检索结果-内蒙古大学图书馆

Deep Learning Representation using autoencoder for 3D Shape Retrieval

NEUROCOMPUTING 2016年 204卷 41-50页

作者： Zhu, Zhuotun Wang, Xinggang Bai, Song Yao, Cong Bai, Xiang Huazhong Univ Sci & Technol Sch Elect Informat & Commun 1037 Luoyu Rd Wuhan 430074 Hubei Province Peoples R China

We study the problem of how to build a deep learning representation for 3D shape. Deep learning has shown to be very effective in variety of visual applications, such as image classification and object detection. However, it has not been successfully applied to 3D shape recognition. This is because 3D shape has complex structure in 3D space and there are limited number of 3D shapes for feature learning. To address these problems, we project 3D shapes into 2D space and use autoencoder for feature learning on the 2D images. High accuracy 3D shape retrieval performance is obtained by aggregating the features learned on 2D images. In addition, we show the proposed deep learning feature is complementary to conventional local image descriptors. By combing the global deep learning representation and the local descriptor representation, our method can obtain the state-of-the-art performance on 3D shape retrieval benchmarks. (C) 2016 Published by Elsevier B.V.

关键词： 3D Shape Matching 3D Shape Retrieval autoencoder Shape Representation

来源：评论

学校读者我要写书评

暂无评论

EANet: Multiscale autoencoder based edge attention network for fluid segmentation from SD-OCT images

引用

INTERNATIONAL JOURNAL OF IMAGING SYSTEMS AND TECHNOLOGY 2023年第3期33卷 909-927页

作者： Pappu, Geetha Pavani Tankala, Sreekar Talabhaktula, Krishna Biswal, Birendra Sankar Fdn Eye Hosp & Inst Dept CQI & Res Visakhapatnam India Gayatri Vidya Parishad Coll Engn A Ctr Med Imaging Studies Dept ECE Visakhapatnam India Sankar Fdn Eye Hosp & Inst Vitreo Retina Dept Visakhapatnam India

Macular edema is a retinal complication that occurs due to the presence of excess fluid between the retinal layers. This might lead to swelling in the retina and cause severe vision impairment if not detected in its early stages. This paper presents a robust Edge Attention network (EANet) for segmenting the different retinal fluids like Intraretinal Fluid (IRF), Subretinal Fluid (SRF), and Pigment Epithelial Detachment (PED) from the Spectral Domain - Optical Coherence Tomography (SD-OCT) images. The proposed method employs a novel image enhancement technique by filtering OCT images using a BM3D (Block Matching and 3D Filtering) filter followed by Contrast Limited Adaptive Histogram Equalization (CLAHE) and a linear filter based on multivariate Taylor series to acquire the edge maps of the OCT images. A novel autoencoder based multiscale attention mechanism is incorporated with EANet that feeds on both the OCT image and edge-enhanced OCT image at every level of the encoder. The proposed network, EANet, has been trained and tested for the segmentation of all three types of fluids on the RETOUCH challenge dataset, and the segmentation of the IRF on the OPTIMA challenge and DUKE DME datasets. The average dice coefficient of IRF, SRF, and PED for the RETOUCH dataset is 0.683, 0.873, and 0.756, respectively, whereas it is 0.805, 0.77, and 0.756 for Cirrus, Spectralis, and Topcon vendors, respectively. The proposed method outperformed all the teams that participated in the OPTIMA challenge on all types of vendor images in terms of dice coefficient. The average dice coefficients of IRF on the OPTIMA and DUKE DME datasets are 0.84 and 0.72, respectively.

