检索结果-内蒙古大学图书馆

Domain adaptation network based on hypergraph regularized denoising autoencoder

ARTIFICIAL INTELLIGENCE REVIEW 2019年第3期52卷 2061-2079页

作者： Wang, Xuesong Ma, Yuting Cheng, Yuhu China Univ Min & Technol Sch Informat & Control Engn Xuzhou 221116 Jiangsu Peoples R China

Domain adaptation learning aims to solve the classification problems of unlabeled target domain by using rich labeled samples in source domain, but there are three main problems: negative transfer, under adaptation and under fitting. Aiming at these problems, a domain adaptation network based on hypergraph regularized denoising autoencoder (DAHDA) is proposed in this paper. To better fit the data distribution, the network is built with denoising autoencoder which can extract more robust feature representation. In the last feature and classification layers, the marginal and conditional distribution matching terms between domains are obtained via maximum mean discrepancy measurement to solve the under adaptation problem. To avoid negative transfer, the hypergraph regularization term is introduced to explore the high-order relationships among data. The classification performance of the model can be improved by preserving the statistical property and geometric structure simultaneously. Experimental results of 16 cross-domain transfer tasks verify that DAHDA outperforms other state-of-the-art methods.

关键词： Domain adaptation Hypergraph denoising autoencoder Maximum mean discrepancy

来源：评论

学校读者我要写书评

暂无评论

uDAS: An Untied denoising autoencoder With Sparsity for Spectral Unmixing

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2019年第3期57卷 1698-1712页

作者： Qu, Ying Qi, Hairong Univ Tennessee Adv Imaging & Collaborat Informat Proc Grp Dept Elect Engn & Comp Sci Knoxville TN 37996 USA

Linear spectral unmixing is the practice of decomposing the mixed pixel into a linear combination of the constituent endmembers and the estimated abundances. This paper focuses on unsupervised spectral unmixing where the endmembers are unknown a priori. Conventional approaches use either geometrical-or statistical-based approaches. In this paper, we address the challenges of spectral unmixing with unsupervised deep learning models, in specific, the autoencoder models, where the decoder serves as the endmembers and the hidden layer output serves as the abundances. In several recent attempts, part-based autoencoders have been designed to solve the unsupervised spectral unmixing problem. However, the performance has not been satisfactory. In this paper, we first discuss some important findings we make on issues with part-based autoencoders. By proof of counterexample, we show that all existing part-based autoencoder networks with nonnegative and tied encoder and decoder are inherently defective by making these inappropriate assumptions on the network structure. As a result, they are not suitable for solving the spectral unmixing problem. We propose a so-called untied denoising autoencoder with sparsity, in which the encoder and decoder of the network are independent, and only the decoder of the network is enforced to be nonnegative. Furthermore, we make two critical additions to the network design. First, since denoising is an essential step for spectral unmixing, we propose to incorporate the denoising capacity into the network optimization in the format of a denoising constraint rather than cascading another denoising preprocessor in order to avoid the introduction of additional reconstruction error. Second, to be more robust to the inaccurate estimation of a number of endmembers, we adopt an l(21)-norm on the encoder of the network to reduce the redundant endmembers while decreasing the reconstruction error simultaneously. The experimental results demonstrate that t

关键词： Deep learning denoising autoencoder hyperspectral image (HSI) spectral unmixing

来源：评论

学校读者我要写书评

暂无评论

Transformed denoising autoencoder prior for image restoration

引用

JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 2020年 72卷 102927-102927页

作者： Zhou, Jinjie He, Zhuonan Liu, Xiaodong Wang, Yuhao Wang, Shanshan Liu, Qiegen Nanchang Univ Dept Elect Informat Engn Nanchang 330031 Jiangxi Peoples R China Wuhan Univ Sch Elect Informat Wuhan 430072 Peoples R China Chinese Acad Sci Paul C Lauterbur Res Ctr Biomed Imaging Shenzhen Inst Adv Technol Shenzhen 518055 Peoples R China

Image restoration problem is generally ill-posed, which can be alleviated by learning image prior. Inspired by the considerable performance of utilizing priors in pixel domain and wavelet domain jointly, we propose a novel transformed denoising autoencoder as prior (TDAEP). The core idea behind TDAEP is to enhance the classical denoising autoencoder (DAE) via transform domain, which captures complementary information from multiple views. Specifically, 1-level nonorthogonal wavelet coefficients are used to form 4-channel feature images. Moreover, a 5-channel tensor is obtained by stacking the original image under the pixel domain and 4-channel feature images under the wavelet domain. Then we train the transformed DAE (TDAE) with the 5-channel tensor as the network input. The optimized image prior is obtained based on the trained autoencoder, and it is incorporated into an iterative restoration procedure with the aid of the auxiliary variable technique. The resulting model is affiliationed by proximal gradient descent technique. Numerous experiments demonstrated that the TDAEP outperforms a set of image restoration benchmark algorithms.

