检索结果-内蒙古大学图书馆

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

作者： Fan, Ganghui Ma, Yong Huang, Jun Mei, Xiaoguang Ma, Jiayi Wuhan Univ Elect Informat Sch Wuhan 430072 Peoples R China Wuhan Univ Inst Aerosp Sci & Technol Wuhan 430072 Peoples R China

ISBN: (纸本)9781728176055

autoencoder can not only extract features in an unsupervised manner, but also selects samples out that differs significantly from others. However, autoencoder is sensitive to noise and anomalies during training, and the relationships between pixels are discarded. In order to tackle these problems, we propose a robust graph autoencoder (RGAE) for hyperspectral anomaly detection. To be specific, we first redesign the objective function to encourage the network more robust to noise and anomalies. Meanwhile, a superpixel segmentation-based graph regularization term (SuperGraph) is incorporated into AE to preserve the geometric structure and spatial information simultaneously. Experiments with three real data sets are conducted to evaluate the performance, and the detection results demonstrate that our method outperforms other state-of-the-art hyperspectral anomaly detectors.

关键词： Unsupervised learning anomaly detection hyperspectral imagery autoencoder

来源：评论

学校读者我要写书评

暂无评论

Brain Tissue Microstructure Characterization Using dMRI Based autoencoder Neural-Networks 12th

Brain Tissue Microstructure Characterization Using dMRI Base...

引用

12th International Workshop on Computational Diffusion MRI (CDMRI)

作者： Zucchelli, Mauro Deslauriers-Gauthier, Samuel Deriche, Rachid Univ Cote dAzur INRIA Sophia Antipolis France

ISBN: (纸本)9783030876159;9783030876142

In recent years, multi-compartmental models have been widely used to try to characterize brain tissue microstructure from Diffusion Magnetic Resonance Imaging (dMRI) data. One of the main drawbacks of this approach is that the number of microstructural features needs to be decided a priori and it is embedded in the model definition. However, the number of microstructural features which is possible to obtain from dMRI data given the acquisition scheme is still not clear. In this work, we aim at characterizing brain tissue using autoencoder neural networks in combination with rotation-invariant features. By changing the number of neurons in the autoencoder latent-space, we can effectively control the number of microstructural features that we obtained from the data. By plotting the autoencoder reconstruction error to the number of features we were able to find the optimal trade-off between data fidelity and the number of microstructural features. Our results show how this number is impacted by the number of shells and the b-values used to sample the dMRI signal. We also show how our technique paves the way to a richer characterization of the brain tissue microstructure in-vivo.

关键词： Spherical harmonics Rotation invariant features Neural networks Diffusion MRI autoencoder

来源：评论

学校读者我要写书评

暂无评论

Beets or Cotton? Blind Extraction of Fine Agricultural Classes Using a Convolutional autoencoder Applied to Temporal SAR Signatures

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022年 60卷 1页

作者： Di Martino, Thomas Guinvarc'h, Regis Thirion-Lefevre, Laetitia Koeniguer, Elise Colin Univ Paris Saclay SONDRA Lab Cent Supelec F-91190 Gif Sur Yvette France Univ Paris Saclay ONERA Dept Traitement Informat & Syst F-91123 Palaiseau France

We present a fully unsupervised learning pipeline, which involves both a projection method and a clustering algorithm dedicated to the pixel-wise classification of multitemporal SAR images. We design a Convolutional autoencoder as the method to project our time series onto a lower dimensional latent space, where semantically similar temporal signals are placed close together. The additional use of convolutional layers as feature extraction steps allows us to exploit the sequential nature of time series, exhibiting higher representation performance than fully connected layers. The extracted clusters can encapture different semantic levels to either separate classes or extract outlying temporal signals. The application of this method to crop-types mapping enables the extraction of major crop-types within a scene, without supervision. In a labeled context, this method also allows for the extraction of outlying profiles which can lead to the discovery of mislabeled time series.

