检索结果-内蒙古大学图书馆

Relation-aware collaborative autoencoder for personalized multiple facet selection

KNOWLEDGE-BASED SYSTEMS 2022年 246卷 1页

作者： Chantamunee, Siripinyo Wong, Kok Wai Fung, Chun Che Murdoch Univ Discipline Informat Technol Perth Australia Walailak Univ Sch Engn & Technol Nakhon Si Thammarat Thailand Walailak Univ Informat Innovat Ctr Excellence Nakhon Si Thammarat Thailand

Collaborative-based personalization has been one of the most successful techniques used in building personalization for recommender systems and facet selection. The technique predicts users' interests based on the preferences of similar people or items. The prediction is usually made on one single group of users or items/facets. However, multiple facet selection creates a different challenge where the prediction needs to be based on the similarity among different groups of users and facets. In conventional collaborative approach, user-facet representation is created from the concatenation of user preferences on each facet. This creates a spared representation which affects the accuracy of the personalized model. It is essential to develop a more suitable representation that effectively represents the collaborative preferences given across multiple facets and a predictive model to estimate the possible preferences across those groups. Multiple facets appear to be correlated to each other and this can be useful for associating the existing preferences. None of the previous works has addressed the issue due to the association of facet relationships. Hence, this paper aims to examine the effectiveness of a new approach that utilizes multiple-facet relationships to associate the collaborative interests across different facets. This study proposes a new collaborative-based personalization model for multiple facet selection, called Relation-aware Collaborative autoencoder (RCAE) Model. A new embedding methodology was introduced for incorporating multiple facet relationships into user-facet interaction. Evaluations based on four real-world datasets demonstrated that the proposed model utilizing facet relationships has achieved significant improvement over the conventional collaborative approach. (C)& nbsp;2022 Elsevier B.V. All rights reserved.

关键词： Multiple facets Personalized facet selection Collaborative-based personalization autoencoder Deep neural network Knowledge graph embedding

来源：评论

学校读者我要写书评

暂无评论

A novel method based on adaptive autoencoder and improved long short-term memory and gated recurrent unit for nuclear radiation measurement and monitoring

引用

MEASUREMENT 2022年 199卷

作者： Liao, Yilin Wang, Wenhai Zhang, Zeyin Zhao, Shunping Niu, Yunlong Liu, Xinggao Zhejiang Univ Coll Control Sci & Engn Hangzhou 310027 Peoples R China Zhejiang Univ Math Dept Hangzhou 310027 Peoples R China Minist Ecol & Environm Radiat Environm Monitoring Technol Ctr Hangzhou 310012 Peoples R China

One way to implement the defense against nuclear threat is based on the measurement and detection of radi-ation. To cope with the problems of low precision and slow warning speed in nuclear radiation monitoring and warning, a novel method based on adaptive autoencoder and improved Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) is proposed. Considering the large amount of redundant information in the nuclear radiation energy spectrum, an adaptive autoencoder network is designed to reduce the dimension of data. In order to overcome the problems of slow training speed of LSTM/GRU and insufficient utilization of internal features of the network, the polynomial combinations are increased, which will help to improve the accuracy on the task. The experiments conducted on data measured in real scenario show that the proposed method has high accuracy and reliability for nuclear radiation monitoring and early warning in the real world event.

关键词： Nuclear radiation measurement Monitoring and warning autoencoder Long Short -Term Memory Gated Recurrent Unit

来源：评论

学校读者我要写书评

暂无评论

Stacked LSTM Sequence-to-Sequence autoencoder with Feature Selection for Daily Solar Radiation Prediction: A Review and New Modeling Results

引用

ENERGIES 2022年第3期15卷 1061页

作者： Ghimire, Sujan Deo, Ravinesh C. Wang, Hua Al-Musaylh, Mohanad S. Casillas-Perez, David Salcedo-Sanz, Sancho Univ Southern Queensland Sch Math Phys & Comp Springfield Qld 4300 Australia Victoria Univ Inst Sustainable Ind & Liveable Cities Melbourne Vic 3122 Australia Southern Tech Univ Management Tech Coll Basrah 61001 Iraq Univ Rey Juan Carlos Dept Signal Proc & Commun Fuenlabrada 28942 Spain Univ Alcala Dept Signal Proc & Commun Alcala De Henares 28805 Spain

