检索结果-内蒙古大学图书馆

Looseness Identification of Track Fasteners Based on Ultra-Weak FBG Sensing Technology and convolutional autoencoder network

引用

SENSORS 2022年第15期22卷 5653-5653页

作者： Li, Sheng Jin, Liang Jiang, Jinpeng Wang, Honghai Nan, Qiuming Sun, Lizhi Wuhan Univ Technol Natl Engn Res Ctr Fiber Opt Sensing Technol & Net Wuhan 430070 Peoples R China Wuhan Univ Technol Sch Informat Engn Wuhan 430070 Peoples R China Univ Calif Irvine Dept Civil & Environm Engn Irvine CA 92697 USA

Changes in the geological environment and track wear, and deterioration of train bogies may lead to the looseness of subway fasteners. Identifying loose fasteners randomly distributed along the subway line is of great significance to avoid train derailment. This paper presents a convolutional autoencoder (CAE) network-based method for identifying fastener loosening features from the distributed vibration responses of track beds detected by an ultra-weak fiber Bragg grating sensing array. For an actual subway tunnel monitoring system, a field experiment used to collect the samples of fastener looseness was designed and implemented, where a crowbar was used to loosen or tighten three pairs of fasteners symmetrical on both sides of the track within the common track bed area and the moving load of a rail inspection vehicle was employed to generate 12 groups of distributed vibration signals of the track bed. The original vibration signals obtained from the on-site test were converted into two-dimensional images through the pseudo-Hilbert scan to facilitate the proposed two-stage CAE network with acceptable capabilities in feature extraction and recognition. The performance of the proposed methodology was quantified by accuracy, precision, recall, and F1-score, and displayed intuitively by t-distributed stochastic neighbor embedding (t-SNE). The raster scan and the Hilbert scan were selected to compare with the pseudo-Hilbert scan under a similar CAE network architecture. The identification performance results represented by the four quantification indicators (accuracy, precision, recall, and F1-score) based on the scan strategy in this paper were at least 23.8%, 9.5%, 20.0%, and 21.1% higher than those of the two common scan methods. As well as that, the clustering visualization by t-SNE further verified that the proposed approach had a stronger ability in distinguishing the feature of fastener looseness.

关键词： feature identification track fastener looseness distributed vibration convolutional autoencoder network pseudo-Hilbert scan ultra-weak fiber optic Bragg grating

来源：评论

学校读者我要写书评

暂无评论

Mineral Prospectivity Prediction by Integration of convolutional autoencoder network and Random Forest

引用

NATURAL RESOURCES RESEARCH 2022年第3期31卷 1103-1119页

作者： Yang, Na Zhang, Zhenkai Yang, Jianhua Hong, Zenglin Northwestern Polytech Univ Sch Automat Xian 710072 Peoples R China Northwestern Polytech Univ Res Ctr Intelligent Geol Survey Xian 710072 Peoples R China Shaanxi Ctr Mineral Geol Survey Xian 710068 Peoples R China Nat Resources Shaanxi Satellite Applicat Technol Xian 710119 Peoples R China Shaanxi Inst Geol Survey Xian 710054 Peoples R China

The convolutional neural networks used widely in mineral prospectivity prediction usually perform mixed feature extraction for multichannel inputs. This results in redundant features and impacts further improvement of predictive performance. To solve this limitation, this paper utilized convolutional autoencoder networks to mine latent high-level features for each predictor variable in parallel to prevent the mixing of features and to enhance the feature mapping outcomes of each channel. convolutional autoencoder networks, as unsupervised learning methods, can handle input images with high-dimensional features. They can train samples without differences such that the reconstructed outputs can restore inputs as accurately as possible to reduce the extraction of irrelevant feature information. Moreover, convolutional autoencoder networks focus on finding the fewest features for representing all inputs, and the extracted features express internal spatial relations at a high level. It is helpful to improve the performance of metallogenic prediction. Hence, this paper arranged these obtained features into one-dimensional vectors to establish the inputs of classifiers. Through modeling with four classifiers (logistic regression, support vector machine, artificial neural network, and random forest), we achieved different models for mineral prospectivity prediction. According to the comprehensive evaluations, the random forest model outperformed the other models. Taking the prediction of gold deposits in the Fengxian region of Southern Qinling in China as an example, the predictive capability of the proposed integrated method was shown to be effective and reliable. The predicted high-potential areas can provide significant guidance for gold deposit exploration in the study area.