关键词： Time series analysis Feature extraction Convolution Synthetic aperture radar Agriculture Task analysis Semantics Agriculture autoencoder machine learning SAR time series unsupervised classification

来源：评论

学校读者我要写书评

暂无评论

A novel autoencoder approach to feature extraction with linear separability for high-dimensional data

引用

PEERJ COMPUTER SCIENCE 2022年 8卷 e1061页

作者： Zheng, Jian Qu, Hongchun Li, Zhaoni Li, Lin Tang, Xiaoming Guo, Fei Chongqing Univ Post & Telecommun Coll Comp Sci & Technol Chongqing Peoples R China Chongqing Univ Posts & Telecommun Coll Automation Chongqing Peoples R China

Feature extraction often needs to rely on sufficient information of the input data, however, the distribution of the data upon a high-dimensional space is too sparse to provide sufficient information for feature extraction. Furthermore, high dimensionality of the data also creates trouble for the searching of those features scattered in subspaces. As such, it is a tricky task for feature extraction from the data upon a high-dimensional space. To address this issue, this article proposes a novel autoencoder method using Mahalanobis distance metric of rescaling transformation. The key idea of the method is that by implementing Mahalanobis distance metric of rescaling transformation, the difference between the reconstructed distribution and the original distribution can be reduced, so as to improve the ability of feature extraction to the autoencoder. Results show that the proposed approach wins the state-of-the-art methods in terms of both the accuracy of feature extraction and the linear separabilities of the extracted features. We indicate that distance metric-based methods are more suitable for extracting those features with linear separabilities from high-dimensional data than feature selection-based methods. In a high-dimensional space, evaluating feature similarity is relatively easier than evaluating feature importance, so that distance metric methods by evaluating feature similarity gain advantages over feature selection methods by assessing feature importance for feature extraction, while evaluating feature importance is more computationally efficient than evaluating feature similarity.

关键词： autoencoder Distance metric Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Collaborative Reflection-Augmented autoencoder Network for Recommender Systems

引用

ACM TRANSACTIONS ON INFORMATION SYSTEMS 2022年第1期40卷 10-10页

作者： Xia, Lianghao Huang, Chao Xu, Yong Xu, Huance Li, Xiang Zhang, Weiguo South China Univ Technol Waihuan Rd East Guangzhou 510006 Guangdong Peoples R China Univ Hong Kong Pokfulam Chow Yei Ching Bldg Hong Kong 999077 Peoples R China Australian Natl Univ Canberra ACT 2600 Australia

As the deep learning techniques have expanded to real-world recommendation tasks, many deep neural network based Collaborative Filtering (CF) models have been developed to project user-item interactions into latent feature space, based on various neural architectures, such as multi-layer perceptron, autoencoder, and graph neural networks. However, the majority of existing collaborative filtering systems are not well designed to handle missing data. Particularly, in order to inject the negative signals in the training phase, these solutions largely rely on negative sampling from unobserved user-item interactions and simply treating them as negative instances, which brings the recommendation performance degradation. To address the issues, we develop a Collaborative Reflection-Augmented autoencoder Network (CRANet), that is capable of exploring transferable knowledge from observed and unobserved user-item interactions. The network architecture of CRANet is formed of an integrative structure with a reflective receptor network and an information fusion autoencoder module. which endows our recommendation framework with the ability of encoding implicit user's pairwise preference on both interacted and non-interacted items. Additionally, a parametric regularization-based tied-weight scheme is designed to perform robust joint training of the two-stage CRANet model. We finally experimentally validate CRANet on four diverse benchmark datasets corresponding to two recommendation tasks, to show that debiasing the negative signals of user-item interactions improves the performance as compared to various state-of-the-art recommendation techniques. Our source code is available at https://***/akaxlh/CRANet.

