检索结果-内蒙古大学图书馆

35th Chinese Control and Decision Conference (CCDC)

作者： Luo, Tao Zhu, Songhao Nanjing Univ Posts & Telecommun Coll Automat & Artificial Intelligence Nanjing Peoples R China

ISBN: (纸本)9798350334722

Cross-domain person re-recognition is very important for the applications of intelligent video surveillance. To further reduce the cross-domain differences, a new multi-branch convolutional auto-encoder based cross-domain person re-recognition network (MCAENet) is here proposed. Firstly, the reconstructed feature map is utilized as an input of the generative model module, and reconstruction loss and divergence loss are utilized to extract domain specific features and unknown domain features;then, the domain invariant feature guidance branch is introduced to enhance the robustness of domain invariant features;finally, identity loss is introduced and combined with the triple loss to constrain the distance between different pedestrians, so as to extract representative features to distinguish different pedestrians. Extensive experimental results demonstrate that the proposed cross-domain person re-recognition method based on convolutional -encoder achieves the best identification accuracy in various environments.

关键词： Person Re-Recognition convolutional auto-encoder Invariant Features Specific Feature

来源：评论

学校读者我要写书评

暂无评论

One-dimensional residual convolutional auto-encoder for fault detection in complex industrial processes

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2022年第18期60卷 5655-5674页

作者： Yu, Jianbo Liu, Xing Tongji Univ Sch Mech Engn 4800 CaoAn Rd Shanghai 201804 Peoples R China

Fault detection and diagnosis have always been the key techniques for safe and reliable operation of industrial processes. However, the high dimension and noise of process variables have brought great challenges to the fault detection model. In recent years, due to the powerful feature extraction ability, deep learning has been widely applied in process fault detection and diagnosis. However, these deep neural networks (DNNs) often need a large amount of label data for supervised training, or show poor performance in learning features under unsupervised-learning condition. This paper proposes a new DNN model, a one-dimension residual convolutional auto-encoder (1DRCAE), where unsupervised learning is used to extract representative features from complex industrial processes. 1DRCAE effectively integrates the one-dimensional convolutional kernel with an auto-encoder and is embedded residual learning block for effective feature extraction from one-dimensional data. The two statistics and squared prediction error are generated in the feature space and residual space of 1DRCAE, respectively. Finally, the feasibility and superiority of 1DRCAE are verified on a simulation process, Tennessee Eastman process, Fed-batch fermentation penicillin process, and a real-life case. The convolutional auto-encoder technique provides a new way for feature learning and fault detection on complex industrial processes.

关键词： Industrial process fault detection deep learning convolutional auto-encoder residual learning

来源：评论

学校读者我要写书评

暂无评论

Spatial Resolution Enhancement Technology of FY-3D MWRI Based on convolutional auto-encoder

Spatial Resolution Enhancement Technology of FY-3D MWRI Base...

引用

2023 Cross Strait Radio Science and Wireless Technology Conference, CSRSWTC 2023

作者： Jiang, Han Hu, Weidong School of Integrated Circuits and Electronics Beijing Institute of Technology Beijing China

ISBN: (纸本)9798350358971

During data collection, the Microwave Radiation Imager (MWRI) on the FY3D satellite is affected by various degradation factors, resulting in varying degrees of reduced spatial resolution of multi-channel data. Irreversible high-frequency information degradation occurs during the degradation process. However, the existing spatial resolution enhancement methods cannot perfectly restore the high-frequency information of the original measurement. In this study, an algorithm based convolutional auto-encoder(CAE) is proposed to improve the image resolution of MWRI and restore high-frequency information. Experimental results on simulated and actual MWRI images have demonstrated the validity and effectiveness of the method. © 2023 IEEE.