关键词： Image restoration denoising autoencoder Pixel domain Wavelet domain

来源：评论

学校读者我要写书评

暂无评论

denoising autoencoder Self-Organizing Map (DASOM)

引用

NEURAL NETWORKS 2018年 105卷 112-131页

作者： Ferles, Christos Papanikolaou, Yannis Naidoo, Kevin J. Univ Cape Town Sci Comp Res Unit Fac Sci ZA-7701 Rondebosch South Africa Univ Cape Town Dept Chem Fac Sci ZA-7701 Rondebosch South Africa Aristotle Univ Thessaloniki Dept Informat Thessaloniki 54124 Greece Univ Cape Town Inst Infect Dis & Mol Med Fac Heath Sci ZA-7701 Rondebosch South Africa

In this report, we address the question of combining nonlinearities of neurons into networks for modeling increasingly varying and progressively more complex functions. A fundamental approach is the use of higher-level representations devised by restricted Boltzmann machines and (denoising) autoencoders. We present the denoising autoencoder Self-Organizing Map (DASOM) that integrates the latter into a hierarchically organized hybrid model where the front-end component is a grid of topologically ordered neurons. The approach is to interpose a layer of hidden representations between the input space and the neural lattice of the self-organizing map. In so doing the parameters are adjusted by the proposed unsupervised learning algorithm. The model therefore maintains the clustering properties of its predecessor, whereas by extending and enhancing its visualization capacity enables an inclusion and an analysis of the intermediate representation space. A comprehensive series of experiments comprising optical recognition of text and images, and cancer type clustering and categorization is used to demonstrate DASOM's efficiency, performance and projection capabilities. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： Unsupervised learning denoising autoencoder Self-organizing map Clustering Visualization

来源：评论

学校读者我要写书评

暂无评论

Wi-Fi DSAR: Wi-Fi based Indoor Localization using denoising Supervised autoencoder 30

Wi-Fi DSAR: Wi-Fi based Indoor Localization using Denoising ...

引用

30th Wireless and Optical Communications Conference (WOCC)

作者： Wang, Yun-Hao Yang, Ta-Wei Chou, Cheng-Fu Chang, Ing-Chau Natl Taiwan Univ Dept Comp Sci & Informat Engn Taipei Taiwan Natl Taiwan Univ Grad Inst Networking & Multimedia Taipei Taiwan Natl Taiwan Univ Informat Technol Off Taipei Taiwan Natl Changhua Univ Educ Dept Comp Sci & Informat Engn Changhua Taiwan

ISBN: (纸本)9781665427722

In recent years, the demand for Wi-Fi has grown exponentially, which has led to the rapid development of indoor positioning services based on Wi-Fi fingerprints. Due to the Received Signal Strength Indicator (RSSI) variation over time, the device heterogeneity, and dynamic changes in the environment, the accuracy and robustness of traditional Wi-Fi fingerprint-based methods usually degrade. To alleviate these issues, we propose an approach based on the denoising supervised autoencoder for regression tasks that we named Wi-Fi DSAR. The idea of Wi-Fi DSAR design is to (a) has strong resistance to the noise in the received Wi-Fi signal, and (b) prevent overfitting the fingerprint database to achieve robustness. We do a performance study by comparing other fingerprint-based works with our Wi-Fi DSAR. All works are evaluated in three open datasets, i.e., DSI, IPIN2016, and IPIN2020, with different area sizes and access point densities. Experimental results demonstrate that compared with existing fingerprint-based methods, our Wi-Fi DSAR is able to reduce the average positioning error by 20% to 50% This is because our Wi-Fi DSAR has both noise immunity and generalization performance.

关键词： indoor localization Wi-Fi fingerprint positioning machine learning RSSI denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Automated Computer-aided Design of Cranial Implants Using a Deep Volumetric Convolutional denoising autoencoder

Automated Computer-aided Design of Cranial Implants Using a ...

引用

World Conference on Information Systems and Technologies (WorldCIST)

作者： Morais, Ana Egger, Jan Alves, Victor Univ Minho Sch Engn Dept Informat Braga Portugal Graz Univ Technol Inst Comp Graph & Vis Graz Austria Univ Minho Algoritmi Ctr Braga Portugal Comp Algorithms Med Lab Graz Austria

ISBN: (纸本)9783030161866;9783030161873

Computer-aided Design (CAD) software enables the design of patient-specific cranial implants, but it often requires of a lot of manual user-interactions. This paper proposes a Deep Learning (DL) approach towards the automated CAD of cranial implants, allowing the design process to be less user-dependent and even less time-consuming. The problem of reconstructing a cranial defect, which is essentially filling in a region in a skull, was posed as a 3D shape completion task and, to solve it, a Volumetric Convolutional denoising autoencoder was implemented using the open-source DL framework PyTorch. The autoencoder was trained on 3D skull models obtained by processing an open-access dataset of Magnetic Resonance Imaging brain scans. The 3D skull models were represented as binary voxel occupancy grids and experiments were carried out for different voxel resolutions. For each experiment, the autoencoder was evaluated in terms of quantitative and qualitative 3D shape completion performance. The obtained results showed that the implemented Deep Neural Network is able to perform shape completion on 3D models of defected skulls, allowing for an efficient and automatic reconstruction of cranial defects.

