检索结果-内蒙古大学图书馆

Markov transition fields and auto-encoder-based preprocessing for event recognition of Φ-OTDR

OPTICA APPLICATA 2024年第2期54卷 217-229页

作者： Hu, Xin Dai, Jingyi Wei, Ziyi Shen, Wei Yu, Hao Wu, Haiyang Xu, Yingwen Hu, Chengyon Deng, Chuanlu Huang, Yi China State Grid Taizhou Power Supply Co Taizhou 225300 Peoples R China Shanghai Univ Key Lab Specialty Fiber Opt & Opt Access Networks Shanghai 200444 Peoples R China

To improve the model training efficiency and the classification performance of the phase-sensitive optical time-domain reflectometer (Phi-OTDR) in disturbance events recognition, a preprocessing method based on Markov transition fields (MTF) and auto-encoder (AE) is proposed. The phase time series, derived from demodulation of the original scattering signals, are converted into images by using the MTF method. Subsequently, an auto-encoder is introduced to perform a dimensionality reduction characterization of the MTF images, and the outputs of the encoder will be used as features for classification. The experimental results demonstrate that, compared with directly processing time series using 1-D CNN and classifying MTF images using CNN, the features obtained by the proposed method can accelerate the training process and improve the recognition performance of the classification model. The recognition accuracy for the four classes of events on the fence reaches 95.6%, representing a 12% increase.

关键词： distributed optical fiber sensing Phi-OTDR disturbance recognition Markov transition fields auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Human Motion Segmentation via Velocity-Sensitive Dual-Side auto-encoder

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2023年 32卷 524-536页

作者： Bai, Yue Wang, Lichen Liu, Yunyu Yin, Yu Di, Hang Fu, Yun Northeastern Univ Dept Elect & Comp Engn Boston MA 02115 USA Northeastern Univ Khoury Coll Comp Sci Boston MA 02115 USA

Human motion segmentation (HMS) aims to segment a long human action video into a bunch of short and meaningful action clips. Existing supervised learning approaches need a large amount of training data which may be costly in real-world scenario, while most unsupervised clustering methods cannot fully explore the temporal correlations among human motions and hard to achieve promising performances. In our paper, we design a novel unsupervised framework, called Velocity-Sensitive Dual-Side auto-encoder (VSDA), for HMS task. Specifically, a multi-neighbor auto-encoder (MNA) is proposed to extract informative temporal features, which fully explores the local temporal patterns of human motions. In addition, a long-short distance encoding (LSE) strategy is designed. It constrains the encoded representations of close (short-distance) frames becoming similar while the representations of far-away (long-distance) frames becoming distinctive. Similarly, this strategy is also deployed on the decoded outputs as the long-short distance decoding (LSD) module. The LSE/LSD guides the learning process explicitly and implicitly to achieve the dual-side structure. Moreover, we consider the energy variations during the human motion to propose the velocity-sensitive (VS) guidance mechanism for further model improvement. VSDA leverages the temporal characteristics of human motion and derives promising HMS performance. Comprehensive experiments on six real-world human motion datasets illustrate the effectiveness of our proposed model.

关键词： Human motion unsupervised learning auto-encoder energy-based

来源：评论

学校读者我要写书评

暂无评论

auto-encoder Based automated Epilepsy Diagnosis 7

Auto-encoder Based Automated Epilepsy Diagnosis

引用

7th International Conference on Computing, Communications and Informatics (ICACCI)

作者： Sharathappriyaa, V Gautham, S. Lavanya, R. Amrita Vishwa Vidyapeetham Amrita Sch Engn Dept Elect & Commun Engn Coimbatore Tamil Nadu India

ISBN: (纸本)9781538653142

This work proposes the design of an automated system based on auto-encoders to detect epilepsy using Electroencephalogram (EEG) signal. HarmonicWavelet Packet Transform (HWPT) and Fractal Analysis are employed to extract the initial feature vector. HWPT is used to capture spectral information using non-overlapping octave bands, thereby avoiding recursive calculations. Fractal dimension (FD) based on Katz technique is performed on windowed segments of the signal to capture spatial information of the EEG signal. Features comprising HWPT and FD are fed to an auto-encoder, which is used to compress the high dimensional feature vector to a more discriminative and lower dimensional feature vector, for efficient classification. Finally, a Softmax classifier is used for the binary classification problem of discriminating epilepsy signals from normal cases.

关键词： EEG Fractal dimension Harmonic wavelet packet transform auto-encoder Softmax

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction for Hyperspectral Data Based on Sample-Dependent Repulsion Graph Regularized auto-encoder

引用

Chinese Journal of Electronics 2017年第6期26卷 1233-1238页

作者： WANG Xuesong KONG Yi CHENG Yuhu School of Information and Control Engineering China University of Mining and Technology

To achieve high classification accuracy of hyperspectral data, a dimensionality reduction algorithm called Sample-dependent repulsion graph regularized auto-encoder(SRGAE) is proposed. Based on the sample-dependent graph, by applying the repulsion force to the samples from different classes but nearby, a sampledependent repulsion graph is built to make the samples from the same class will be pro jected to samples that are close-by and the samples from different classes will be pro jected to samples that are far away. The sampledependent repulsion graph can avoid the neighborhood parameter selection problem existing in the nearest neighborhood graph. By integrating advantages of deep learning and graph regularization technique, the SRGAE can maintain the learned deep features are consistent with the inherent manifold structure of the original hyperspectral data. Experimental results on two real hyperspectral data show that, when compared with some popular dimensionality reduction algorithms, the proposed SRGAE can yield higher classification accuracy.