关键词： autoencoder edge enhancement macular edema multiscale attention mechanism optical coherence tomography images retinal fluid segmentation

来源：评论

学校读者我要写书评

暂无评论

Coupled Deep autoencoder for Single Image Super-Resolution

引用

IEEE TRANSACTIONS ON CYBERNETICS 2017年第1期47卷 27-37页

作者： Zeng, Kun Yu, Jun Wang, Ruxin Li, Cuihua Tao, Dacheng Xiamen Univ Sch Informat Sci & Engn Dept Comp Sci Xiamen 361005 Peoples R China Hangzhou Dianzi Univ Minist Educ Sch Comp Sci Hangzhou 310018 Zhejiang Peoples R China Hangzhou Dianzi Univ Minist Educ Key Lab Complex Syst Modeling & Simulat Hangzhou 310018 Zhejiang Peoples R China Univ Technol Sydney Ctr Quantum Computat & Intelligent Syst Fac Engn & Informat Technol Ultimo NSW 2007 Australia

Sparse coding has been widely applied to learning-based single image super-resolution (SR) and has obtained promising performance by jointly learning effective representations for low-resolution (LR) and high-resolution (HR) image patch pairs. However, the resulting HR images often suffer from ringing, jaggy, and blurring artifacts due to the strong yet ad hoc assumptions that the LR image patch representation is equal to, is linear with, lies on a manifold similar to, or has the same support set as the corresponding HR image patch representation. Motivated by the success of deep learning, we develop a data-driven model coupled deep autoencoder (CDA) for single image SR. CDA is based on a new deep architecture and has high representational capability. CDA simultaneously learns the intrinsic representations of LR and HR image patches and a big-data-driven function that precisely maps these LR representations to their corresponding HR representations. Extensive experimentation demonstrates the superior effectiveness and efficiency of CDA for single image SR compared to other state-of-the-art methods on Set5 and Set14 datasets.

关键词： autoencoder deep learning single image super-resolution (SR)

来源：评论

学校读者我要写书评

暂无评论

A new investment method with autoencoder: Applications to crypto currencies

引用

EXPERT SYSTEMS WITH APPLICATIONS 2020年 162卷 113730-113730页

作者： Nakano, Masafumi Takahashi, Akihiko GCI Asset Management Chiyoda Ku 10F Chiyoda First Bldg East3-8-1 Nishi Kanda Tokyo 1010065 Japan Univ Tokyo Fac Econ Bunkyo Ku 7-3-1 Hongo Tokyo 1130033 Japan

This paper proposes a novel approach to the portfolio management using an autoencoder. In particular, features learned by an autoencoder with ReLU are directly exploited to portfolio constructions. Since the autoencoder extracts characteristics of data through a non-linear activation function ReLU, its realization is generally difficult due to the non-linear transformation procedure. In the current paper, we solve this problem by taking full advantage of the similarity of ReLU and an option payoff. Especially, this paper shows that the features are successfully replicated by applying so-called dynamic delta hedging strategy. An out of sample simulation with crypto currency dataset shows the effectiveness of our proposed strategy. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： autoencoder Crypto currency Delta hedging Artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Model of MT and MST areas using an autoencoder

引用

PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 2003年第1-4期322卷 531-545页

作者： Katayama, K Ando, M Horiguchi, T Tohoku Univ GSIS Dept Math & Comp Sci Sendai Miyagi 9808579 Japan Tohoku Univ Elect Commun Res Inst Sendai Miyagi 9808577 Japan

We propose a model for a system with middle temporal neurons and medial superior temporal (MST) neurons by using a three-layered autoencoder. Noise effect is taken into account by using the framework of statistical physics. We define a cost function of the autoencoder, from which a learning rule is derived by a gradient descent method, within a mean-field approximation. We find a pair of values of two noise levels at which a minimum value of the cost function is attained. We investigate response properties of the MST neurons to optical flows for various types of motion at the pair of optimal values of two noise levels. We obtain that the response properties of the MST neurons are similar to those obtained from neurophysiological experiments. (C) 2002 Elsevier Science B.V. All rights reserved.