We review the latest modeling techniques and propose new hybrid SAELSTM framework based on Deep Learning (DL) to construct prediction intervals for daily Global Solar Radiation (GSR) using the Manta Ray Foraging Optimization (MRFO) feature selection to select model parameters. Features are employed as potential inputs for Long Short-Term Memory and a seq2seq SAELSTM autoencoder Deep Learning (DL) system in the final GSR prediction. Six solar energy farms in Queensland, Australia are considered to evaluate the method with predictors from Global Climate Models and ground-based observation. Comparisons are carried out among DL models (i.e., Deep Neural Network) and conventional Machine Learning algorithms (i.e., Gradient Boosting Regression, Random Forest Regression, Extremely Randomized Trees, and Adaptive Boosting Regression). The hyperparameters are deduced with grid search, and simulations demonstrate that the DL hybrid SAELSTM model is accurate compared with the other models as well as the persistence methods. The SAELSTM model obtains quality solar energy prediction intervals with high coverage probability and low interval errors. The review and new modelling results utilising an autoencoder deep learning method show that our approach is acceptable to predict solar radiation, and therefore is useful in solar energy monitoring systems to capture the stochastic variations in solar power generation due to cloud cover, aerosols, ozone changes, and other atmospheric attenuation factors.

关键词： LSTM network sequence to sequence (Seq2Seq) model autoencoder solar energy monitoring sustainable renewable energy deep learning

来源：评论

学校读者我要写书评

暂无评论

A hybrid autoencoder framework of dimensionality reduction for brain-computer interface decoding

引用

COMPUTERS IN BIOLOGY AND MEDICINE 2022年 148卷 105871-105871页

作者： Ran, Xingchen Chen, Weidong Yvert, Blaise Zhang, Shaomin Zhejiang Univ Qiushi Acad Adv Studies Hangzhou Peoples R China Zhejiang Univ Zhejiang Prov Key Lab Cardiocerebral Vasc Detect Minist Educ Dept Biomed EngnKey Lab Biomed Engn Hangzhou Peoples R China INSERM Grenoble France Univ Grenoble Alpes BrainTech Lab U1205 Grenoble France

Objective: As the scale of neural recording increases, Brain-computer interfaces (BCIs) are restrained by high-dimensional neural features, so dimensionality reduction is required as a preprocess of neural features. In this context, we propose a novel framework based on deep learning to reduce the dimensionality of neural features that are typically extracted from electrocorticography (ECoG) or local field potential (LFP). Approach: A high-performance autoencoder was implemented by chaining convolutional layers to deal with spatial and frequency dimensions with bottleneck long short-term memory (LSTM) layers to deal with the temporal dimension of the features. Furthermore, this autoencoder is combined with a fully connected layer to regularize the training. Main results: By applying the proposed method to two different datasets, we found that this dimensionality reduction method largely outperforms kernel principal component analysis (KPCA), partial least square (PLS), preferential subspace identification (PSID), and latent factor analysis via dynamical systems (LFADS). Besides, the new features obtained by our method can be applied to various BCI decoders, without significant differences in decoding performance. Significance: A novel method is proposed as a reliable tool for efficient dimensionality reduction of neural signals. Its high performance and robustness are promising to enhance the decoding accuracy and long-term stability of online BCI systems based on large-scale neural recordings.

关键词： Dimensionality reduction autoencoder Brain-computer interface Neural decoding

来源：评论

学校读者我要写书评

暂无评论

Detecting Extreme Traffic Events Via a Context Augmented Graph autoencoder

引用

ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY 2022年第6期13卷 101-101页

作者： Hu, Yue Qu, Ao Work, Dan Vanderbilt Univ 1025 16th Ave S Nashville TN 37212 USA

