检索结果-内蒙古大学图书馆

21st IEEE International Workshop on Signal Processing Advances in Wireless Communications (IEEE SPAWC)

作者： Zhang, Wanqing Li, Shuaichao Cui, Ying Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China

ISBN: (纸本)9781728154787

In this paper, a data-driven approach is proposed to jointly design the common sensing (measurement) matrix and jointly support recovery method for complex signals, using a standard deep auto-encoder for real numbers. The auto-encoder in the proposed approach includes an encoder that mimics the noisy linear measurement process for jointly sparse signals with a common sensing matrix, and a decoder that approximately performs jointly sparse support recovery based on the empirical covariance matrix of noisy linear measurements. The proposed approach can effectively utilize the feature of common support and properties of sparsity patterns to achieve high recovery accuracy, and has significantly shorter computation time than existing methods. We also study an application example, i.e., device activity detection in Multiple-Input Multiple-Output (MIMO)-based grant-free random access for massive machine type communications (mMTC). The numerical results show that the proposed approach can provide pilot sequences and device activity detection with better detection accuracy and substantially shorter computation time than well-known recovery methods.

关键词： Jointly sparse support recovery deep learning auto-encoder activity detection grant-free random access

来源：评论

学校读者我要写书评

暂无评论

Situational Estimation of Sports Broadcasting using a Character Level auto-encoder for Live Tweets

Situational Estimation of Sports Broadcasting using a Charac...

引用

IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT)

作者： Fujimoto, Nodoka Ushiama, Taketoshi Kyushu Univ Grad Sch Design Fukuoka Japan Kyushu Univ Fac Design Fukuoka Japan

ISBN: (纸本)9781665419246

Real-time videos enable people to experience real-world events in real time. However, it is challenging for people to keep watching an event when they are busy and have other activities to carry out. It is therefore crucial to develop a method for supporting the viewers' real-time video viewing effectively. Using sports broadcasting as a representative example of such videos, our goal is to develop a system that detects and automatically estimates the events in sports games that are likely to be of high value to the viewers and notifies them in real time during sports broadcasts. To this end, we propose a general-purpose method that efficiently models situations from small amounts of tweets without using domain-specific knowledge. The effectiveness of the method was verified via experiments by estimating the number of tweets posted from the modeled features of a situation with high accuracy.

关键词： SNS Live Tweet auto-encoder Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Rare Failure Prediction Using an Integrated auto-encoder and Bidirectional Gated Recurrent Unit Network 4

Rare Failure Prediction Using an Integrated Auto-encoder and...

引用

4th International-Federation-of-automatic-Control (IFAC) Workshop on Advanced Maintenance Engineering, Services and Technologies (AMEST)

作者： Dangut, Maren David Skaf, Zakwan Jennions, Ian K. Cranfield Univ Bedford Integrated Vehicle Hlth Management IVHM Ctr Cranfield MK43 0AL Beds England Cranfield Univ Integrated Vehicle Hlth Management IVHM Ctr Bedford MK43 0AL England Higher Coll Technol Mech Engn Dept Abu Dhabi U Arab Emirates

Aircraft fault detection and prediction is a critical element of preventing failures, reducing maintenance costs, and increasing fleet availability. This paper considers a problem of rare failure prediction in the context of aircraft predictive maintenance. It presents a novel approach of predicting extremely rare failures, based on combining two deep learning techniques, auto-encoder (AE) and Bidirectional Gated Recurrent Unit (BGRU) network. AE is modified and trained to detect rare failure, and the result from AE is fed into the BGRU to predict the next occurrence of failure. The applicability of the proposed approach is evaluated using real-world test cases of log-based warning and failure messages obtained from the aircraft central maintenance system fleet database and the records of maintenance history. The proposed AE-BGRU model is compared with other similar deep learning methods, the proposed approach is 25% better in precision, 14% in the recall, and 3% in G-mean. The result also shows robustness in predicting failure within a defined useful period. Copyright (C) 2020 The Authors.

关键词： predictive maintenance machine learning extreme rare failure auto-encoder GRU network aircraft

来源：评论

学校读者我要写书评

暂无评论

Developing a Clustering Structure with Consideration of Cross-Domain Text Classification based on Deep Sparse auto-encoder

Developing a Clustering Structure with Consideration of Cros...

引用

IEEE International Conference on Bioinformatics and Biomedicine (IEEE BIBM)

作者： Guo, Yufan Fei, Rong Zhang, Kuan Tang, Yu Hu, Bo Xian Univ Technol Coll Comp Sci & Engn Xian Peoples R China Beijing Huadian Youkong Technol Co Ltd Beijing Peoples R China

ISBN: (纸本)9781728162157

A Abstract feature dimension and cross-domain classification in text classification may lead to low efficiency of text classification. Therefore, in order to study the specificity of the 2019-novel coronavirus, this paper proposes an improved clustering structure based on deep sparse auto-encoder for cross-domain text classification. In this structure, the word vector model and cosine similarity are used to construct the similarity matrix, and then the deep sparse automatic encoder based on unsupervised learning is used to reduce the dimension and extract the feature structure of complex network, and the k-means clustering method is used for testing. Finally, the results are obtained through mean-shift autonomous classification. The performance of the structure is verified on the data set of the title of the paper. The experimental results show the effectiveness of the structure and the practicability of the paper.

