检索结果-内蒙古大学图书馆

A multi-scale convolutional auto-encoder and its application in fault diagnosis of rolling bearings

Journal of Southeast University(English Edition) 2019年第4期35卷 417-423页

作者： Ding Yunhao Jia Minping School of Mechanical Engineering Southeast UniversityNanjing 211189China

Aiming at the difficulty of fault identification caused by manual extraction of fault features of rotating machinery,a one-dimensional multi-scale convolutional auto-encoder fault diagnosis model is proposed,based on the standard convolutional *** this model,the parallel convolutional and deconvolutional kernels of different scales are used to extract the features from the input signal and reconstruct the input signal;then the feature map extracted by multi-scale convolutional kernels is used as the input of the classifier;and finally the parameters of the whole model are fine-tuned using labeled *** on one set of simulation fault data and two sets of rolling bearing fault data are conducted to validate the proposed *** results show that the model can achieve 99.75%,99.3%and 100%diagnostic accuracy,*** addition,the diagnostic accuracy and reconstruction error of the one-dimensional multi-scale convolutional auto-encoder are compared with traditional machine learning,convolutional neural networks and a traditional convolutional *** final results show that the proposed model has a better recognition effect for rolling bearing fault data.

关键词： fault diagnosis deep learning convolutional auto-encoder multi-scale convolutional kernel feature extraction

来源：评论

学校读者我要写书评

暂无评论

An Unsupervised Classification Method for Flame Image of Pulverized Coal Combustion Based on convolutional auto-encoder and Hidden Markov Model

引用

ENERGIES 2019年第13期12卷 2585-2585页

作者： Qiu, Tian Liu, Minjian Zhou, Guiping Wang, Li Gao, Kai North China Elect Power Univ Beijing Key Lab New Technol & Syst Measuring & Co Beijing 102206 Peoples R China State Grid Liaoning Elect Power Supply Co Ltd Shenyang 110004 Liaoning Peoples R China

Combustion condition monitoring is a fundamental and critical issue that needs to be addressed in the wide-load operation of coal-fired boilers. In this paper, an unsupervised classification framework based on the convolutional auto-encoder (CAE), the principal component analysis (PCA), and the hidden Markov model (HMM) is proposed to monitor the combustion condition with the uniformly spaced flame images, which are collected from the furnace combustion monitoring system. First, CAE is adopted to extract the features from the flame images, which obtain the sparse representations in the images. Then, PCA is applied to project the feature vectors into the orthogonal space for robustness and computation efficiency. Finally, a HMM is built to calculate the corresponding optimal states by learning the temporal behaviors in the compressed representations. A coal combustion adjustment experiment was conducted in a 660 MW opposed-firing boiler, and the sequential 14,400 flame images with three different combustion states were obtained to evaluate the effectiveness of the proposed approach. We tested six different compression dimensions of the latent variable z in the CAE model and ensured that the appropriate compress parameter was 1024. The proposed framework is compared with five other methods: the CAE + Gaussian mixture model (GMM), CAE + Kmean, the CAE + fuzzy c-mean method, CAE + HMM, and the traditional handcraft feature extraction method (TH) + HMM. The results show that the proposed framework has the highest classification accuracy (95.25% for the training samples and 97.36% for the testing samples) and has the best performance in recognizing the semi-stable state (85.67% for the training samples and 77.60% for the testing samples), indicating that the proposed framework is capable of identifying the combustion condition, changing when the combustion deteriorates as the coal feed rate falls.

关键词： flame images convolutional auto-encoder hidden Markov model unsupervised classification

来源：评论

学校读者我要写书评

暂无评论

A data-driven robotic Chinese calligraphy system using convolutional auto-encoder and differential evolution

引用

KNOWLEDGE-BASED SYSTEMS 2019年 182卷 104802-000页

作者： Gao, Xingen Zhou, Changle Chao, Fei Yang, Longzhi Lin, Chih-Min Xu, Tao Shang, Changjing Shen, Qiang Xiamen Univ Sch Informat Sci & Engn Cognit Sci Dept Xiamen Fujian Peoples R China Aberystwyth Univ Inst Math Phys & Comp Sci Aberystwyth Dyfed Wales Northumbria Univ Dept Comp & Informat Sci Newcastle Upon Tyne Tyne & Wear England Yuan Ze Univ Dept Elect Engn Taoyuan Taiwan