Accurate and timely detection of large events on urban transportation networks enables informed mobility management. This work tackles the problem of extreme event detection on large-scale transportation networks using origin-destination mobility data, which is now widely available. Such data is highly structured in time and space, but high dimensional and sparse. Current multivariate time series anomaly detection methods cannot fully address these challenges. To exploit the structure of mobility data, we formulate the event detection problem in a novel way, as detecting anomalies in a set of time-dependent directed weighted graphs. We further propose a Context augmented Graph autoencoder (Con-GAE) model to solve the problem, which leverages graph embedding and context embedding techniques to capture the spatial and temporal patterns. Con-GAE adopts an autoencoder framework and detects anomalies via semi-supervised learning. The performance of the method is assessed on several city-scale travel-time datasets from Uber Movement, New York taxis, and Chicago taxis and compared to state-of-the-art approaches. The proposed Con-GAE can achieve an improvement in the area under the curve score as large as 0.15 over the second best method. We also discuss real-world traffic anomalies detected by Con-GAE.

关键词： Anomaly detection transportation graph neural network autoencoder

来源：评论

学校读者我要写书评

暂无评论

3-D Poststack Seismic Data Compression With a Deep autoencoder

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷

作者： Schiavon, Ana Paula Ribeiro, Kevyn Navarro, Joao Paulo Vieira, Marcelo Bernardes Cruz e Silva, Pedro Mario Univ Fed Juiz de Fora UFJF Dept Ciencia Comp BR-36036900 Juiz De Fora Brazil NVIDIA BR-04576020 Sao Paulo Brazil

We approach the problem of 3-D poststack seismic data compression by training a model based on a deep autoencoder. Our network architecture is trained to consider the similarity between 3-D seismic sections drawn from one or multiple seismic volumes. A whole seismic volume is compressed with the latent representations of each of its composing volumetric sections. The goal is to compress the seismic data at very low bit rates with high-quality reconstruction. Our model is suitable for training general compressors from multiple seismic surveys or for specialized compression of a single seismic volume. Results show that our method can compress seismic data with extremely low bit rates, below 0.3 bits-per-voxel (bpv) while yielding peak signal-to-noise ratio (PSNR) values over 40 dB.

关键词： Bit rate Data compression Task analysis Image coding Decoding Convolution Training 3-D poststack data autoencoder deep learning seismic data compression

来源：评论

学校读者我要写书评

暂无评论

Model order reduction of building energy simulation models using a convolutional neural network autoencoder

引用

BUILDING AND ENVIRONMENT 2022年第PartB期207卷 108498-108498页

作者： Banihashemi, Farzan Weber, Manuel Lang, Werner Tech Univ Munich Inst Energy Efficient & Sustainable Design & Bldg Munich Germany HM Munich Univ Appl Sci Dept Comp Sci & Math Munich Germany

Building energy simulation (BES) tools are fundamental for predicting energy performance and comfort. However, detailed models are computationally complex and demand high simulation times. These lead to difficulties in parametric runs and numerical optimizations. Performing numerous retrofit scenarios is hardly feasible, especially in multi-zone buildings with complex geometries. This paper introduces a novel approach to model order reduction (MOR) of BES models. The approach utilizes a deep learning-based unsupervised convolutional neural network autoencoder (CNN-AE). The method decomposes complex time series data derived from detailed simulations into lower dimension features. The low dimension representations can be grouped through clustering algorithms to build a reduced-order model (ROM). The approach in this study automatically finds archetype zones of the original model that represent the energy behavior of a group of rooms, and removes redundant ones. The energy demand of the whole building can be estimated through these archetype zones. Our investigation shows that CNN-AE can be efficiently applied to reduce complex building energy simulation models. As proof of concept, a detailed model of a multi-zone campus building with 889 thermal zones is compared to the ROM derived from the CNN-AE. Comprehensive autoencoder hyperparameter training to optimize the accuracy of the model is provided. The ROM supports different purposes, such as energy scenario developments, with a total error of less than 1% compared to the original model, and reduced simulation times by a factor of more than 16.