关键词： neural network MT neurons MST neurons optical flow autoencoder learning mean-field approximation

来源：评论

学校读者我要写书评

暂无评论

Pattern discovery in time series using autoencoder in comparison to nonlearning approaches

引用

INTEGRATED COMPUTER-AIDED ENGINEERING 2021年第3期28卷 237-256页

作者： Noering, Fabian Kai-Dietrich Schroeder, Yannik Jonas, Konstantin Klawonn, Frank Volkswagen AG Wolfsburg Germany Univ Potsdam Potsdam Germany Deutsch Bahn AG Berlin Germany Ostfalia Univ Appl Sci Dept Comp Sci Wolfenbuettel Germany Helmholtz Ctr Infect Res Braunschweig Germany

In technical systems the analysis of similar situations is a promising technique to gain information about the system's state, its health or wearing. Very often, situations cannot be defined but need to be discovered as recurrent patterns within time series data of the system under consideration. This paper addresses the assessment of different approaches to discover frequent variable-length patterns in time series. Because of the success of artificial neural networks (NN) in various research fields, a special issue of this work is the applicability of NNs to the problem of pattern discovery in time series. Therefore we applied and adapted a Convolutional autoencoder and compared it to classical nonlearning approaches based on Dynamic Time Warping, based on time series discretization as well as based on the Matrix Profile. These nonlearning approaches have also been adapted, to fulfill our requirements like the discovery of potentially time scaled patterns from noisy time series. We showed the performance (quality, computing time, effort of parametrization) of those approaches in an extensive test with synthetic data sets. Additionally the transferability to other data sets is tested by using real life vehicle data. We demonstrated the ability of Convolutional autoencoders to discover patterns in an unsupervised way. Furthermore the tests showed, that the autoencoder is able to discover patterns with a similar quality like classical nonlearning approaches.

关键词： Time series data mining pattern discovery motif discovery autoencoder unsupervised

来源：评论

学校读者我要写书评

暂无评论

Personalized recommendation with knowledge graph via dual-autoencoder

引用

APPLIED INTELLIGENCE 2022年第6期52卷 6196-6207页

作者： Yang, Yang Zhu, Yi Li, Yun Yangzhou Univ Sch Informat Engn Yangzhou 225009 Jiangsu Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ Hefei 230009 Peoples R China Hefei Univ Technol Sch Comp Sci & Informat Engn Hefei 230009 Peoples R China

In the past decades, personalized recommendation systems have attracted a vast amount of attention and researches from multiple disciplines. Recently, for the powerful ability of feature representation learning, deep neural networks have achieved sound performance in the recommendation. However, most of the existing deep recommendation approaches require a large number of labeled data, which is often expensive and labor-some in applications. Meanwhile, the side information of users and items that can extend the feature space effectively is usually scarce. To address these problems, we propose a Personalized Recommendation method, which extends items' feature representations with Knowledge Graph via dual-autoencoder (short for PRKG). More specifically, we first extract items' side information from open knowledge graph like DBpedia as items' feature extension. Secondly, we learn the low-dimensional representations of additional features collected from DBpedia via the autoencoder module and then integrate the processed features into the original feature space. Finally, the reconstructed features is incorporated into the semi-autoencoder for personalized recommendations. Extensive experiments conducted on several real-world datasets validate the effectiveness of our proposed methods compared to several state-of-the-art models.

关键词： Knowledge graph autoencoder Recommendation systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing water quality prediction with advanced machine learning techniques: An extreme gradient boosting model based on long short-term memory and autoencoder

引用

JOURNAL OF HYDROLOGY 2024年 644卷

作者： Zhang, Kai Wang, Xinyuan Liu, Tianlong Wei, Wenguang Zhang, Fengshan Huang, Mingzhi Liu, Hongbin Nanjing Forestry Univ Jiangsu Coinnovat Ctr Efficient Proc & Utilizat Fo Nanjing 210037 Peoples R China Guangxi Univ Coll Light Ind & Food Engn Guangxi Key Lab Clean Pulp & Papermaking & Pollut Nanning 530004 Peoples R China Shandong Huatai Paper Co Ltd Dongying 257335 Peoples R China Shandong Yellow Triangle Biotechnol Ind Res Inst C Dongying 257399 Peoples R China Western Univ Dept Chem & Biochem Engn London ON N6A 3K7 Canada South China Normal Univ Guangdong Prov Engn Res Ctr Intelligent Low carbon Guangzhou 510006 Peoples R China Nanan SCNU Inst Green & Low carbon Res SCNU NANAN Green & Low carbon Innovat Ctr Quanzhou 362300 Peoples R China

