检索结果-内蒙古大学图书馆

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Giusti, Lorenzo Battiloro, Claudio Di Lorenzo, Paolo Barbarossa, Sergio Sapienza Univ Rome DIAG Dept Via Ariosto 25 I-00185 Rome Italy Sapienza Univ Rome DIET Dept Via Eudossiana 18 I-00184 Rome Italy

ISBN: (纸本)9781665405409

This work aims to propose a novel architecture and training strategy for graph convolutional networks (GCN). The proposed architecture, named autoencoder-Aided GCN (AA-GCN), compresses the convolutional features in an information-rich embedding at multiple hidden layers, exploiting the presence of autoencoders before the point-wise nonlinearities. Then, we propose a novel end-to-end training procedure that learns different graph representations per layer, jointly with the GCN weights and auto-encoder parameters. As a result, the proposed strategy improves the computational scalability of the GCN, learning the best graph representations at each layer in a data-driven fashion. Several numerical results on synthetic and real data illustrate how our architecture and training procedure compares favorably with other state-of-the-art solutions, both in terms of robustness and learning performance.

关键词： Deep learning graph convolutional networks graph signal processing graph learning autoencoder

来源：评论

学校读者我要写书评

暂无评论

GEAE: Gated Enhanced autoencoder based Feature Extraction and Clustering for Customer Segmentation

GEAE: Gated Enhanced Autoencoder based Feature Extraction an...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) / IEEE World Congress on Computational Intelligence (IEEE WCCI) / International Joint Conference on Neural Networks (IJCNN) / IEEE Congress on Evolutionary Computation (IEEE CEC)

作者： Wu, Haotian Wang, Qi Beijing Jiaotong Univ Sch Econ & Management Beijing Peoples R China Northeastern Univ Qinhuangdao Sch Math & Stat Qinhuangdao Peoples R China

ISBN: (数字)9781728186719

ISBN: (纸本)9781728186719

Customer segmentation is a core issue in the customer relationship management community. It provides an important reference for companies to understand customers' needs and develop accurate marketing programs by dividing customers with similar needs into specific categories. With the advent of the era of big data, the recorded data of customer characteristics become more diversified, and the data dimension presents a trend of sharp growth. The relationships among data have become more complicated, and both manual statistical analysis and traditional clustering algorithms have encountered bottlenecks. A kind of work that uses autoencoder to reduce dimensions and then conducts clustering research provides a good solution to this problem. autoencoder can effectively capture nonlinear and complex data features by stacking hidden layers with activation functions. However, the uncontrollability of the encoding-decoding process in autoencoders is neglected in the existing research on autoencoders. To solve this problem, a gated enhanced autoencoder(GEAE) is proposed in this paper. The gating block connection between encoder and decoder is established to make the encoding process guide the decoding process and reduce the uncontrollability of the encoding-decoding process. We verify the validity of the proposed method on a real data set for customer segmentation. GEAE obviously outperforms AE in terms of both reconstruction performance and the effect of downstream clustering tasks. In addition, this research also verifies the importance of selecting the appropriate position of the gating block in GEAE through ablation experiments.

关键词： Customer segmentation Clustering Gating mechanism autoencoder Neural network

来源：评论

学校读者我要写书评

暂无评论

DEEP FEATURE COMPRESSION USING RATE-DISTORTION OPTIMIZATION GUIDED autoencoder 29

DEEP FEATURE COMPRESSION USING RATE-DISTORTION OPTIMIZATION ...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Yamazaki, Meguru Kora, Yuichiro Nakao, Takanori Lei, Xuying Yokoo, Kaoru Fujitsu Ltd Tokyo Japan