关键词： Hyperspectral data Dimensionality reduction Sample-dependent repulsion graph Regularized auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Bi-GAE:A Bidirectional Generative auto-encoder

引用

Journal of Computer Science & Technology 2023年第3期38卷 626-643页

作者：华勤胡瀚文钱诗友杨定裕曹健 Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Alibaba Group Shanghai 201210China

Improving the generative and representational capabilities of auto-encoders is a hot research topic. However, it is a challenge to jointly and simultaneously optimize the bidirectional mapping between the encoder and the decoder/generator while ensuing convergence. Most existing auto-encoders cannot automatically trade off bidirectional mapping. In this work, we propose Bi-GAE, an unsupervised bidirectional generative auto-encoder based on bidirectional generative adversarial network (BiGAN). First, we introduce two terms that enhance information expansion in decoding to follow human visual models and to improve semantic-relevant feature representation capability in encoding. Furthermore, we embed a generative adversarial network (GAN) to improve representation while ensuring convergence. The experimental results show that Bi-GAE achieves competitive results in both generation and representation with stable convergence. Compared with its counterparts, the representational power of Bi-GAE improves the classification accuracy of high-resolution images by about 8.09%. In addition, Bi-GAE increases structural similarity index measure (SSIM) by 0.045, and decreases Fréchet inception distance (FID) by in the reconstruction of 512*512 images.

关键词： auto-encoder adversarial network image reconstruction and generation feature representation

来源：评论

学校读者我要写书评

暂无评论

A novel approach to reconstruction based saliency detection via convolutional neural network stacked with auto-encoder

引用

NEUROCOMPUTING 2019年 349卷 145-155页

作者： Lin, Xinchen Tang, Yang Tianfield, Huaglory Qian, Feng Zhong, Weimin East China Univ Sci & Technol Minist Educ Key Lab Adv Control & Optimizat Chem Proc Shanghai 200237 Peoples R China Glasgow Caledonian Univ Sch Comp Engn & Built Environm Glasgow G4 0BA Lanark Scotland

Visual saliency detection, aimed at the simulation of human visual system (HVS), has drawn wide attention in recent decades. Reconstruction based saliency detection models are established methods for saliency detection, which predict unexpected regions via linear combination or auto-encoder network. However, these models are ineffective in dealing with images due to the loss of spatial information caused by the conversion from images to vectors. In this paper, a novel approach is proposed to solve this problem. The core is a deep reconstruction model, i.e., convolutional neural network for reconstruction stacked with auto-encoder (CNNR for short). On the one hand, the use of CNN is able to directly take two-dimensional data as input rather than having to convert the matrix to a series of vectors as in conventional reconstruction based saliency detection methods. On the other hand, the training process of CNN is augmented with the initialization obtained by an unsupervised learning process of convolutional auto-encoder (CAE). By this way, our CNNR model can be trained on limited labeled data, with the weights of the CNN being meaningfully initialized by CAE instead of random initialization. Performance evaluations are conducted through comprehensive experiments on four benchmark datasets and the comparisons with eight state-of-the-art saliency detection models show that our proposed deep reconstruction model outperforms most of the eight state-of-the-art saliency detection models. (C) 2019 Published by Elsevier B.V.

关键词： Convolutional neural network auto-encoder Deep learning Reconstruction Saliency detection

来源：评论

学校读者我要写书评

暂无评论

An Image Clustering auto-encoder Based on Predefined Evenly-Distributed Class Centroids and MMD Distance

引用

NEURAL PROCESSING LETTERS 2020年第2期51卷 1973-1988页

作者： Zhu, Qiuyu Wang, Zhengyong Shanghai Univ Sch Commun & Informat Engn Shanghai Peoples R China

In this paper, we propose a novel, effective and simpler end-to-end image clustering auto-encoder algorithm: ICAE. The algorithm uses predefined evenly-distributed class centroids (PEDCC) as the clustering centers, which ensures the inter-class distance of latent features is maximal, and adds data distribution constraint, data augmentation constraint, auto-encoder reconstruction constraint and Sobel smooth constraint to improve the clustering performance. Specifically, we perform one-to-one data augmentation to learn the more effective features. The data and the augmented data are simultaneously input into the autoencoder to obtain latent features and the augmented latent features whose similarity are constrained by an augmentation loss. Then, making use of the maximum mean discrepancy distance, we combine the latent features and augmented latent features to make their distribution close to the PEDCC distribution (uniform distribution between classes, Dirac distribution within the class) to further learn clustering-oriented features. At the same time, the MSE of the original input image and reconstructed image is used as reconstruction constraint, and the Sobel smooth loss to build generalization constraint to improve the generalization ability. Finally, extensive experiments on three common datasets MNIST, Fashion-MNIST, COIL20 are conducted. The experimental results show that the algorithm has achieved the best clustering results so far. In addition, we can use the predefined PEDCC class centers, and the decoder to clearly generate the samples of each class. The code can be downloaded at

