检索结果-内蒙古大学图书馆

3D convolutional auto-encoder based multi-scale feature extraction for point cloud registration

OPTICS AND LASER TECHNOLOGY 2022年 149卷 107860-107860页

作者： Ma, Hao Yin, De-Yu Liu, Jing-Bin Chen, Rui-Zhi Wuhan Univ State Key Lab Informat Engn Surveying Mapping & R Wuhan 430079 Peoples R China Finnish Geospatial Res Inst Dept Remote Sensing & Photogrammetry Masala 02430 Finland Finnish Geospatial Res Inst Ctr Excellence Laser Scanning Res Masala 02430 Finland

Searching corresponding features between two consecutive point cloud sequences is a key step in frame-to-frame matching. Utilizing multi-resolution strategy and voxel model which reserves the original shape of input data, we propose a fully unsupervised convolutional auto-encoder (CAE) based feature matching methodology that extracts features from multi-resolution voxel model. Different resolutions can capture different information: hight resolution better reflects local details, and low resolution can describe coarse appearance in a relative wide range. CAE is further adopted to encode the voxel patch of a specific resolution to a low dimension one. The final feature descriptor is concatenated by the encoded features of different resolutions and is used to determine the initial corresponding features in terms of Euclidean distance. Refined matches are obtained through RANSAC. Experiments based on KITTI dataset show that our features outperform state-of-the-art by almost 20-30% in average matching inlier ratio.

关键词： convolutional auto-encoder Multi-scale Feature descriptor Point cloud Registration

来源：评论

学校读者我要写书评

暂无评论

A Semantic Segmentation Method for Road Environment Images Based on Hybrid convolutional auto-encoder

引用

TRAITEMENT DU SIGNAL 2022年第4期39卷 1235-1245页

作者： Song, Xiaona Liu, Haichao Wang, Lijun Wang, Song Cao, Yunyu Xu, Donglai Zhang, Shenfeng North China Univ Water Resources & Elect Power Sch Mech Engn Zhengzhou 450011 Peoples R China Teesside Univ Sch Comp Engn & Digital Technol Middlesbrough TS1 3BX England Suzhou Tianshuo Intelligent Software Co Ltd Suzhou 215011 Peoples R China

Deep convolutional neural networks (CNNs) have presented amazing performance in the task of semantic segmentation. However, the network model is complex, the training time is prolonged, the semantic segmentation accuracy is not high and the real-time performance is not good, so it is difficult to be directly used in the semantic segmentation of road environment images of autonomous vehicles. As one of the three models of deep learning, the auto-encoder (AE) has powerful data learning and feature extracting capabilities from the raw data itself. In this study, the network architecture of auto-encoder and convolutional auto-encoder (CAE) is improved, supervised learning auto-encoder and improved convolutional auto-encoder are proposed, and a hybrid convolutional auto-encoder model is constructed by combining them. It can extract low-dimensional abstract features of road environment images by using convolution layers and pooling layers in front of the network, and then supervised learning auto-encoder are used to enhance and express semantic segmentation features, and finally de-convolution layers and un-pooling layers are used to generate semantic segmentation results. The hybrid convolutional auto-encoder model proposed in this paper not only contains encoding and decoding parts which are used in the common semantic segmentation models, but also adds semantic feature enhancing and representing parts, so that the network which has fewer convolutional and pooling layers can still achieve better semantic segmentation effects. Compared to the semantic segmentation based on convolutional neural networks, the hybrid convolutional auto -encoder has fewer network layers, fewer network parameters, and simpler network training. We evaluated our proposed method on Camvid and Cityscapes, which are standard benchmarks for semantic segmentation, and it proved to have a better semantic segmentation effect and good real-time performance.

关键词： semantic segmentation convolutional auto-encoder deep learning autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Research on the Fault Diagnosis Method of an Internal Gear Pump Based on a convolutional auto-encoder and PSO-LSSVM

引用

SENSORS 2022年第24期22卷 9841页

作者： Liao, Jian Zheng, Jianbo Chen, Zongbin Naval Univ Engn Inst Vibrat & Noise Wuhan 430033 Peoples R China Naval Univ Engn Naval Key Lab Ship Vibrat & Noise Wuhan 430033 Peoples R China

The raw signals produced by internal gear pumps are susceptible to noises brought on by mechanical vibrations and the surrounding environment, and the sample count collected during the various operating periods is not distributed evenly. Accurately diagnosing faults in internal gear pumps is significantly complicated by these factors. In light of these issues, accelerated life testing was performed in order to collect signals from an internal gear pump during various operating periods. Based on the architecture of a convolutional auto-encoder network, preprocessing of the signals in the various operating periods was performed to suppress noise and enhance operating period-representing features. Thereafter, variational mode decomposition was utilized to decompose the preprocessed signal into multiple intrinsic mode functions, and the multi-scale permutation entropy value was extracted for each intrinsic mode function to form a feature set. The feature set was subsequently divided into a training set and a test set, with the training set being trained to utilize a particle swarm optimization-least squares support vector machine network. For pattern recognition, the test set samples were fed into the trained model. The results demonstrated a 99.2% diagnostic accuracy. Compared to other methods of fault diagnosis, the proposed method is more effective and accurate.