关键词： convolutional autoencoder network Feature extraction Random forest Mineral prospectivity prediction

来源：评论

学校读者我要写书评

暂无评论

Sphere phantom approach to measure MTF of computed tomography system using convolutional autoencoder network

Sphere phantom approach to measure MTF of computed tomograph...

引用

Medical Imaging Conference - Physics of Medical Imaging

作者： Lee, Changwoo Baek, Jongduk Korea Res Inst Stand & Sci Safety Measurement Inst Daejeon South Korea Yonsei Univ Sch Integrated Technol Seoul South Korea Yonsei Univ Yonsei Inst Convergence Technol Seoul South Korea

ISBN: (纸本)9781510640207

Image quality assessment is important task to maintain and improve the imaging system performance, and modulation transfer function (MTF) is widely used as a quantitative metric describing the spatial resolution of an image for fan beam computed tomography (CT) system. In MTF measurement, although fine wire and edge objects are generally used, there are difficulties in precise phantom alignment. To overcome this limitation, a sphere object was considered as an alternative phantom due to spherically symmetric property. However, the sphere phantom is more suitable for measuring 1D MTF along the particular direction than 2D MTF for fan beam CT system. In this work, we proposed a sphere phantom approach to measure whole 2D MTF of fan beam CT system using convolutional autoencoder network. We generated projection data of point and sphere objects, and reconstructed using filtered back-projection (FBP). The reconstructed point image was regarded as an ideal 2D point spread function (PSF). The ideal 2D modulation transfer function (MTF) was calculated by taking Fourier transform of the ideal 2D PSF. To measure 2D MTF, we divided the Fourier transform of reconstructed sphere phantom by that of ideal sphere object. The estimation errors caused by the inverse filtering were corrected using proposed convolutional autoencoder network. After applying the network, the estimated 2D MTF shows a good agreement with the ideal 2D MTF, indicating that the convolutional autoencoder network is effective for measuring 2D MTF of fan beam CT system.

关键词： MTF convolutional autoencoder network fan beam computed tomography system sphere phantom

来源：评论

学校读者我要写书评

暂无评论

Unsupervised seismic data deblending based on the convolutional autoencoder regularization

引用

ACTA GEOPHYSICA 2022年第3期70卷 1171-1182页

作者： Xue, Yaru Chen, Yuyao Jiang, Minhui Duan, Hanting Niu, Libo Chen, Chong China Univ Petr Coll Informat Sci & Engn State Key Lab Petr Resources & Prospecting Beijing 102249 Peoples R China

Simultaneous source technology can provide high-quality seismic data with lower acquisition costs. However, a deblending algorithm is needed to suppress the blending noise. The supervised deep learning methods are effective, but are usually limited by the lack of labels. To solve the problem, we propose an unsupervised deep learning method based on acquisition system. A convolutional autoencoder (CAE) network is employed to predict the deblending results of the input pseudo-deblended data. And then, the deblending results will be re-blended using the given blending operator. The parameters of CAE will be optimized by the difference between re-blended data and input data, which is defined as 'blending loss.' The blending problem is ill-posed but the CAE can be regarded as an implicit regularization term which constrains the solving process to obtain the desire solution. A numerical test on synthetic data demonstrates that the proposed method can converge to correct results and two field data experiments verify the flexibility and effectiveness of our model. The transfer training method is also used to improve model performance.