关键词： auto-encoder Clustering Predefined evenly-distributed class centroids (PEDCC) Data augmentation Maximum mean discrepancy (MMD)

来源：评论

学校读者我要写书评

暂无评论

SSS-AE: Anomaly Detection Using Self-Attention Based Sequence-to-Sequence auto-encoder in SMD Assembly Machine Sound

引用

IEEE ACCESS 2021年 9卷 131191-131202页

作者： Nam, Ki Hyun Song, Young Jong Yun, Il Dong Hankuk Univ Foreign Studies Dept Comp Engn Yongin 17035 South Korea

A Surface-Mounted Device (SMD) assembly machine continuously assembles various products in real field. Unwanted situations such as assembly failure and device breakdown can occur at any time during the assembly process and result in costly losses. Anomaly detection techniques using deep learning are effective in detecting such abnormal situations. Two training scenarios, single-product learning and multi-product learning, can be considered for SMD anomaly detection workflows. Since there are not many products in previous studies, single-product learning is sufficient. However, multi-product learning is required when the number of products increases gradually. Successful multi-product learning on various assembly sound data in an industrial environment with limited resources requires efficient and light learning methods. In this paper, we propose robust model and effective data preprocessing method, Self-Attention based Sequence-to-Sequence auto-encoder (SSS-AE) and Temporal Adaptive Average Pooling (TAAP). For more accurate evaluation compared with the previous SMD anomaly detection studies, a new large-scale SMD dataset containing observed real abnormal products were collected and evaluated. As a result, we show that SSS-AE and TAAP are powerful and practical approaches for both single-product learning and multi-product learning.

关键词： Anomaly detection Data models Decoding Training Unsupervised learning Adaptation models Task analysis Anomaly detection auto-encoder self-attention sequence-to-sequence

来源：评论

学校读者我要写书评

暂无评论

A road segmentation method based on the deep auto-encoder with supervised learning

引用

COMPUTERS & ELECTRICAL ENGINEERING 2018年 68卷 381-388页

作者： Song, Xiaona Rui, Ting Zhang, Sai Fei, Jianchao Wang, Xinqing Army Engn Univ PLA Coll Filed Engn Guanghua Rd Nanjing Jiangsu Peoples R China North China Univ Water Resources & Elect Power Coll Mech Engn Beihuan Rd Zhengzhou Henan Peoples R China Nanjing Univ State Key Lab Novel Software Technol Hankou Rd Nanjing Jiangsu Peoples R China

Road environment perception is a key technique for unmanned vehicles. Segmentation of road images is an important method of determining the driving area. The segmentation precisions of existing methods are not high, and some are not in real-time. To solve these problems, we design a supervised deep auto-encoder (AE) model to complete the semantic segmentation of road environment images. By adding a supervised layer to a classical AE, and using the segmentation image of training samples as the supervised information, the model can learn the useful features to complete the semantic segmentation. Next, the multilayer stacking method of the supervised AE is designed to build the supervised deep AE, since the deep network has more abundant and diversified features. Finally, we verified the method using CamVid. Compared with Convolutional Neural Networks(CNN) and Fully Convolutional Networks(FCN), the road segmentation performance, such as precision and speed were improved.

关键词： Image segmentation Road recognition auto-encoder Semantic segmentation Unmanned vehicle

来源：评论

学校读者我要写书评

暂无评论

A Cross-Attention Fusion Based Graph Convolution auto-encoder for Open Relation Extraction

引用

IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2023年 31卷 476-485页

作者： Xie, Binhong Li, Yu Zhao, Hongyan Pan, Lihu Wang, Enhui Taiyuan Univ Sci & Technol Dept Comp Sci & Technol Taiyuan Peoples R China Shanxi Univ Dept Comp & Informat Technol Taiyuan Peoples R China

Open Relation Extraction (OpenRE) aims at clustering relation instances to extract relation types. By learning relation patterns between named entities, it clusters semantically equivalent patterns into a unified relation cluster. Existing clustering-based OpenRE methods only consider the information of the instance itself, ignoring knowledge of any relations between instances. Therefore, a Cross-Attention Fusion based Graph Convolution auto-encoder (CAGCE) method for Open Relation Extraction is proposed. The auto-encoder learns the semantic information of the sentence instance itself, and the Graph Convolution Network learns the relational similarity information between sentences. Then, the two heterogeneous representations are crossed and fused layer-by-layer through a cross-attention fusion mechanism. Finally, the fused features are used for clustering to form the relation types. A comparison with baseline models using the FewRel and NYT-FB datasets shows the effectiveness and superiority of the proposed method.

关键词： Attention mechanism auto-encoder graph convolution network open relation extraction

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：