produce crops with consistent quality. However, this would be costly and time-consuming. In this work, we apply machine learning and develop an application to recognize tea clones automatically. We propose a convolutional variational autoencoder-based feature learning algorithm to produce robust features against data distortions. There are two main advantages of using this algorithm for feature learning. First, there is no need to design complex handcrafted features for classifications, usually conducted in machine learning. Second, the resulting features are more robust when tested with data taken from unideal conditions. The proposed method is evaluated using the original and the distorted image. Our proposed method achieves the best performance of 0.83 (83%) for the original image test, 0.75 (75%) for the gaussian blur image test, and 0.78 (78%) for the median blur image test. This is a much more robust result than VGGNet16, a popular supervised deep convolutional neural network. (C) 2021 The Authors. Published by Elsevier B.V. on behalf of King Saud University.

关键词： convolutional variational autoencoder Feature learning Deep learning Tea clones recognition

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 in Large Hydrogenerators by Using Stray Flux Measurement Combined With convolutional variational autoencoder Analysis (CVAE)

引用

IEEE TRANSACTIONS ON INDUSTRY APPLICATIONS 2024年第1期60卷 196-205页

作者： Bechara, Helene Zemouri, Ryad Kedjar, Bachir Merkhouf, Arezki Al-Haddad, Kamal Tahan, Antoine Ecole Technol Super Dept Elect Engn Montreal PQ H3C1K3 Canada IREQ Inst Derech dHydroquebec Varennes PQ J3X 1S1 Canada Ecolede Technol Super Dept Mech Engn Montreal PQ H3C1K3 Canada

Salient Pole Synchronous Generators (SPSG) are known for their robustness and stability;However, internal faults like rotor interturn short circuits (ITSC) might still occur and lead to unscheduled machine shutdowns if not caught early. The literature focuses mainly on high-speed SPSGs and is short on studies covering the diagnosis of low-speed machines. To bridge this gap, this paper presents a non-invasive diagnosis method for low-speed SPSG used by Hydro-Quebec. The proposed approach is based on real measurements of stray flux signals and faulty synthetic signals, obtained by FEM simulations. The convolutional variational autoencoder (CVAE) is used to cluster signals according to the fault severity, and to visualize them in 2D space. Furthermore, two studies were conducted to compare the performance and robustness of the CVAE against the ${\bm{RMS}}$ standard method. The results demonstrate that the CVAE is more sensitive and reliable in detecting ITSCs in large hydrogenerators. Finally, a case study was conducted to validate the proposed method using a real faulty dataset, confirming the obtained results.

关键词： Circuit faults Rotors Robustness Convolution Monitoring Fault diagnosis Air gaps convolutional variational autoencoder hydrogenerators non-invasive diagnosis rotor interturn short circuit stray flux

来源：评论

学校读者我要写书评

暂无评论

Smart manufacturing under limited and heterogeneous data: a sim-to-real transfer learning with convolutional variational autoencoder in thermoforming

引用

INTERNATIONAL JOURNAL OF COMPUTER INTEGRATED MANUFACTURING 2024年第1-2期37卷 18-36页

作者： Ramezankhani, Milad Harandi, Mehrtash Seethaler, Rudolf Milani, Abbas S. Univ British Columbia Mat & Mfg Res Inst Kelowna BC Canada Monash Univ Dept Elect & Comp Syst Engn Clayton Australia Univ British Columbia Mat & Mfg Res Inst Kelowna BC V1V 1V7 Canada

Data in advanced manufacturing are often sparse and collected from various sensory devices in a heterogeneous and multi-modal fashion. Thus, for such intricate input spaces, learning robust and reliable predictive models for product quality assessments entails implementing complex nonlinear models such as deep learning. However, these 'data-greedy' models require massive datasets for training, and they tend to exhibit poor generalization performance otherwise. To address the data paucity and the data heterogeneity in smart manufacturing applications, this paper introduces a sim-to-real transfer-learning framework. Specifically, using a unified wide-and-deep learning approach, the model pre-processes structured sensory data (wide) as well as high-dimensional thermal images (deep) separately, and then passes the respective concatenated features to a regressor for predicting product quality metrics. convolutional variational autoencoder (ConvVAE) is utilized to learn concise representations of thermal images in an unsupervised fashion. ConvVAE is trained via a sim-to-real transfer learning approach, backed by theory-based heat transfer simulations. The proposed metamodeling framework was evaluated in an industrial thermoforming process case study. The results suggested that ConvVAE outperforms conventional dimensionality reduction methods despite limited data. A model explainability analysis was conducted and the resulting SHAP values demonstrated the agreement between the model's predictions, theoretical expectations, and data correlation statistics.