关键词： internal gear pumps fault diagnosis convolutional auto-encoder multi-scale permutation entropy least squares support vector machine

来源：评论

学校读者我要写书评

暂无评论

One-dimensional convolutional auto-encoder-based feature learning for fault diagnosis of multivariate processes

引用

JOURNAL OF PROCESS CONTROL 2020年 87卷 54-67页

作者： Chen, Shumei Yu, Jianbo Wang, Shijin Tongji Univ Sch Mech Engn Shanghai 201804 Peoples R China Tongji Univ Sch Econ & Management Shanghai 200082 Peoples R China

Noise and high-dimension of process signals decrease effectiveness of those regular fault detection and diagnosis models in multivariate processes. Deep learning technique shows very excellent performance in high-level feature learning from image and visual data. However, the large labeled data are required for deep neural networks (DNNs) with supervised learning like convolutional neural network (CNN), which increases the time cost of model construction significantly. A new DNN model, one-dimensional convolutional auto-encoder (1D-CAE) is proposed for fault detection and diagnosis of multivariate processes in this paper. 1D-CAE is utilized to learn hierarchical feature representations through noise reduction of high-dimensional process signals. auto-encoder integrated with convolutional kernels and pooling units allows feature extraction to be particularly effective, which is of great importance for fault detection and diagnosis in multivariate processes. The comparison between 1D-CAE and other typical DNNs illustrates effectiveness of 1D-CAE for fault detection and diagnosis on Tennessee Eastman Process and Fed-batch fermentation penicillin process. The proposed method provides an effective platform for deep-learningbased process fault detection and diagnosis of multivariate processes. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Multivariate process Fault diagnosis convolutional auto-encoder Feature learning Tennessee Eastman Process Fed-batch fermentation penicillin process

来源：评论

学校读者我要写书评

暂无评论

Steady-State Process Fault Detection for Liquid Rocket Engines Based on convolutional auto-encoder and One-Class Support Vector Machine

引用

IEEE ACCESS 2020年 8卷 3144-3158页

作者： Zhu, Xiaobin Cheng, Yuqiang Wu, Jianjun Hu, Runsheng Cui, Xing Natl Univ Def Technol Coll Aerosp Sci & Engn Changsha 410073 Peoples R China

Liquid rocket engines (LREs) are the main propulsive devices of launch vehicles. Due to the complex structures and extreme working environments, LREs are also the components prone to failure. It is of great engineering significance to develop fault detection technologies which can detect fault symptoms in time and provide criteria for further fault diagnosis and control measures to avoid serious consequences during both the ground tests and flight missions. This paper presents a novel fault detection method based on convolutional auto-encoder (CAE) and one-class support vector machine (OCSVM) for the steady-state process of LREs. We train the CAEs by normal ground hot-fire test data of a certain type of large LRE for automatic feature extraction. Then the obtained features are used to train the OCSVMs to accomplish the fault detection task. The results demonstrate that the proposed method outperforms traditional redline system (RS), adaptive threshold algorithm (ATA), and back-propagation neural network (BPNN). We also study the effect of sample sizes and domain knowledge on the performance of the proposed method. The results suggest that appropriate measures that enrich the effective information content in the training data, such as increasing sample size and introducing domain knowledge, can further improve the performance of the proposed fault detection method.

关键词： convolutional auto-encoder one-class support vector machine liquid rocket engine steady-state process fault detection

来源：评论

学校读者我要写书评

暂无评论

FRWCAE: joint faster-RCNN and Wasserstein convolutional auto-encoder for instance retrieval

引用

APPLIED INTELLIGENCE 2020年第7期50卷 2208-2221页

作者： Zhang, Yi-yang Feng, Yong Liu, Da-jiang Shang, Jia-xing Qiang, Bao-hua Chongqing Univ Coll Comp Sci Chongqing 400030 Peoples R China Minist Educ Key Lab Dependable Serv Comp Cyber Phys Soc Chongqing 400030 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Trusted Software Guilin 541004 Peoples R China Guilin Univ Elect Technol Guangxi Key Lab Optoelect Informat Proc Guilin 541004 Peoples R China

Based on the powerful feature extraction capability of deep convolutional neural networks, image-level retrieval methods have achieved superior performance compared to the hand-crafted features and indexing algorithms. However, people tend to focus on foreground objects of interest in images. Locating objects accurately and using object-level features for retrieval become the essential tasks of instance search. In this work, we propose a novel instance retrieval method FRWACE, which combines the Faster R-CNN framework for object-level feature extraction with a brand-new Wasserstein convolutional auto-encoder for dimensionality reduction. In addition, we propose a considerate category-first spatial re-rank strategy to improve instance-level retrieval accuracy. Extensive experiments on four large datasets Oxford 5K, Paris 6K, Oxford 105K and Paris 106K show that our approach has achieved significant performance compared to the state-of-the-arts.