The Chinese stroke evaluation and generation systems required in an autonomous calligraphy robot play a crucial role in producing high-quality writing results with good diversity. These systems often suffer from inefficiency and non-optima despite of intensive research effort investment by the robotic community. This paper proposes a new learning system to allow a robot to automatically learn to write Chinese calligraphy effectively. In the proposed system, the writing quality evaluation subsystem assesses written strokes using a convolutional auto-encoder network (CAE), which enables the generation of aesthetic strokes with various writing styles. The trained CAE network effectively excludes poorly written strokes through stroke reconstruction, but guarantees the inheritance of information from well-written ones. With the support of the evaluation subsystem, the writing trajectory model generation subsystem is realized by multivariate normal distributions optimized by differential evolution (DE), a type of heuristic optimization search algorithm. The proposed approach was validated and evaluated using a dataset of nine stroke categories: high-quality written strokes have been resulted with good diversity which shows the robustness and efficacy of the proposed approach and its potential in autonomous action-state space exploration for other real-world applications. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Robotic Chinese calligraphy Data-driven evaluation model convolutional auto-encoder Differential evolution

来源：评论

学校读者我要写书评

暂无评论

Compressed Sensing via a Deep convolutional auto-encoder 33

Compressed Sensing via a Deep Convolutional Auto-encoder

引用

33rd IEEE International Conference on Visual Communications and Image Processing (IEEE VCIP)

作者： Wu, Hao Zheng, Ziyang Li, Yong Dai, Wenrui Xiong, Hongkai Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China Univ Texas Hlth Sci Ctr Houston Sch Biomed Informat Houston TX 77030 USA

ISBN: (纸本)9781538644584

The nonlinear recovery is not promising in accuracy and speed, which limits the practical usage of compressed sensing (CS). This paper proposes a deep learning-based CS framework which leverages a deep convolutional auto-encoder for image sensing and recovery. The utilized auto-encoder architecture consists of three components: the fully convolutional network acts as an adaptive measurement matrix generator in the encoder;while in the decoder, the deconvolution network and refined reconstruction network are learned for intermediate and final recovery, respectively. Different from most previous work focusing on the block-wise manner to reduce implementation cost but result in blocky artifacts, our adaptive measurement matrix is applicable to any size of scene image and the decoder network reconstructs the whole image efficiently without any blocky artifacts. Moreover, dense connectivity is leveraged to combine multi-level features and alleviate the vanishing-gradient problem in the refined reconstruction network which boosts the performance on image recovery. Compared to the state-of-the-art methods, our algorithm improves more than 0.8 dB in average PSNR.

关键词： Compressed sensing Adaptive measurement matrix convolutional auto-encoder Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Application of a Hybrid Model Based on a convolutional auto-encoder and convolutional Neural Network in Object-Oriented Remote Sensing Classification

引用

ALGORITHMS 2018年第1期11卷 9-9页

作者： Cui, Wei Zhou, Qi Zheng, Zhendong Wuhan Univ Technol Resource & Environm Engn Coll Wuhan 430070 Hubei Peoples R China

Variation in the format and classification requirements for remote sensing data makes establishing a standard remote sensing sample dataset difficult. As a result, few remote sensing deep neural network models have been widely accepted. We propose a hybrid deep neural network model based on a convolutional auto-encoder and a complementary convolutional neural network to solve this problem. The convolutional auto-encoder supports feature extraction and data dimension reduction of remote sensing data. The extracted features are input into the convolutional neural network and subsequently classified. Experimental results show that in the proposed model, the classification accuracy increases from 0.916 to 0.944, compared to a traditional convolutional neural network model;furthermore, the number of training runs is reduced from 40,000 to 22,000, and the number of labelled samples can be reduced by more than half, all while ensuring a classification accuracy of no less than 0.9, which suggests the effectiveness and feasibility of the proposed model.

关键词： remote sensing classification object-oriented convolutional auto-encoder convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

HIGH RESOLUTION MAPPING OF VEGETATION BIODIVERSITY BY HYPERSPECTRAL IMAGES AND convolutional autoencoderS

HIGH RESOLUTION MAPPING OF VEGETATION BIODIVERSITY BY HYPERS...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Nicol, Giovanni Monaco, Manilo Masci, Olimpia Cimino, Mario G. C. A. Natl Res Council Italy Inst Appl Math Bari Italy Italian Space Agcy Matera Italy DIAN Srl Matera Italy Univ Pisa Dept Informat Engn Pisa Italy

ISBN: (纸本)9798350360332;9798350360325

A methodology is presented to map the vegetation biodiversity based on the hypothesis of the spectral variation (SV) which has been proposed to assess the forest biodiversity by means of Earth Observation (EO) data. Hyperspectral data acquired by the PRecursore Iperspettrale della Missione Applicativa (PRISMA) mission of the Italian Space Agency to spectral signature with a high spectral resolution. The NDVI is computed from PRISMA data and used to identify pixels corresponding to vegetation cover. The spectral signatures at those pixels are then clusterized using the convolutional autoenconders technique and the final map with the location of pixels belonging to the different classes is produce. The methodology is applied to assess the vegetation biodiversity in National Parks of Gargano, Alta Murgia, Cilento-Vallo di Diano-Alburni, Appennino Lucano Val D'Agri Lagonegrese and Pollino, all located in Southern Italy.