关键词： convolutional auto-encoder high-frequency information MWRI spatial resolution

来源：评论

学校读者我要写书评

暂无评论

Residual squeeze-and-excitation convolutional auto-encoder for fault detection and diagnosis in complex industrial processes

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartA期136卷

作者： Yu, Jianbo Li, Shijin Liu, Xing Li, Hao Ma, Mingyan Liu, Peilun You, Lichun Tongji Univ Sch Mech Engn 4800 Caoan Rd Shanghai 201804 Peoples R China COMAC Shanghai Aircraft Mfg Co Ltd Shanghai 201324 Peoples R China State Key Lab Large Elect Drive Syst & Equipment T Tianshui Gansu Peoples R China

Recently, deep learning has attracted increasing attention in process monitoring. However, it is still a big challenge to extract effective features of process data for fault detection and diagnosis (FDD) by using deep learning-based methods. In this study, a novel deep learning-based model, residual squeeze-and-excitation convolutional auto-encoder (RSECAE) is proposed for FDD in complex industrial processes. A hybrid structure that integrates convolution calculation and auto-encoder is proposed to construct multiple convolution layers and deconvolution layers in the encoder and decoder respectively. Thus, RSECAE can learn effective features from the process signals in an unsupervised manner. At the same time, multiple residual squeeze-and-excitation networks (RSENets) are embedded in the deep network, which effectively preserves the critical feature representations of the convolution layer and transmits them to the decoder in the form of residuals. Finally, maximum mean discrepancy (MMD) term is utilized in RSECAE to reduce the distribution difference between the process signals and the learned features. This enables RSECAE to extract effective features with prior distribution information. RSECAE provides a new solution for process FDD for complicated industrial processes. Two industrial cases are adopted to validate the effectiveness of the RSECAE in process FDD. The experimental results demonstrate the effectiveness and superiority of RSECAE in process fault detection and fault diagnosis.

关键词： Complex industrial process Process FDD Deep learning Feature learning convolutional auto-encoder

来源：评论

学校读者我要写书评

暂无评论

convolutional auto-encoder Based Sky Image Prediction Model for Minutely Solar PV Power Forecasting

Convolutional Auto-encoder Based Sky Image Prediction Model ...

引用

IEEE-Industry-Applications-Society Annual Meeting

作者： Chai, Hua Zhen, Zhao Li, Kangping Wang, Fei Dehghanian, Payman Shafie-khah, Miadreza Catalao, Joao P. S. North China Elect Power Univ Dept Elect Engn Baoding 071003 Peoples R China George Washington Univ Dept Elect & Comp Engn Washington DC USA Univ Vaasa Sch Technol & Innovat Vaasa 65200 Finland Univ Porto Fac Engn P-4200465 Porto Portugal INESC TEC P-4200465 Porto Portugal

ISBN: (纸本)9781728171920

The precise minute time scale forecasting of an individual Photovoltaic power station output relies on accurate sky image prediction. To avoid the two deficiencies of traditional digital image processing technology (DIPT) in predicting sky images: relatively limited input spatiotemporal information and linear extrapolation of images, convolutional auto-encoder (CAE) based sky image prediction models are proposed according to the spatiotemporal feature extraction ability of 2D and 3D convolutional layers. To verify the effectiveness of the proposed models, two typical DIPT methods, including particle image velocimetry (PIV) and Fourier phase correlation theory (FPCT) are introduced to build the benchmark models. The results show that the proposed models outperform the benchmark models under different scenarios.

关键词： Solar PV power forecasting minute time scale sky image convolutional auto-encoder spatiotemporal feature

来源：评论

学校读者我要写书评

暂无评论

Image Geo-Site Estimation Using convolutional auto-encoder and Multi-Label Support Vector Machine

引用

INFORMATION 2023年第1期14卷 29页

作者： Jain, Arpit Verma, Chaman Kumar, Neerendra Raboaca, Maria Simona Baliya, Jyoti Narayan Suciu, George Koneru Lakshmaiah Educ Fdn Dept Comp Sci & Engn Vaddeswaram 515001 Andhra Pradesh India Eotvos Lorand Univ Fac Informat Dept Media & Educ Informat H-1053 Budapest Hungary Cent Univ Jammu Dept Comp Sci & IT Jammu 181143 India Univ Politehn Bucuresti Doctoral Sch Splaiul Independentei St 313 Bucharest 060042 Romania Tech Univ Cluj Napoca Fac Bldg Serv Engn C-tin Daicoviciu St 15 Cluj Napoca 400020 Romania ICSI Energy Natl Res & Dev Inst Cryogen & Isotop T Ramnicu Valcea 240050 Romania Cent Univ Jammu Dept Educ Studies Jammu 181143 India R&D Dept Beia Consult Int Bucharest Bucharest 041386 Romania

The estimation of an image geo-site solely based on its contents is a promising task. Compelling image labelling relies heavily on contextual information, which is not as simple as recognizing a single object in an image. An auto-Encode-based support vector machine approach is proposed in this work to estimate the image geo-site to address the issue of misclassifying the estimations. The proposed method for geo-site estimation is conducted using a dataset consisting of 125 classes of various images captured within 125 countries. The proposed work uses a convolutional auto-Encode for training and dimensionality reduction. After that, the acquired preprocessed input dataset is further processed by a multi-label support vector machine. The performance assessment of the proposed approach has been accomplished using accuracy, sensitivity, specificity, and F1-score as evaluation parameters. Eventually, the proposed approach for image geo-site estimation presented in this article outperforms auto-Encode-based K-Nearest Neighbor and auto-Encode-Random Forest methods.