Achieving carbon neutrality in the pulp and paper industry necessitates effectively recycling pulp and papermaking wastewater, where continuous monitoring of effluent quality indices is crucial. This study suggests a novel machine learning-based model named LSTMAE-XGBOOST that integrates the feature extraction capabilities of autoencoder, the sequential feature learning capabilities of LSTM, and the high prediction accuracy of XGBOOST. This model is capable of extracting the complex relationships, non-Gaussian characteristics, and time series features from the papermaking wastewater data, and it demonstrates superior predictive performance. Compared to traditional machine learning models, the proposed model exhibits higher prediction accuracy. Specifically, when contrasted with partial least squares regression, LSTMAE-XGBOOST achieves a 40% increase in R-2 and a 35% reduction in RMSE. Further comparative assessments against other machine learning-based hybrid models with similar structures confirm the superiority of integrating LSTM and XGBOOST within the hybrid model approach. This study contributes a compelling methodology for modeling effluent quality indices, offering significant implications for environmental management in the pulp and paper industry.

关键词： Pulp and papermaking wastewater Machine learning autoencoder LSTM XGBOOST LSTM XGBOOST

来源：评论

学校读者我要写书评

暂无评论

A semisupervised autoencoder-based approach for anomaly detection in high performance computing systems

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2019年 85卷 634-644页

作者： Borghesi, Andrea Bartolini, Andrea Lombardi, Michele Milano, Michela Benini, Luca Univ Bologna DISI Viale Risorgimento 2 I-40123 Bologna Italy Univ Bologna DEI Viale Risorgimento 2 I-40123 Bologna Italy Swiss Fed Inst Technol Integrated Syst Lab Zurich Switzerland

High Performance Computing (HPC) systems are complex machines with heterogeneous components that can break or malfunction. Automated anomaly detection in these systems is a challenging and critical task, as HPC systems are expected to work 24/7. The majority of the current state-of-the-art methods dealing with this problem are Machine Learning techniques or statistical models that rely on a supervised approach, namely the detection mechanism is trained to recognize a fixed number of different states (i.e. normal and anomalous conditions). In this paper a novel semi-supervised approach for anomaly detection in supercomputers is proposed, based on a type of neural network called autoencoder. The approach learns the normal state of the supercomputer nodes and after the training phase can be used to discern anomalous conditions from normal behavior;in doing so it relies only on the availability of data characterizing only the normal state of the system. This is different from supervised methods that require data sets with many examples of anomalous states, which are in general very rare and/or hard to obtain. The approach was tested on a real-life High Performance Computing system equipped with a monitoring infrastructure capable to generate large amount of data describing the system state. The proposed approach definitely outperforms the best current techniques for semi-supervised anomaly detection, with an increase in accuracy detection of around 12%. Two different implementations are discussed: one where each supercomputer node has a specific model and one with a single, generalized model for all nodes, in order to explore the trade-off between accuracy and ease of deployment.

关键词： Anomaly detection High performance computing autoencoder Machine learning

来源：评论

学校读者我要写书评

暂无评论

A distributed source autoencoder of local visual descriptors for 3D reconstruction

引用

PATTERN RECOGNITION LETTERS 2021年 146卷 193-199页

作者： Milani, Simone Univ Padua Dept Informat Engn Via Gradenigo 6-B I-35131 Padua Italy

This paper presents a local descriptor coding scheme for multicamera surveillance and 3D reconstruction embedding an autoencoder into a traditional distributed source coding strategy. The proposed solution permits shifting most of the computational complexity at the decoder/receiver and exploiting the correlation among descriptors of different cameras (thus reducing the coded bit rate) without increasing the inter-device communication load. Experimental results show that the proposed scheme permits obtaining a satisfying accuracy with respect to the most recent solutions while generating a limited bit rate. (c) 2021 Elsevier B.V. All rights reserved.

关键词： Distributed vision networks Distributed source coding autoencoder Local descriptor coding Structure-from-Motion

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：