关键词： Cranial implant Medical imaging Computer-aided Design (CAD) Deep Learning 3D shape completion denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Degradation Indicator Construction Method for Aeroengine Lifetime Estimation based on denoising autoencoder 3

A Degradation Indicator Construction Method for Aeroengine L...

引用

IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC)

作者： Niu Yifan Shao Jingfeng Xian Polytech Univ Sch Management Xian Shaanxi Peoples R China

ISBN: (纸本)9781538662434

Degradation indicator construction is essential for the lifetime estimation process, since it provides useful indicator for lifetime estimation effectively. However, the degradation indicator is hard to constructed because of the complex relationships between various parameters. This paper proposes a degradation indicator construction method for aeroengine based on denoising autoencoder (DAE) algorithm. To make the degradation data can indicate the equipment operation state easily, the spearman correlation was adopted for the process of equipment operating state characterizing. Thus, the data smoothing method was used to smooth the degradation data, in order to make the prediction results of the equipment lifetime more accurate. Moreover, the degradation construction method was verified to predict the aeroengine lifetime by adopting the aeroengine degradation data provide by NASA datasets. The expected results of this construction method for degradation indicator based on parameter fusion has a lower mean-square error.

关键词： denoising autoencoder Lifetime Estimation Aeroengine Degradation Indicator

来源：评论

学校读者我要写书评

暂无评论

DUAL denoising autoencoder FEATURE LEARNING FOR CANCER DIAGNOSIS 18

DUAL DENOISING AUTOENCODER FEATURE LEARNING FOR CANCER DIAGN...

引用

18th IEEE International Conference on Cognitive Informatics and Cognitive Computing (ICCI*CC)

作者： Gao, Yuqing Ng, Wing W. Y. Wang, Ting Kwong, Sam South China Univ Technol Guangdong Prov Key Lab Computat Intelligence & Cy Sch Comp Sci & Engn Guangzhou Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

ISBN: (纸本)9781728114194

Microarray data analysis has emerged as a strong tool for cancer diagnosis. Nevertheless, researches on it are significantly challenging as the microarray datasets are imbalanced and high-dimensional with relatively small sample size. In this paper, we utilized Dual denoising autoencoder Features (DDAF), which integrates two denoising Auto-Encoders (DAE) with different activation function to map the features for both minority and majority classes into a better classification representation. The experimental results on four typical microarray datasets show that the DDAF outperforms the Dual autoencoder Features (DAF) and the Cost-sensitive Oversampling Stacked denoising Auto-Encoder (CO-SDAE), rendering the robust ability for dimensionality reduction and imbalanced classification.

关键词： imbalanced classification denoising autoencoder feature learning

来源：评论

学校读者我要写书评

暂无评论

A denoising autoencoder FOR SPEAKER RECOGNITION. RESULTS ON THE MCE 2018 CHALLENGE 44

A DENOISING AUTOENCODER FOR SPEAKER RECOGNITION. RESULTS ON ...

引用

44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Font, Roberto Biometr Vox SL Murcia Spain

ISBN: (纸本)9781479981311

We propose a denoising autoencoder ( DAE) for speaker recognition, trained to map each individual ivector to the mean of all ivectors belonging to that particular speaker. The aim of this DAE is to compensate for inter-session variability and increase the discriminative power of the ivectors prior to PLDA scoring. We test the proposed approach on the MCE 2018 1st Multi-target speaker detection and identification Challenge Evaluation. This evaluation presents a call-center fraud detection scenario: given a speech segment, detect if it belongs to any of the speakers in a blacklist. We show that our DAE system consistently outperforms the usual LDA + PLDA pipeline, achieving a Top-S EER of 4.33% and Top-1 EER of 6.11% on the evaluation set, which represents a 45.6% error reduction with respect to the baseline system provided by organizers.

关键词： MCE 2018 challenge speaker recognition blacklist detection denoising autoencoder speaker embeddings

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Missing Data Imputation Using Recurrent denoising autoencoder

Multivariate Time Series Missing Data Imputation Using Recur...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Zhang, Jianye Yin, Peng Chinese Acad Sci Joint Engn Res Ctr Hlth Big Data Intelligent Anal Shenzhen Inst Adv Technol Shenzhen Peoples R China Tsinghua Univ Shenzhen Int Grad Sch Dept Comp Sci & Technol Shenzhen Peoples R China

ISBN: (纸本)9781728118673

This paper presents a novel method for imputing missing data of multivariate time series by adapting the Long Short Term-Memory(LSTM) and denoising autoencoder(DAE). Missing data are ubiquitous in many domains;proper imputation methods can improve performance on many tasks. Our method focus on multivariate time series, applying bidirectional LSTM to learn temporal information and DAE to learn correlation between variables, and we combine these two models by using LSTM as the encoder component of DAE. Several real-world datasets, including electroencephalogram(EEG), electromyogram(EMG) and electronic health records(EHRs), are extracted to test the performance of our method. Through simulation studies, we compare the proposed recurrent denoising autoencoder with several baseline imputation methods and demonstrate its effectiveness in both missing data estimation and label prediction after imputation.

关键词： missing data multivariate time series denoising autoencoder

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：