关键词： SVM classification convolutional auto-encoder auto-encoder-KNN algorithm random forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Node-Image CAE: A Novel Embedding Method via convolutional auto-encoder and High-Order Proximities 14th

Node-Image CAE: A Novel Embedding Method via Convolutional A...

引用

14th International Conference on Knowledge Science, Engineering, and Management (KSEM)

作者： Qiao, Di Yang, Wu Wang, Wei Harbin Engn Univ Harbin Heilongjiang Peoples R China

ISBN: (纸本)9783030821364;9783030821357

The network embedding method, which mainly aims to generate low-dimensional embedding vectors for nodes in a network, has received great passion from researchers and provides excellent tools for application and research. Various models have been applied to this field to gain high-quality embedding vectors and got prodigious success, such as Matrix Factorization, Multilayer Perceptron, Recurrent Neural Network, Generative Adversarial Networks, Graph convolutional Network, and so on. However, a very powerful model-convolutional Neural Network, which plays a significant role in Digital Image Processing, Natural Language Processing, etc.-has not been widely used (except whole-graph embedding). CNN is thought inappropriate to embed nodes into vectors because traditional CNN can only work on grid-like data such as images while a graph generally has a irregular structure. And with the development of the embedding method, high-order proximities are gradually found playing a crucial role in exploring the network's underlying structure. However, many existing embedding methods can only preserve fixed-order proximities, limiting the scope of their application. In this paper, we try to explore a viable way to apply CNN on node-embedding task. We first build an image for each node that can flexibly preserve different order proximities and feed them into a variation of the convolutional Neural Network, the convolutional auto-encoder (CAE), to generate embedding vectors. Experiments show that our method outperforms state-of-the-art embedding methods.

关键词： Graph embedding High-order proximity convolutional auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Double JPEG compression detection and localization based on convolutional auto-encoder for image content removal

引用

DIGITAL SIGNAL PROCESSING 2022年第0期123卷 103429-103429页

作者： Rahmati, Mohammad Razzazi, Farbod Behrad, Alireza Islamic Azad Univ Sci & Res Branch Dept Elect & Comp Engn Tehran Iran Shahed Univ Elect Engn Dept Tehran Iran

Due to the widespread prevalence of JPEG images in daily life, their authenticity has often been investigated in detecting the traces caused by double JPEG (DJPEG) compression. This paper presents a novel method of DJPEG compression detection based on deep neural networks. After removing the image con -tent using a convolutional auto-encoder (CAE), we separated the JPEG and DJPEG feature spaces into two aligned and non-aligned scenarios using a convolutional neural network (CNN) in the spatial domain. Besides detecting DJPEG compression for small-sized 64 x 64 image patches, the approach also lets us determine the manipulated regions. The proposed network was evaluated for different input images. Results on the standard raw images dataset (RAISE) demonstrated that the proposed methods outperform previous algorithms, especially in the non-aligned case. If an accurate determination of the first and second JPEG compression quality factors (QFs) is not possible, our algorithm is robust to their perturbations. Compared to one of the best existing methods, we achieved about 65% improvement in relative error reduction in some cases. (C)& nbsp;2022 Elsevier Inc. All rights reserved.