关键词： Intelligent manufacturing transfer learning convolutional variational autoencoder thermoforming model explainability

来源：评论

学校读者我要写书评

暂无评论

Deep order-wavelet convolutional variational autoencoder for fault identification of rolling bearing under fluctuating speed conditions

引用

EXPERT SYSTEMS WITH APPLICATIONS 2023年第1期216卷

作者： Yan, Xiaoan She, Daoming Xu, Yadong Nanjing Forestry Univ Sch Mechatron Engn Nanjing 210037 Peoples R China Jiangsu Univ Sch Mech Engn Zhenjiang 212013 Peoples R China Southeast Univ Sch Mech Engn Nanjing 211189 Peoples R China

Because of the complex operating environment of high-end industrial machinery, rolling bearing is generally operated at fluctuating working conditions such as variable speeds or loads, thus enables fault feature infor-mation is not obvious. That said, bearing fault identification under fluctuating working conditions are recognized as a very challenging problem. Deep learning blazes a valid route to address this issue by right of strong self -learning performance. Nevertheless, the performance of traditional deep learning model will degrade in the face of the fluctuating data with a sharp rising and heavy external interference. Therefore, to overcome this limitation, this study proposes a novel method named deep order-wavelet convolutional variational autoencoder (DOWCVAE) to identify bearing faults under fluctuating speed conditions, which can improve feature learning ability of a plain convolutional variational autoencoder (CVAE). Within this approach, an improved energy-order analysis with frequency-weighted energy operator (FWEO) is firstly presented to convert the raw time-domain vibration signal into the resampled angle-domain signal to relieve the influence of speed fluctuating and ac-quire the enhanced order spectrum data. Afterwards, wavelet kernel convolutional block (WKCB) with anti -symmetric real Laplace wavelet (ARLW) is constructed to extract the latent feature information closely related to equipment states from the enhanced order spectrum data via the stacked way layer by layer, which is capable of further promoting learning performance of overall network model and improve its generalizability. In addi-tion, a high-efficiency intelligent optimization algorithm termed as multi-objective gray wolf optimizer (MOGWO) is introduced for choosing automatically optimal wavelet parameters of DOWCVAE model and avoiding negative impact posed by artificially adjusting parameter. Ultimately, the learned latent features are loaded to the softmax classifier to achi

关键词： convolutional variational autoencoder Order analysis Laplace wavelet Bearing fault identification Fluctuating speeds

来源：评论

学校读者我要写书评

暂无评论

Identification of Composite Damages in Cement-Based Structures Using convolutional variational autoencoder Combined with Surface Wave Dispersion Energy 5th

Identification of Composite Damages in Cement-Based Structur...

引用

5th International Conference on Vibration and Energy Harvesting Applications-VEH

作者： Hu, Meng Wang, Shaohua Xu, Yude Tang, Lihua Tongji Univ Key Lab Rd & Traff Engn Minist Educ Shanghai Peoples R China Univ Auckland Dept Mech & Mech Engn Auckland New Zealand

ISBN: (纸本)9789819611935;9789819611911;9789819611904

In multilayered cement-based structures, the characteristics of ultrasonic waves are influenced by the laminar and meso-scale properties of the materials, leading to frequency dispersion effect. This phenomenon enables the utilization of surface wave dispersion energy (SWDE) to identify the damages in these structures. However, interpreting complex composite damages using SWDE in such structures is challenging. To address this, the potential of convolutional variational autoencoder (CVAE) in detecting complex composite damage in multilayered cement-based structures through SWDE is investigated in this work. Specifically, the finite difference method is employed to establish the model for the ultrasonic wave field in multilayered cement-based structures, incorporating the mesoscopic material properties. Subsequently, ultrasonic wave signals, indicative of different types of complex composite damages, are extracted and transformed into SWDE. Finally, the CVAE model, trained with these SWDE datasets, is employed for the identification of various damages. The results demonstrate that the proposed method is capable of effectively extracting and interpreting structural characteristics in the time, frequency, and spatial domains from SWDE, and is sensitive to changes in structural features due to invisible complex composite damages in multilayered cement-based structures. The effectiveness of the proposed method is validated by compared to other deep learning methods.