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Collaborative intelligence (CI) has been proposed to efficiently utilize computational resources on edge devices over edge-cloud environments. To realize this, a deep neural network (DNN) model is divided into two parts, which are deployed to the edge device and cloud separately so that they can perform DNN inference collaboratively. Feature compression methods have been investigated to reduce the traffic volume between the edge and cloud because the data size of a feature map, which is the output of the edge device in CI, is relatively larger than that of the compressed original image. Although feature compression methods can achieve a good compression rate, the traffic volume is not small enough because the data size of a feature map might exceed that of the original image. Herein, we propose a novel feature compression method that utilizes an autoencoder (AE) to compress the feature map. In image compression, distortion and data size are minimized, whereas in our method, the AE is trained to minimize the prediction error and data size. In this way, the AE can extract only the data needed for the task of the DNN model and considerably reduce the data size while maintaining the prediction accuracy. In performance evaluation, we apply the proposed method to widely used convolutional neural network models: VGG16, ResNet50, and YOLOv3. Our results confirm that the proposed method drastically reduces the traffic volume while utilizing the resources of edge devices in CI. Our proposed method reduces the traffic volume by 62-99%, 16-99%, and 35-53% compared to versatile video coding in each model.

关键词： Feature Compression Collaborative Intelligence autoencoder Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Decomposition of Invariant and Variant Features by Using Convolutional autoencoder 28th

Decomposition of Invariant and Variant Features by Using Con...

引用

28th International Workshop on Frontiers of Computer Vision (IW-FCV)

作者： Ide, Hidenori Fujishige, Hiromu Miyao, Junichi Kurita, Takio Hiroshima Univ Higashihiroshima Japan

ISBN: (纸本)9783031063817;9783031063800

In our brain, the visual information captured by the retina is processed by the two different visual pathways known as ventral stream and the dorsal stream. The ventral stream known as the "what pathway" is involved with object and visual identification and recognition and the dorsal stream known as "where pathway" is involved with processing the object's spatial location relative to the viewer. This means that the human brain decomposes the visual information captured by the retina into the invariant information and the variant information. In this paper, we propose two network architectures based on the convolutional autoencoder in order to decompose the input information into invariant information and variant information. The decomposition of variant and invariant information is realized by decomposing the feature vectors obtained in the hidden layer of the convolutional autoencoder. To extract invariant information, the classifier or the estimator of the invariant image are combined with the convolutional autoencoder. Effectiveness of the proposed architectures are experimentally confirmed by visualizing the extracted feature vectors.

关键词： Invariant feature Variant feature autoencoder Visual pathway Decomposition Character recognition White balance correction

来源：评论

学校读者我要写书评

暂无评论

Student Dropout Prediction using 1D CNN-LSTM with Variational autoencoder Oversampling 8

Student Dropout Prediction using 1D CNN-LSTM with Variationa...

引用

IEEE Latin American Conference on Computational Intelligence (LA-CCI)

作者： Coppo, Eduarda C. Caetano, Rhuan S. de Lima, Leandro M. Krohling, Renato A. LABCIN UFES Vitoria ES Brazil LABCIN UFES PPGI UFES Vitoria ES Brazil

ISBN: (数字)9781665488587

ISBN: (纸本)9781665488587

Student dropout represents a social, resource and time loss for everyone involved. By identifying students with the potential to evade, it is possible to take the necessary measures to prevent that from happening. This paper investigates different techniques for classification using a real students dataset that is multivariate, sequential and imbalanced. To address imbalance, an approach using weighted loss function and an approach using synthetic data generated through a combination of variational autoencoder and the Adaptive Synthetic (ADASYN) technique were investigated. In addition, we propose two models for predicting evasion using LSTM and 1D CNN networks to take advantage of the multivariate sequential property. The experiments showed that the approach only with LSTM architecture in the dynamic module using the preprocessed original dataset and without the use of weighted loss function obtained the best mean sensitivity (0.9676) among the investigated proposals. The LSTM architecture in the dynamic module using the preprocessed original dataset with weighted loss function had better specificity (0.9558) and area under curve (0.9735). Both had the same mean accuracy of 0.9549.

关键词： student dropout prediction imbalance autoencoder LSTM network convolutional network

来源：评论

学校读者我要写书评

暂无评论

Comparison Analysis of Data Augmentation using Bootstrap, GANs and autoencoder 14

Comparison Analysis of Data Augmentation using Bootstrap, GA...