关键词： auto-encoder word2vec Mean shift

来源：评论

学校读者我要写书评

暂无评论

Deep Stacked Sparse auto-encoder based on Patches for Image Classification 12

Deep Stacked Sparse Auto-encoder based on Patches for Image ...

引用

12th International Conference on Machine Vision (ICMV)

作者： Jemel, Intidar Hassairi, Salima Ejbali, Ridha Zaied, Mourad Natl Engn Sch Gabes Res Team Intelligent Machines Gabes 6072 Tunisia

ISBN: (纸本)9781510636446

Image classification is an area where deep learning and especially stacked auto-encoders have really proven their strength. The contributions of this paper lie in the creation of a new classifier to remedy some classification problems. This new method of classification presents a combination of the most used techniques in Deep Learning (DL) and Sparse Coding (SC) in the field of classification. Proposed deep neural networks consist of three stacked auto-encoders and a Softmax used as an outer layer for classification. The first auto-encoder is created from a sparse representation of all images of the dataset. The sparse representation of all images represents the decoder part of the first auto-encoder. Then the transpose of the matrix is applied to get the encoder part. Experiments performed on standard datasets such as ImageNet and the Coil-100 reveal the efficacy of this approach.

关键词： Deep learning Patches auto-encoder Image classification

来源：评论

学校读者我要写书评

暂无评论

Jointly Sparse Signal Recovery via Deep auto-encoder and Parallel Coordinate Descent Unrolling

Jointly Sparse Signal Recovery via Deep Auto-encoder and Par...

引用

IEEE Wireless Communications and Networking Conference (IEEE WCNC)

作者： Li, Shuaichao Zhang, Wanqing Cui, Ying Shanghai Jiao Tong Univ Dept EE Shanghai Peoples R China

ISBN: (纸本)9781728131061

In this paper, combining techniques in compressed sensing, parallel optimization and deep learning, an auto-encoder-based approach is proposed to jointly design the common measurement matrix and jointly sparse signal recovery method for complex sparse signals. The encoder achieves noisy linear compression for jointly sparse signals, with a common measurement matrix. The decoder realizes jointly sparse signal recovery based on an iterative parallel-coordinate descent algorithm which is proposed to solve GROUP LASSO in a parallel manner. In particular, the decoder consists of an approximation part which unfolds (several iterations of) the proposed iterative algorithm to obtain an approximate solution of GROUP LASSO and a correction part which reduces the difference between the approximate solution and the actual jointly sparse signals. To our knowledge, this is the first time that an optimization-based jointly sparse signal recovery method is implemented using a neural network. The proposed approach achieves higher recovery accuracy with less computation time than the classic GROUP LASSO method, and the gain significantly increases in the presence of extra structures in sparse patterns. The common measurement matrix obtained by the proposed approach is also suitable for the classic GROUP LASSO method. We consider an application example, i.e., channel estimation in Multiple-Input Multiple-Output (MIMO)-based grant-free massive access for massive machine-type communications (mMTC). By numerical results, we demonstrate the substantial gains of the proposed approach over GROUP LASSO and AMP when the number of jointly sparse signals is not very large.

关键词： Compressed sensing jointly sparse signal recovery deep learning auto-encoder parallel optimization

来源：评论

学校读者我要写书评

暂无评论

A Fault Detection Method based on Convolutional Gated Recurrent Unit auto-encoder for Tennessee Eastman Process

A Fault Detection Method based on Convolutional Gated Recurr...

引用

Chinese automation Congress (CAC)

作者： Yu, Jianbo Liu, Xing Tongji Univ Sch Mech Engn Shanghai Peoples R China

ISBN: (纸本)9781728176871

Due to the powerful ability of feature learning, deep learning has been widely used in the field of manufacturing process monitoring. This paper proposes a new fault detection method, convolutional gated recurrent unit auto-encoder (CGRU-AE) for feature learning from process signals. CGRU-AE is used to learn the effective features of time series data for fault detection. Two statistics, the T-2 and the squared prediction error (SPE), are generated in the feature space and the residual space of CGRU-AE, respectively. Finally, the feasibility and advantages of CGRU-AE are shown on the Tennessee-Eastman process. The results show that CGRU-AE is capable of learning effective features from complex process variables and outperforms other typical methods.

关键词： Deep learning Fault detection auto-encoder Gated recurrent unit

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Dimension Reduction for Image Classification Using Regularized Convolutional auto-encoder

Unsupervised Dimension Reduction for Image Classification Us...