关键词： Recommender Systems Collaborative Filtering autoencoder

来源：评论

学校读者我要写书评

暂无评论

Model Inspired autoencoder for Unsupervised Hyperspectral Image Super-Resolution

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2022年 60卷 1页

作者： Liu, Jianjun Wu, Zebin Xiao, Liang Wu, Xiao-Jun Jiangnan Univ Jiangsu Prov Engn Lab Pattern Recognit & Computat Wuxi 214122 Jiangsu Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci Nanjing 210094 Peoples R China

This article focuses on hyperspectral image (HSI) super-resolution that aims to fuse a low-spatial-resolution HSI and a high-spatial-resolution multispectral image to form a high-spatial-resolution HSI (HR-HSI). Existing deep learning-based approaches are mostly supervised that rely on a large number of labeled training samples, which is unrealistic. The commonly used model-based approaches are unsupervised and flexible but rely on handcrafted priors. Inspired by the specific properties of model, we make the first attempt to design a model-inspired deep network for HSI super-resolution in an unsupervised manner. This approach consists of an implicit autoencoder network built on the target HR-HSI that treats each pixel as an individual sample. The nonnegative matrix factorization (NMF) of the target HR-HSI is integrated into the autoencoder network, where the two NMF parts, spectral and spatial matrices, are treated as decoder parameters and hidden outputs, respectively. In the encoding stage, we present a pixelwise fusion model to estimate hidden outputs directly and then reformulate and unfold the model & x2019;s algorithm to form the encoder network. With the specific architecture, the proposed network is similar to a manifold prior-based model and can be trained patch by patch rather than the entire images. Moreover, we propose an additional unsupervised network to estimate the point spread function and spectral response function. Experimental results conducted on both synthetic and real datasets demonstrate the effectiveness of the proposed approach.

关键词： Superresolution Spatial resolution Hyperspectral imaging Fuses Decoding Energy resolution Tensors autoencoder hyperspectral image (HSI) nonnegative matrix factorization (NMF) super-resolution unfolding

来源：评论

学校读者我要写书评

暂无评论

Probabilistic occupancy forecasting for risk-aware optimal ventilation through autoencoder Bayesian deep neural networks

引用

BUILDING AND ENVIRONMENT 2022年 219卷 109207页

作者： Zhuang, Chaoqun Choudhary, Ruchi Mavrogianni, Anna Alan Turing Inst Data centr Engn London England Univ Cambridge Dept Engn Energy Efficient Cities Initiat Cambridge England UCL Inst Environm Design & Engn Bartlett Fac Built Environm London England

Ventilation plays a noteworthy role in maintaining a healthy, comfortable and energy-efficient indoor environment and mitigating the risk of aerosol transmission and disease infection (e.g., SARS-COV-2). In most commercial and office buildings, demand-controlled ventilation (DCV) systems are widely utilized to conserve energy based on occupancy. However, as the presence of occupants is often inherently stochastic, accurate occupancy prediction is challenging. This study, therefore, proposes an autoencoder Bayesian Long Short-term Memory neural network (LSTM) model for probabilistic occupancy prediction, taking account of model misspecification, epistemic uncertainty, and aleatoric uncertainty. Performances of the proposed models are evaluated using real data in an educational building at the University of Cambridge, UK. The models trained on data of one open-plan space are used to predict occupant numbers for other spaces (with similar layout and function) in the same building. The probabilistic occupant profiles are then used for estimating optimal ventilation rates for two scenarios (i.e., normal DCV mode for energy conservation and anti-infection mode for virus transmission prevention). Results show that, during the test period, for the 1-h ahead prediction, the proposed model achieved better performance with up to 5.8% mean absolute percentage error reduction than the traditional LSTM model. More flexible alternatives for ventilation can be offered by the proposed risk-aware decision-making schemes serving different purposes under real operation. The findings from this study provide new occupancy forecasting solutions and explore the potential of probabilistic decision making for building ventilation optimization.

关键词： Occupancy prediction autoencoder Bayesian deep neural network Ventilation COVID-19

来源：评论

学校读者我要写书评

暂无评论

A CUDA-Parallelized Fast autoencoder for Highly Efficient Latent Factor Analysis on High-Dimensional and Sparse Matrices from Recommender Systems

A CUDA-Parallelized Fast AutoEncoder for Highly Efficient La...