引用

14th International Conference on Knowledge and Smart Technology (KST)

作者： Nakhwan, Mukrin Duangsoithong, Rakkrit Prince Songkla Univ Coll Digital Sci Hat Yai Thailand Prince Songkla Univ Dept Elect Engn Hat Yai Thailand

ISBN: (纸本)9781665400145

In order to improve predictive accuracy for insufficient observations, data augmentation is a well-known and commonly useful technique to increase more samples by generating new data which can avoid data collection problems. This paper presents comparison analysis of three data augmentation methods using Bootstrap method, Generative Adversarial Networks (GANs) and autoencoder for increasing a number of samples. The proposal is applied on 8 datasets with binary classification from repository data websites. The research is mainly evaluated by generating new additional data using data augmentation. Secondly, combining generated samples and original data. Finally, validating performance on four classifier models. The experimental result showed that the proposed approach of increasing samples by autoencoder and GANs achieved better predictive performance than the original data. Conversely, increasing samples by Bootstrap method provided lowest predictive performance.

关键词： Data augmentation Generative Adversarial Networks (GANs) Bootstrap method autoencoder Tabular data

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Shaping for Multidimensional Signals with autoencoder-based End-to-end Learning

Probabilistic Shaping for Multidimensional Signals with Auto...

引用

IEEE Wireless Communications and Networking Conference (IEEE WCNC)

作者： Liu, Xinyue Darwazeh, Izzat Zein, Nader Sasaki, Eisaku UCL Dept Elect & Elect Engn London WC1E 7JE England NEC Europe NEC Labs Europe Ruislip HA4 6QE Middx England NEC Corp Ltd Wireless Access Solut Div 1 Tokyo 2118666 Japan

ISBN: (纸本)9781665442664

This work proposes a system that optimises multidimensional signal transmission, utilising signals with probabilistic shaping designed with the aid of end-to-end learning of an autoencoder-based architecture. For the first time, this work reports bit mapping optimisation for multidimensional signals and applied the newly derived optimised signals to the probabilistic shaping system. The autoencoder employs two neural networks for the transceiver, separated by the embedded channel. The optimisation of the autoencoder configuration is implemented for probabilistic shaping for n-dimensional signals. Specifically, We investigate a 4-dimensional (4D) signal employing 2 successive time slots that has better noise immunity relative to regular 2-dimensional quadrature amplitude modulation (QAM) signals. We propose a new application of autoencoders in communication systems based on 4D signals and apply machine learning to optimise the 4D probabilistic shaping on the basis of receiver signal-to-noise-ratio (SNR). The performance of the optimised probabilistically shaped 4D signals is evaluated in terms of the bit error rate (BER) and mutual information. Simulation results show that the proposed probabilistically shaped 4D signal achieves better BER performance relative to the unshaped 4D and regular 2D QAM. We demonstrate the mutual information of the proposed signal with varying SNR, showing its improved capacity in comparison with other constellations.

关键词： probabilistic shaping end-to-end learning multidimensional modulation autoencoder

来源：评论

学校读者我要写书评

暂无评论

ContrastNet: Unsupervised feature learning by autoencoder and prototypical contrastive learning for hyperspectral imagery classification

引用

NEUROCOMPUTING 2021年 460卷 71-83页

作者： Cao, Zeyu Li, Xiaorun Feng, Yueming Chen, Shuhan Xia, Chaoqun Zhao, Liaoying Zhejiang Univ Coll Elect Engn 38 Zheda Rd Hangzhou 310027 Peoples R China State Grid Jiaxing Power Supply Co Jiaxing 314100 Zhejiang Peoples R China HangZhou Dianzi Univ China Inst Comp Applicat Technol Hangzhou 310018 Peoples R China