关键词： convolutional auto-encoder convolutional neural network DJPEG compression detection DJPEG localization Image content removal

来源：评论

学校读者我要写书评

暂无评论

Fitbeat: COVID-19 estimation based on wristband heart rate using a contrastive convolutional auto-encoder

引用

PATTERN RECOGNITION 2022年 123卷 108403-108403页

作者： Liu, Shuo Han, Jing Puyal, Estela Laporta Kontaxis, Spyridon Sun, Shaoxiong Locatelli, Patrick Dineley, Judith Pokorny, Florian B. Dalla Costa, Gloria Leocani, Letizia Guerrero, Ana Isabel Nos, Carlos Zabalza, Ana Sorensen, Per Soelberg Buron, Mathias Magyari, Melinda Ranjan, Yatharth Rashid, Zulqarnain Conde, Pauline Stewart, Callum Folarin, Amos A. Dobson, Richard J. B. Bailon, Raquel Vairavan, Srinivasan Cummins, Nicholas Narayan, Vaibhav A. Hotopf, Matthew Comi, Giancarlo Schuller, Bjoern Univ Augsburg EIHW Chair Embedded Intelligence Hlth Care & Well Augsburg Germany Univ Cambridge Dept Comp Sci & Technol Cambridge England Univ Zaragoza Aragon Inst Engn Res I3A IIS Aragon BSICoS Grp Zaragoza Spain Biomat & Nanomed CIBER BNN CIBER Bioengn Madrid Spain Kings Coll London Inst Psychiat Psychol & Neurosci Dept Biostat & Hlth Informat London England Univ Bergamo Dept Engn & Appl Sci Bergamo Italy Med Univ Graz Div Phoniatr Graz Austria Sci Inst Hosp San Raffaele Univ Vita Salute San Raffaele & Expt Neurophysiol Inst Expt Neurol Milan Italy Univ Autonoma Barcelona Hosp Univ Vall dHebron Multiple Sclerosis Ctr Catalonia Cemcat Dept Neurol Neuroimmunol Barcelona Spain Copenhagen Univ Hosp Rigshosp Danish Multiple Sclerosis Ctr Dept Neurol Copenhagen Denmark UCL Inst Hlth Informat London England Janssen Res & Dev LLC Titusville NJ USA Kings Coll London Inst Psychiat Psychol & Neurosci Dept Psychol Med London England South London & Maudsley Natl Hlth Serv Fdn Trust London England Univ Vita Salute San Raffaele Casa Cura Privata Policlin Milan Italy Imperial Coll London GLAM Grp Language Audio & Mus London England RADAR CNS Consortium London England

This study proposes a contrastive convolutional auto-encoder (contrastive CAE), a combined architecture of an auto-encoder and contrastive loss, to identify individuals with suspected COVID-19 infection using heart-rate data from participants with multiple sclerosis (MS) in the ongoing RADAR-CNS mHealth research project. Heart-rate data was remotely collected using a Fitbit wristband. COVID-19 infection was either confirmed through a positive swab test, or inferred through a self-reported set of recognised symptoms of the virus. The contrastive CAE outperforms a conventional convolutional neural network (CNN), a long short-term memory (LSTM) model, and a convolutional auto-encoder without contrastive loss (CAE). On a test set of 19 participants with MS with reported symptoms of COVID-19, each one paired with a participant with MS with no COVID-19 symptoms, the contrastive CAE achieves an unweighted average recall of 95 . 3% , a sensitivity of 100% and a specificity of 90 . 6% , an area under the receiver operating characteristic curve (AUC-ROC) of 0.944, indicating a maximum successful detection of symptoms in the given heart rate measurement period, whilst at the same time keeping a low false alarm rate. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： COVID-19 Respiratory tract infection Anomaly detection Contrastive learning convolutional auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Multi-Branch convolutional auto-encoder Model For Cross-Domain Person Re-Recognition

Multi-Branch Convolutional Auto-Encoder Model For Cross-Doma...

引用

第35届中国控制与决策会议

作者： Tao Luo Songhao Zhu College of Automation and Artificial Intelligence Nanjing University of Posts and Telecommunications

Cross-domain person re-recognition is very important for the applications of intelligent video *** further reduce the cross-domain differences,a new multi-branch convolutional auto-encoder based cross-domain person re-recognition network(MCAENet) is here ***,the reconstructed feature map is utilized as an input of the generative model module,and reconstruction loss and divergence loss are utilized to extract domain specific features and unknown domain features;then,the domain invariant feature guidance branch is introduced to enhance the robustness of domain invariant features;finally,identity loss is introduced and combined with the triple loss to constrain the distance between different pedestrians,so as to extract representative features to distinguish different *** experimental results demonstrate that the proposed cross-domain person re-recognition method based on convolutional-encoder achieves the best identification accuracy in various environments.

关键词： Person Re-Recognition convolutional auto-encoder Invariant Features Specific Feature

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：