关键词： Vegetation biodiversity Spectral diversity hyperspectral images PRISMA convolutional auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A Novel Zero-Shot Real World Spatio-Temporal Super-Resolution (ZS-RW-STSR) Model for Video Super-Resolution

引用

IEEE ACCESS 2024年 12卷 123969-123984页

作者： Shukla, Ankit Upadhyay, Avinash Sharma, Manoj Saini, Anil Fatema, Nuzhat Malik, Hasmat Afthanorhan, Asyraf Hossaini, Mohammad Asef Bennett Univ Dept Elect & Commun Engn Greater Noida 208019 India CSIR CEERI Pilani 333031 India Univ Teknol Malaysia Fac Management Johor Baharu 81310 Malaysia Univ Teknol Malaysia Dept Elect Power Engn Faulty Elect Engn Johor Baharu 81310 Malaysia Graphic Era Dept Elect Engn Dehra Dun 248002 India Univ Sultan Zainal Abidin UniSZA Artificial Intelligence Islamic Civilizat & Sustai Kuala Nerus 21300 Terengganu Malaysia Univ Sultan Zainal Abidin UniSZA Operat Res & Management Sci Kuala Nerus 21300 Terengganu Malaysia Badghis Univ Dept Phys Badghis 3351 Afghanistan

Super-resolution (SR) of the degraded and real low-resolution (LR) video remains a challenging problem despite the development of deep learning-based SR models. Most existing state-of-the-art networks focus on getting high-resolution (HR) videos from the corresponding down-sampled LR video but fail in scenarios with noisy or degraded low-resolution video. In this article, a novel real-world "zero-shot" video spatio-temporal SR model, i.e., 3D-Deep convolutional auto-encoder (3D-CAE) guided attention-based deep spatio-temporal back-projection network has been proposed. 3D-CAE is utilized for extracting noise-free features from real low-resolution video and used in the attention-based deep spatio-temporal back-projection network for clean, high-resolution video reconstruction. In the proposed framework, the denoising loss of low-resolution video with high-resolution video reconstruction loss is jointly used in an end-to-end manner with a zero-shot setting. Further, Meta-learning is used to initialize the weights of the proposed model to take advantage of learning on the external dataset with internal learning in a zero-shot environment. To maintain the temporal coherency, we have used the Motion Compensation Transformer (MCT) for motion estimation and the Sub-Pixel Motion Compensation (SPMC) layer for motion compensation. We have evaluated the performance of our proposed model on REDS and Vid4 Dataset. The PSNR value of our model is 25.13 dB for the RealVSR dataset, which is 0.72 dB more than the next-best performing model, EAVSR+. For MVSR4x, our model provides 24.61 db PSNR, 0.67 dB more than the EAVSR+ model. Experimental results demonstrate the effectiveness of the proposed framework on degraded and noisy real low-resolution video compared to the existing methods. Furthermore, an ablation study has been conducted to highlight the contribution of 3D-CAE and attention layer to the overall network performance.

关键词： Superresolution Degradation Computational modeling Adaptation models Image reconstruction Three-dimensional displays Zero-shot learning Encoding convolutional neural networks Zero-shot super-resolution convolutional auto-encoder

来源：评论

学校读者我要写书评

暂无评论

A joint deep learning model for bearing fault diagnosis in noisy environments

引用

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY 2024年第7期38卷 3265-3281页

作者： Ji, Min Chu, Changsheng Yang, Jinghui Shanghai Polytech Univ Sch Intelligent Mfg & Control Engn Shanghai 201209 Peoples R China Shanghai Polytech Univ Inst Artificial Intelligence Sch Comp & Informat Engn Shanghai 201209 Peoples R China