关键词： Cement-based structures Surface wave dispersion energy convolutional variational autoencoder Composite damage

来源：评论

学校读者我要写书评

暂无评论

Escher-Like Tiling Design from Video Images Using convolutional variational autoencoder

引用

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2021年第3期37卷 575-592页

作者： Hisatomi, Asuka Matsuyama, Tomofumi Kinoshita, Takahiro Mizuno, Kazunori Ono, Satoshi Kagoshima Univ Dept Informat Sci & Biomed Engn Kagoshima 8900065 Japan Takushoku Univ Dept Comp Sci Tokyo 1930985 Japan

This paper proposes a method that deforms a prominent movie or animation character into a tileable shape. Tiling is the act of covering the plane with one or a very few types of figures without overlaps and/or gaps. Although some previous methods can transform a given shape into a tileable shape, they cannot easily move the character into a suitably tileable pose. The proposed method learns the latent feature space that abstracts the target character's silhouettes using a convolutional variational autoencoder, and looks for the poses suitable for tiling by optimization in the latent space. Experimental results showed that the proposed method successfully generated tileable figures of the tested character in various poses, some of which were not included in the training dataset.

关键词： tiling tessellations hierarchical optimization genetic algorithm convolutional variational autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep convolutional variational autoencoder as a 2D-Visualization Tool for Partial Discharge Source Classification in Hydrogenerators

引用

IEEE ACCESS 2020年 8卷 5438-5454页

作者： Zemouri, Ryad Levesque, Melanie Amyot, Normand Hudon, Claude Kokoko, Olivier Tahan, Antoine HESAM Univ CEDRIC Lab Conservatoire Natl Arts & Metiers CNAM F-750141 Paris 03 France Inst Rech Hydroquebec IREQ Varennes PQ J3X 1S1 Canada Ecole Technol Super Montreal PQ H3C 1K3 Canada

Hydrogenerators are strategic assets for power utilities. Their reliability and availability can lead to significant benefits. For decades, monitoring and diagnosis of hydrogenerators have been at the core of maintenance strategies. A significant part of generator diagnosis relies on Partial Discharge (PD) measurements, because the main cause of hydrogenerator breakdown comes from failure of its high voltage stator, which is a major component of hydrogenerators. A study of all stator failure mechanisms reveals that more than 85 & x0025;of them involve the presence of PD activity. PD signal can be detected from the lead of the hydrogenerator while it is running, thus allowing for on-line diagnosis. Hydro-Qu & x00E9;bec has been collecting more than 33 000 unlabeled PD measurement files over the last decades. Up to now, this diagnostic technique has been quantified based on global PD amplitudes and integrated PD energy irrespective of the source of the PD signal. Several PD sources exist and they all have different relative risk, but in order to recognize the nature of the PD, or its source, the judgement of experts is required. In this paper, we propose a new method based on visual data analysis to build a PD source classifier with a minimum of labeled data. A convolutional variational autoencoder has been used to help experts to visually select the best training data set in order to improve the performances of the PD source classifier.

关键词： Hydrogenerators diagnosis partial discharges deep neural networks convolutional variational autoencoder data visualization feature extraction model interpretation generative model

来源：评论

学校读者我要写书评

暂无评论

Hydrogeophysical Characterization of Nonstationary DNAPL Source Zones by Integrating a convolutional variational autoencoder and Ensemble Smoother

引用

WATER RESOURCES RESEARCH 2021年第2期57卷 e2020WR028538-e2020WR028538页

作者： Kang, Xueyuan Kokkinaki, Amalia Kitanidis, Peter K. Shi, Xiaoqing Lee, Jonghyun Mo, Shaoxing Wu, Jichun Nanjing Univ Sch Earth Sci & Engn Minist Educ Key Lab Surficial Geochem Nanjing Peoples R China Stanford Univ Dept Civil & Environm Engn Stanford CA 94305 USA Univ San Francisco Dept Environm Sci San Francisco CA USA Univ Hawaii Manoa Dept Civil & Environm Engn Honolulu HI 96822 USA Univ Hawaii Manoa Water Resources Res Ctr Honolulu HI 96822 USA

Detailed characterization of dense nonaqueous phase liquid (DNAPL) source zone architecture (SZA) is essential for designing efficient remediation strategies. However, it is difficult to characterize a highly irregular and localized SZA, because traditional drilling investigations provide limited information. With limited data, the estimation accuracy of traditional geostatistical methods is strongly affected by the parameterization of the prior description of the SZA. To improve characterization performance, we parameterized the DNAPL saturation field using a physics-based approach. We trained a convolutional variational autoencoder (CVAE) using data from multiphase modeling that captures the physics of DNAPL infiltration. The trained CVAE network was used in SZA inversion to obtain an improved prior DNAPL saturation field, instead of the typical stationary prior covariances. We then integrated the CVAE network into an iterative ensemble smoother (ES), to formulate a joint inversion framework. To overcome difficulties from limited/sparse data, we incorporated hydrogeological and geophysical datasets in the proposed inversion framework. To evaluate the performance of our method, we conducted numerical experiments in a hypothetical heterogeneous aquifer with an intricate SZA. The results show that the CVAE was an effective and efficient parameterization method which can capture the DNAPL infiltration patterns better than a Gaussian prior. The improved prior, combined with multisource datasets, can result in better resolution, and overall improved SZA characterization. In contrast to the standard ES method, the proposed framework reconstructed the SZA more accurately. We also demonstrated that DNAPL depletion behavior and dissolved concentration profiles can be predicted accurately using the estimated SZA.