关键词： Simultaneous source data Deblending Unsupervised learning convolutional autoencoder network

来源：评论

学校读者我要写书评

暂无评论

Automatic classification with an autoencoder of seismic signals on a distributed acoustic sensing cable

引用

COMPUTERS AND GEOTECHNICS 2023年 155卷

作者： Chien, Chih-Chieh Jenkins II, William F. Gerstoft, Peter Zumberge, Mark Mellors, Robert Univ Calif San Diego Scripps Inst Oceanog La Jolla CA 92037 USA

This study probes the association between fluid injection in enhanced geothermal systems and certain kinds of seismicity that may result from hydraulic fracturing occurring at depth using unsupervised machine learning. In April and May 2019, a distributed acoustic sensing borehole array at the Frontier Observatory for Research in Geothermal Energy site near Milford, Utah recorded seismic data during hydraulic injection stimulation of a nearby well. Using an autoencoder, a type of deep neural network, we reduce the dimensionality of spectrograms of the detected signals to a lower-dimensional latent feature space with just nine dimensions. Next, Gaussian mixture model clustering is performed on this latent feature space, assigning each detected signal to one of 7 classes. For each signal class, we examine spatiotemporal distributions of the clustered results and find that total detections exhibit a bimodal distribution with respect to channel depth. The shallow mode occurs between 250 and 500 m, and the deep mode is centered around 750 m. In the temporal distribution, clustering results show the two best-clustered signal classes exhibit weak or no correlation with injection -related activities. More generally, we demonstrate the ability to discern not just when and where signals are detected, but also what kind, thus enabling rapid and targeted data exploration and providing constraints on source mechanisms.

关键词： Distributed acoustic sensing convolutional autoencoder network Gaussian mixture model

来源：评论

学校读者我要写书评

暂无评论

Image Inpainting Based on Improved Deep convolutional Auto-encoder network

引用

Chinese Journal of Electronics 2020年第6期29卷 1074-1084页

作者： QIANG Zhenping HE Libo DAI Fei ZHANG Qinghui LI Junqiu College of Big Data and Intelligent Engineering Southwest Forestry University Information Security College Yunnan Police College

This paper proposes an effective image inpainting method using an improved deep convolutional auto-encoder *** analogy with exiting methods of image inpainting based on auto-decoders,inpainting methods using the deep convolutional auto-encoder networks are significantly more effective in capturing high-level features than classical methods based on ***,the inpainted regions would appear blurry and global *** alleviate the fuzzy problem,we improved the network model by adding skip connections between mirrored layers in encoder and decoder stacks,so that the generative process of the inpainting area can directly use the low-level features information of the processing *** making the inpainted result look both more plausible and consistent with its surrounding contexts,the model is trained with a combination of standard pixel-wise reconstruction loss and two adversarial losses which ensures pixel-accurate and local-global contents *** extensive experimental on the ImageNet and Paris Streetview datasets,we demonstrate qualitatively and quantitatively that our approach performs better than state of the art.

关键词： Image inpainting convolutional autoencoder network Image completion Skip connections

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature extraction with convolutional autoencoder with application to daily stock market prediction

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2021年第16期33卷 e6282-e6282页

作者： Xie, Li Yu, Sheng Shaoguan Univ Sch Informat Sci & Engn Shaoguan 512005 Guangdong Peoples R China

Due to the volatility and noise of the stock market, accurately obtaining the trend of the stock market is a challenging problem, and gets the attention of many researchers and speculators. Recently, convolutional neural network (CNN) has been used to automatically learn effective features and predict stock market trends. In CNN-based methods reported so far, less focus has been paid to time series information of the stock, but is very crucial for stock forecasting. In this study, an unsupervised feature extraction method with convolutional autoencoder (CAE) with application to daily stock market prediction is proposed, which has a higher prediction than traditional models. The proposed method mainly consists of the data processing part, unsupervised feature learning part, and the support vector machine model part. Data processing part includes time series data transform into two-dimensional data and data normalization. CAE network-based unsupervised feature learning is designed by fusing convolution and autoencoder. In order to verify the performance of the model, various initial financial and economic variables of stock indices are chosen for prediction experiments. The experimental results on different stock indices demonstrate a significant improvement in prediction's performance compared with the baseline methods.

关键词： convolutional autoencoder network convolutional neural network stock market prediction support vector machine

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：