Hyperspectral classification is a fundamental problem for applying hyperspectral technology, and unsupervised learning is a promising direction to address the issue. Unsupervised feature learning algorithm extracts representative features, which help efficiently classify the hyperspectral pixels. This paper combines the popular contrastive learning method (prototypical contrastive learning) and the classic representation learning method (autoencoder) to design an unsupervised feature learning network for hyperspectral classification. First, two different encoders are used to extract different features as augmentation function in a contrastive network (ContrastNet). Second, the prototypical contrastive learning method is adopted to train a contrastive network. Third, features extracted by the contrastive network are used for classification. Experiments have proved that our two proposed autoencoder networks show good feature learning capabilities by themselves and the designed contrastive learning network can further learn better representative features from the two modules. The three modules compose an efficient framework for unsupervised feature learning. Our method also performs reasonably fast in the testing phase, which implies that it is applicable in practice under specific conditions. (C) 2021 Elsevier B.V. All rights reserved.

关键词： Unsupervised learning autoencoder Contrastive learning Hyperspectral imagery classification

来源：评论

学校读者我要写书评

暂无评论

An autoencoder with adaptive transfer learning for intelligent fault diagnosis of rotating machinery

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2021年第5期32卷

作者： Tang, Zhi Bo, Lin Liu, Xiaofeng Wei, Daiping Chongqing Univ State Key Lab Mech Transmiss Chongqing 400044 Peoples R China

Under variable working conditions, a problem arises, which is that it is difficult to obtain enough labeled data;to address this problem, an adaptive transfer autoencoder (ATAE) is established to diagnose faults in rotating machinery. First, a data adaptation module, which calculates the maximum mean discrepancy for the network hidden-layer data in reproducing kernel Hilbert space, is introduced to the autoencoder network, thus making the classification model operate under variable working conditions. Variation particle-swarm optimization is then invoked to optimize the data adaptation parameters. Finally, the k-nearest neighbors algorithm, as the classification layer of the network, identifies the state of health of the rotating machinery. The capabilities of the intelligent fault-diagnosis network are verified using vibration signals from a bearing test rig and a gearbox test rig. The experimental results suggest that, compared with state-of-the-art diagnosis methods, the proposed ATAE network can significantly boost diagnostic performance in the absence of target vibration signal labels.

关键词： rotating machinery intelligent fault diagnosis autoencoder transfer learning adaptive optimization

来源：评论

学校读者我要写书评

暂无评论

Signal-to-noise ratio enhancement for Raman spectra based on optimized Raman spectrometer and convolutional denoising autoencoder

引用

JOURNAL OF RAMAN SPECTROSCOPY 2021年第4期52卷 890-900页

作者： Fan, Xian-guang Zeng, Yingjie Zhi, Yu-Liang Nie, Ting Xu, Ying-jie Wang, Xin Xiamen Univ Dept Instrumental & Elect Engn Xiamen 361102 Fujian Peoples R China Xiamen Key Lab Optoelect Transducer Technol Fujian Key Lab Univ & Coll Transducer Technol Xiamen Peoples R China

The signal-noise ratio plays a key role in acquiring plentiful chemical structural information in the Raman spectrometer. The miniature spectrometer is generally compact at the expense of performance. In this work, we proposed a compact, signal-to-noise ratio (SNR) enhancement of the Raman spectrometer by the optimization of optical structure and a noise reduction method. Concerning its optical structure, the Raman spectrometer is increasing the intensity by adding an off-the-shelf cylindrical lens. On the other side of the algorithm, a relevant automatic denoising method of convolutional denoising autoencoder (CDAE) is proposed to further advance the SNR in Raman spectra without manual intervention. The results indicate the performance of the compact Raman spectrometer could increase to a certain extent by testing with 785 nm laser and Ne/Ar source. Besides, by using CDAE to deal with contaminated Raman spectra, a higher SNR is obtained. The results demonstrate that the improvement of the hardware and algorithm is effective for removing the noisy Raman signal and achieving higher SNR. This result may be helpful in further improving the performance of integrated Raman spectrometers and research on miniaturized instruments.

关键词： autoencoder convolutional neural network Czerny-Turner denoising Raman spectrometer

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：