关键词： Model order reduction Deep learning autoencoder Building energy simulation Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Framework with autoencoder-Based Neural Networks for Fault Prognosis

引用

SENSORS 2022年第24期22卷 9738-9738页

作者： da Rosa, Tiago Gaspar Melani, Arthur Henrique de Andrade Pereira, Fabio Henrique Kashiwagi, Fabio Norikazu de Souza, Gilberto Francisco Martha Salles, Gisele Maria De Oliveira Univ Sao Paulo Polytech Sch Dept Mechatron & Mech Syst Engn BR-05508010 Sao Paulo SP Brazil Univ Nove Julho Informat & Knowledge Management Grad Program BR-01525000 Sao Paulo SP Brazil Co Paranaense Energia COPEL BR-80420170 Curitiba SP Brazil

This paper presents a generic framework for fault prognosis using autoencoder-based deep learning methods. The proposed approach relies upon a semi-supervised extrapolation of autoencoder reconstruction errors, which can deal with the unbalanced proportion between faulty and non-faulty data in an industrial context to improve systems' safety and reliability. In contrast to supervised methods, the approach requires less manual data labeling and can find previously unknown patterns in data. The technique focuses on detecting and isolating possible measurement divergences and tracking their growth to signalize a fault's occurrence while individually evaluating each monitored variable to provide fault detection and prognosis. Additionally, the paper also provides an appropriate set of metrics to measure the accuracy of the models, which is a common disadvantage of unsupervised methods due to the lack of predefined answers during training. Computational results using the Commercial Modular Aero Propulsion System Simulation (CMAPSS) monitoring data show the effectiveness of the proposed framework.

关键词： deep neural networks fault prognosis autoencoder remaining useful life (RUL)

来源：评论

学校读者我要写书评

暂无评论

Perceptual Loss-Constrained Adversarial autoencoder Networks for Hyperspectral Unmixing

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2022年 19卷 1页

作者： Zhao, Min Wang, Mou Chen, Jie Rahardja, Susanto Northwestern Polytech Univ Sch Marine Sci & Technol Xian 710072 Peoples R China

Recently, the use of a deep autoencoder-based method in blind spectral unmixing has attracted great attention as the method can achieve superior performance. However, most autoencoder-based unmixing methods use non-structured reconstruction loss to train networks, leading to the ignorance of band-to-band-dependent characteristics and fine-grained information. To cope with this issue, we propose a general perceptual loss-constrained adversarial autoencoder network for hyperspectral unmixing. Specifically, the adversarial training process is used to update our framework. The discriminate network is found to be efficient in discovering the discrepancy between the reconstructed pixels and their corresponding ground truth. Moreover, the general perceptual loss is combined with the adversarial loss to further improve the consistency of high-level representations. Ablation studies verify the effectiveness of the proposed components of our framework, and experiments with both synthetic and real data illustrate the superiority of our framework when compared with other competing methods.

关键词： Image reconstruction Generators Hyperspectral imaging Convolutional neural networks Training Decoding Loss measurement autoencoder fine structure generative adversarial network (GAN) hyperspectral unmixing perceptual loss

来源：评论

学校读者我要写书评

暂无评论

A TWO-STAGE autoencoder FOR VISUAL ANOMALY DETECTION

A TWO-STAGE AUTOENCODER FOR VISUAL ANOMALY DETECTION

引用

IEEE International Conference on Image Processing (ICIP)

作者： Zhu, Yezhou Wang, Jianzhu Zhang, Jing Li, Qingyong Beijing Jiaotong Univ Beijing Key Lab Traff Data Anal & Min Beijing Peoples R China

ISBN: (纸本)9781665441155

Deep convolutional autoencoder (DCAE) is usually optimized to minimize the difference between the input and the reconstruction, and the reconstruction error has been widely used as an indicator for visual anomaly detection. However, DCAE sometimes can reconstruct anomalies very well and thus may yield misdetections. To tackle this issue, we propose a novel non-symmetrical DCAE, which is trained in a two-stage manner. Specifically, a single RotNet is first trained to serve as encoder. Then, discriminative representations generated by the frozen encoder are used to train two parallel decoders for image reconstruction. Finally, the reconstruction errors obtained by the two decoders are combined as the anomaly score. Massive experiments on three public datasets and one practical industrial dataset demonstrate the superiority of the proposed method among existing reconstruction based methods.

关键词： autoencoder RotNet 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：