引用

International Conference on Cyber-physical Social Intelligence (ICCSI)

作者： Luo, Fei Liu, Zhigang Chongqing Univ Posts & Telecommun Sch Comp Sci & Technol Chongqing Peoples R China Univ Chinese Acad Sci Chongqing Sch Chinese Acad Sci Chongqing Inst Green & Intelligent Technol Chongqing Peoples R China

ISBN: (纸本)9781665426213

An autoencoder (AE)-based latent factor analysis model can precisely extract non-linear latent features from a High-dimensional and Sparse (HiDS) matrix from a recommender system. However, it requires prefilling an HiDS matrix's unknown data to achieve its compatibility with a GPU platform, which leads to tremendous consumption of computation and storage. To address this issue, this paper presents a CUDA-Parallelized Fast autoencoder (CPFAE) for highly efficient latent factor analysis on a high-dimensional and sparse matrix from a recommender system. Its main idea is two-fold: a) implementing mini-batch-based weight update in the form of efficient sparse matrix multiplication to train the neural network, and b) implementing an efficient computation model for a compressed sparse matrix to make full use of a GPU platform's computation power. Experimental results on two HiDS matrices from real applications demonstrate that compared with a state-of-the-art AE-based model, CPFAE achieves significant gain in computation and storage efficiency.

关键词： Recommender System Collaborative Filtering GPU Latent Factor Analysis autoencoder Parallelization CUDA

来源：评论

学校读者我要写书评

暂无评论

A Weight-Sharing autoencoder with Dynamic Quantization for Efficient Feature Compression 12

A Weight-Sharing Autoencoder with Dynamic Quantization for E...

引用

12th International Conference on ICT Convergence (ICTC) - Beyond the Pandemic Era with ICT Convergence Innovation

作者： Choi, Ji Sub Kim, Jungrae Ko, Jong Hwan Sungkyunkwan Univ Dept Elect & Comp Engn Suwon South Korea Sungkyunkwan Univ Coll Informat & Commun Engn Suwon South Korea

ISBN: (纸本)9781665423830

Collaborative inference (CI) enhances the inference efficiency of deep neural networks (DNNs) by partitioning a computational workload between an edge device and a cloud platform. Efficient inference using CI requires searching for the optimal partition layer that minimizes the end-to-end inference latency. In addition, the intermediate feature at the partitioned layer should he effectively compressed. However, recent DNNbased feature compression methods require independent models dedicated for each partition point, resulting in significant storage overhead. In this paper, we propose a novel method that efficiently compresses the features from variable partition layers using a single autoencoder. The proposed method incorporates a weight-sharing technique that shares the weights of autoencoders that compress each partition layer. In addition, dynamic bitwidths quantization is supported for flexibility in compression ratio. The experimental results show that the proposed method reduced the required parameter size by 4x compared to the existing independent model based method, while maintaining the accuracy loss within 0.5%.

关键词： Collaborative Inference autoencoder Feature Compression Dynamic Quantization

来源：评论

学校读者我要写书评

暂无评论

DeepStream: autoencoder-Based Stream Temporal Clustering 21

DeepStream: Autoencoder-Based Stream Temporal Clustering

引用

36th Annual ACM Symposium on Applied Computing (SAC)

作者： Harush, Shimon Meidan, Yair Shabtai, Asaf Ben Gurion Univ Negev Dept Software & Informat Syst Engn Beer Sheva Israel

ISBN: (纸本)9781450381048

This paper presents DeepStream, a novel data stream temporal clustering algorithm that dynamically detects sequential and overlapping clusters. DeepStream is tuned to classify contextual information in real time and is capable of coping with a high-dimensional feature space. DeepStream utilizes stacked autoencoders to reduce the dimensionality of unbounded data streams and for cluster representation. This method detects contextual behavior and captures nonlinear relations of the input data, giving it an advantage over existing methods that rely on PCA. We evaluated DeepStream empirically using four sensor and IoT datasets and compared it to five state-of-the-art stream clustering algorithms. Our evaluation shows that DeepStream outperforms all of these algorithms.

关键词： Stream clustering autoencoder Dimensionality reduction Anomaly 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：