引用

Computer Vision Conference (CVC)

作者： Xu, Chaoyang Wu, Ling Wang, Shiping Putian Univ Sch Informat Engn Putian 351100 Peoples R China Fuzhou Univ Sch Econ & Management Fuzhou 350116 Fujian Peoples R China Fuzhou Univ Coll Math & Comp Sci Fuzhou 350116 Fujian Peoples R China

ISBN: (纸本)9783030177959;9783030177942

Unsupervised dimension reduction has gained widespread attention. Most of previous work performed poorly on image classification due to taking no account of neighborhood relations and spatial localities. In this paper, we propose the 'regularized convolutional auto-encoder', which is a variant of auto-encoder that uses the convolutional operation to extract low-dimensional representations. Each auto-encoder is trained with cluster regularization terms. The contributions of this work are presented as follows: First, we perform different sized filter convolution in parallel and abstract a low-dimensional representation from images cross scales simultaneously. Second, we introduce a cluster regularized rule on auto-encoders to reduce the classification error. Extensive experiments conducted on six publicly available datasets demonstrate that the proposed method significantly reduces the classification error after dimension reduction.

关键词： Deep learning auto-encoder Convolutional neural network Dimension reduction Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised anomaly detection of the gas turbine operation via convolutional auto-encoder

Unsupervised anomaly detection of the gas turbine operation ...

引用

IEEE International Conference on Prognostics and Health Management (ICPHM)

作者： Lee, Geunbae Jung, Myungkyo Song, Myoungwoo Choo, Jaegul Korea Univ Grad Sch Comp & Informat Technol Seoul South Korea Korea Adv Inst Sci & Technol Grad Sch Artificial Intelligence Daejeon South Korea

ISBN: (纸本)9781728162867

This paper proposes a combination of convolutional neural network and auto-encoder (CAE) for unsupervised anomaly detection of industrial gas turbines. autonomous monitoring systems protect the gas turbines, with the settings unchanged in their lifetime. Those systems can not detect any abnormal operation patterns which potentially risk the equipment after long-term exposure. Recently, machine learning and deep learning models are applied for industries to detect those anomalies under the nominal working range. However, for gas turbine protection, not much deep learning (DL) models are introduced. The proposed CAE detects irregular signals in unsupervised learning by combining a convolutional neural network (CNN) and auto-encoder (AE). CNN exponentially reduces the computational cost and decrease the amount of training data, by its extraction capabilities of essential features in spatial input data. A CAE identifies the anomalies by adapting characteristics of an AE, which identifies any errors larger than usual pre-trained, reconstructed errors. Using the Keras library, we developed an AE structure in one-dimensional convolution layer networks. We used actual plant operation data set for performance evaluation with conventional machine learning (ML) models. Compared to the isolation forest (iforest), k- means clustering ( k- means), and one-class support vector machine (OCSVM), our model accurately predicts unusual signal patterns identified in the actual operation than conventional ML models.

关键词： gas turbine anomaly detection convolution auto-encoder deep learning machine learning unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A novel approach to reconstruction based saliency detection via convolutional neural network stacked with auto-encoder

引用

NEUROCOMPUTING 2019年 349卷 145-155页

作者： Lin, Xinchen Tang, Yang Tianfield, Huaglory Qian, Feng Zhong, Weimin East China Univ Sci & Technol Minist Educ Key Lab Adv Control & Optimizat Chem Proc Shanghai 200237 Peoples R China Glasgow Caledonian Univ Sch Comp Engn & Built Environm Glasgow G4 0BA Lanark Scotland

Visual saliency detection, aimed at the simulation of human visual system (HVS), has drawn wide attention in recent decades. Reconstruction based saliency detection models are established methods for saliency detection, which predict unexpected regions via linear combination or auto-encoder network. However, these models are ineffective in dealing with images due to the loss of spatial information caused by the conversion from images to vectors. In this paper, a novel approach is proposed to solve this problem. The core is a deep reconstruction model, i.e., convolutional neural network for reconstruction stacked with auto-encoder (CNNR for short). On the one hand, the use of CNN is able to directly take two-dimensional data as input rather than having to convert the matrix to a series of vectors as in conventional reconstruction based saliency detection methods. On the other hand, the training process of CNN is augmented with the initialization obtained by an unsupervised learning process of convolutional auto-encoder (CAE). By this way, our CNNR model can be trained on limited labeled data, with the weights of the CNN being meaningfully initialized by CAE instead of random initialization. Performance evaluations are conducted through comprehensive experiments on four benchmark datasets and the comparisons with eight state-of-the-art saliency detection models show that our proposed deep reconstruction model outperforms most of the eight state-of-the-art saliency detection models. (C) 2019 Published by Elsevier B.V.

关键词： Convolutional neural network auto-encoder Deep learning Reconstruction Saliency detection

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：