关键词： convolutional variational autoencoder deep‐ learning parameterization ensemble smoother DNAPL source zone characterization joint hydrogeophysical inversion

来源：评论

学校读者我要写书评

暂无评论

Examining the Size of the Latent Space of convolutional variational autoencoders Trained With Spectral Topographic Maps of EEG Frequency Bands

引用

IEEE ACCESS 2022年 10卷 107575-107586页

作者： Ahmed, Taufique Longo, Luca Technol Univ Dublin Sch Comp Sci Artificial Intelligence & Cognit Load Res Lab Dublin D07 H6K8 7 Ireland

Dimensionality reduction and the automatic learning of key features from electroencephalographic (EEG) signals have always been challenging tasks. variational autoencoders (VAEs) have been used for EEG data generation and augmentation, denoising, and automatic feature extraction. However, investigations of the optimal shape of their latent space have been neglected. This research tried to understand the minimal size of the latent space of convolutional VAEs, trained with spectral topographic EEG head maps of different frequency bands, that leads to the maximum reconstruction capacity of the input and maximum utility for classification tasks. Head maps are generated employing a sliding window technique with a 125ms shift. Person-specific convolutional VAEs are trained to learn latent spaces of varying dimensions while a dense neural network is trained to investigate their utility on a classification task. The empirical results suggest that when VAEs are deployed on spectral topographic maps with shape 32 x 32, deployed for 32 electrodes from 2 seconds cerebral activity, they were capable of reducing the input up to almost 99%, with a latent space of 28 means and standard deviations. This did not compromise the salient information, as confirmed by a structural similarity index, and mean squared error between the input and reconstructed maps. Additionally, along the 28 means maximized the utility of latent spaces in the classification task, with an average 0.93% accuracy. This study contributes to the body of knowledge by offering a pipeline for effective dimensionality reduction of EEG data by employing convolutional variational autoencoders.

关键词： Electroencephalography convolutional variational autoencoder latent space deep learning frequency bands spectral topographic maps and neural networks

来源：评论

学校读者我要写书评

暂无评论

Evolving Deep convolutional variational autoencoders for Image Classification

引用

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION 2021年第5期25卷 815-829页

作者： Chen, Xiangru Sun, Yanan Zhang, Mengjie Peng, Dezhong Sichuan Univ Coll Comp Sci Chengdu 610065 Peoples R China Sichuan Eface Technol Co Ltd Chengdu 610093 Peoples R China Victoria Univ Wellington Sch Engn & Comp Sci Wellington 6140 New Zealand Sichuan Univ Coll Comp Sci Machine Intelligence Lab Chengdu 610065 Peoples R China Shenzhen Peng Cheng Lab Shenzhen 518052 Peoples R China Chengdu Sobey Digital Technol Co Ltd Chengdu 610041 Peoples R China

variational autoencoders (VAEs) have demonstrated their superiority in unsupervised learning for image processing in recent years. The performance of the VAEs highly depends on their architectures, which are often handcrafted by the human expertise in deep neural networks (DNNs). However, such expertise is not necessarily available to each of the end users interested. In this article, we propose a novel method to automatically design optimal architectures of VAEs for image classification, called evolving deep convolutional VAE (EvoVAE), based on a genetic algorithm (GA). In the proposed EvoVAE algorithm, the traditional VAEs are first generalized to a more generic and asymmetrical one with four different blocks, and then a variable-length gene encoding mechanism of the GA is presented to search for the optimal network depth. Furthermore, an effective genetic operator is designed to adapt to the proposed variable-length gene encoding strategy. To verify the performance of the proposed algorithm, nine variants of AEs and VAEs are chosen as the peer competitors to perform the comparisons on MNIST, street view house numbers, and CIFAR-10 benchmark datasets. The experiments reveal the superiority of the proposed EvoVAE algorithm, which wins 21 times out of the 24 comparisons and outperforms the best competitors by 1.39%, 14.21%, and 13.03% on the three benchmark datasets, respectively.

关键词： Computer architecture Encoding Task analysis Approximation algorithms Training Genetic algorithms Computer science convolutional variational autoencoder evolving deep learning genetic algorithm (GA) neural architecture search (NAS)

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

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

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：