In practical engineering environments, rolling bearing vibration signal is often interfered by strong noise, which negatively affects the diagnostic accuracy of intelligent diagnosis models. To solve the above problem, a fault diagnosis model (MDCAE-CACNN) that fuses a multi-scale dilated convolutional auto-encoder (MDCAE) and a channel attention-based convolutional neural network (CACNN) is proposed. First, the MDCAE model is used to capture the feature information of different time scales in rolling bearing vibration signal by using convolutional kernels with different receptive field sizes. Through unsupervised learning, the noise is removed to obtain high-quality reconstructed signals. Then, the fault features in the reconstructed signal are effectively extracted by CACNN model and the fault type is accurately diagnosed. The experimental results show that the proposed MDCAE-CACNN model exhibits remarkable improvements in fault diagnosis accuracy and effectiveness. Additionally, it showcases high levels of precision, robustness, and generalization ability.

关键词： Bearing fault diagnosis Channel attention convolutional auto-encoder convolutional neural network Multi-scale dilated convolution

来源：评论

学校读者我要写书评

暂无评论

Video prediction for driving scenes with a memory differential motion network model

引用

APPLIED INTELLIGENCE 2023年第4期53卷 4784-4800页

作者： Li, Chenming Chen, Xiuhong Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi 214122 Jiangsu Peoples R China Jiangnan Univ Jiangsu Key Lab Media Design & Software Technol Wuxi 214122 Jiangsu Peoples R China

Accurate video prediction is critical for human drivers and self-driving cars to make informed decisions. To overcome the limitations of existing deep learning-based video prediction methods in driving scenes, such as inaccurate relative position prediction, high latency, and blurred multi-frame image prediction, we propose a Memory Differential Motion Network (MDMNet) model with a convolutional auto-encoder and a spatiotemporal information learning module, based on an improved Memory In Memory Network (MIM). One prominent characteristic of this newly constructed model is that in each time step, it can learn richer spatiotemporal representation features in each frame, and each layer computes the attention weight of the global spatiotemporal information collected, recalling and focusing on the crucial component. First, inspired by the notion of inter-frame differentiation, the network model incorporates motion filters and differential operations inside the unit, which makes it easier to extract the complex relative motion changes and trends of multiple objects in the scene. Second, an innovative global attention module between pictures and states is implemented to ensure global motion information integrity. Finally, to improve the quality of generated pictures, an adaptive convolutional auto-encoder is created. The MDMNet model outperforms other baseline prediction models in Mean Squared Error (MSE), Mean Absolute Error (MAE), Structural Similarity (SSIM), and Peak Signal to Noise Ratio (PSNR) when tested on D-2-city and BDD100K datasets.

关键词： Video prediction Deep learning convolutional auto-encoder Memory in memory network Spatiotemporal information

来源：评论

学校读者我要写书评

暂无评论

Robust watermarking using diffusion of logo into auto-encoder feature maps

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2023年第29期82卷 45175-45201页

作者： Jamali, Maedeh Karimi, Nader Khadivi, Pejman Shirani, Shahram Samavi, Shadrokh Isfahan Univ Technol Dept Elect & Comp Engn Esfahan *** Iran Seattle Univ Comp Sci Dept Seattle WA 98122 USA McMaster Univ Elect & Comp Engn Dept Hamilton ON Canada

Digital content has grown dramatically in recent years, leading to increased attention to copyright. Image watermarking has been considered one of the most popular methods for copyright protection. With the recent advancements in the application of deep neural networks in image processing, these networks have also been used in image watermarking. Robustness and imperceptibility are two challenging features of watermarking methods that the trade-off between them should be satisfied. In this paper, we propose to use an end-to-end network for watermarking. We use a convolutional neural network (CNN) to control the embedding strength based on the images' content. Dynamic embedding helps the network to have the lowest effect on the visual quality of the watermarked image. Different image processing attacks are simulated as a network layer to improve the robustness of the model. Our method is a blind watermarking approach that replicates the watermark string to create a matrix of the same size as the input image. This helps the network to spread the watermark information in a wider space. Therefore, by removing some parts of the image by attacks, the watermark information can be retrieved from other parts. Using dilation layers is another innovation of the proposed method that helps the watermark spread in the wider neighborhood. This will improve the robustness of the method against image processing attacks during extraction. Instead of diffusing the watermark data into the input image, we inject the data into the feature space and force the network to do this in regions that increase the robustness against various attacks. Having embedding, extraction, and attack layer in an end-to-end network helps increase robustness and imperceptibility. Experimental results show the proposed method's superiority in imperceptibility and robustness compared to the state-of-the-art algorithms.

关键词： Blind watermarking convolutional auto-encoder Dilation layer Robustness Data expanding

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：