关键词： Instance-level retrieval convolutional auto-encoder Wasserstein distance Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

A new deep transfer learning network based on convolutional auto-encoder for mechanical fault diagnosis

引用

MEASUREMENT 2021年 178卷 109352-109352页

作者： Qian, Quan Qin, Yi Wang, Yi Liu, Fuqiang Chongqing Univ State Key Lab Mech Transmission Chongqing 400044 Peoples R China Chongqing Univ Coll Mech & Vehicle Engn Chongqing 400044 Peoples R China

Deep learning has gained a great achievement in the intelligent fault diagnosis of rotating machineries. However, the labeled data is scarce in actual engineering and the marginal distribution of data is discrepant under different conditions. Transfer learning provides a feasible way to overcome these difficulties. Considering the effect of noise on the transfer fault diagnosis, this work puts forward a new deep transfer learning network based on convolutional auto-encoder(CAE-DTLN) to implement the mechanical fault diagnosis in target domain without labeled data. In the proposed framework, CAE is used as the feature extractor as it has the ability of noise removal. Moreover, both CORrelation ALignment (CORAL) loss and domain classification loss are integrated to enhance the effect of domain confusion. The proposed model is applied to the fault transfer diagnosis of planetary gearboxes under different working loads and noise levels, and it is compared with other typical fault transfer diagnosis models. The experimental results show that CAE-DTLN has higher diagnosis accuracy and stronger generalization ability. The average diagnostic accuracy of CAE-DTLN is over 99%. Moreover, the proposed transfer learning model has better anti-noise performance.

关键词： Intelligent fault diagnosis convolutional auto-encoder Deep transfer learning Anti-noise ability Domain adaption

来源：评论

学校读者我要写书评

暂无评论

Yarn-dyed Fabric Defect Detection using U-shaped De-noising convolutional auto-encoder 9

Yarn-dyed Fabric Defect Detection using U-shaped De-noising ...

引用

9th IEEE Data Driven Control and Learning Systems Conference (DDCLS)

作者： Zhang, Hong-wei Tan, Quan-lu Lu, Shuai Ge, Zhi-qiang Gu, De Xian Polytech Univ Sch Elect Informat Xian 710048 Peoples R China Zhejiang Univ Inst Ind Proc Control Hangzhou 310027 Peoples R China Beijing Univ Chem Technol Inst Math Beijing 100029 Peoples R China Jiangnan Univ Inst Automat Key Lab Adv Proc Control Light Ind Minist Educ Wuxi 214122 Jiangsu Peoples R China

ISBN: (纸本)9781728159225

Practical factors such as high labor cost of labelling defect samples and scarcity of defect samples make it difficult for supervised machine learning models to solve the problem of yam-dyed fabric defect detection. To solve this problem, this paper proposes an unsupervised yam-dyed fabric defect detection method based on U-shaped de-noising convolutional auto-encoder (UDCAE). Firstly, for tested samples of yam-dyed fabric, the training dataset was constructed by collecting the non-defect yarn-dyed fabric samples. Then, the non-defect dataset is utilized to model and train the proposed UDCAE model. Finally, the defective area can be quickly detected by calculating the residual between the original tested yarn-dyed fabric image and its reconstructed item correspondingly. The experiment results show that the proposed method can accurately detect defects of yarn-dyed fabrics with different patterns.

关键词： yam-dyed fabric fabric defect detection de-noising auto-encoder convolutional auto-encoder Unet

来源：评论

学校读者我要写书评

暂无评论

HRTF Representation with convolutional auto-encoder 26th

HRTF Representation with Convolutional Auto-encoder

引用

26th International Conference on MultiMedia Modeling (MMM)

作者： Chen, Wei Hu, Ruimin Wang, Xiaochen Li, Dengshi Wuhan Univ Natl Engn Res Ctr Multimedia Software Sch Comp Sci Wuhan 430072 Peoples R China Wuhan Univ Hubei Key Lab Multimedia & Network Commun Engn Wuhan 430072 Peoples R China Collaborat Innovat Ctr Geospatial Technol Wuhan 430079 Peoples R China Jianghan Univ Sch Math & Comp Sci Wuhan Peoples R China

ISBN: (纸本)9783030377311;9783030377304

The head-related transfer function (HRTF) can be considered as some kind of filter that describes how a sound from an arbitrary spatial direction transfers to the listener's eardrums. HRTF can be used to synthesize vivid virtual 3D sound that seems to come from any spatial location, which makes it play an important role in the 3D audio technology. However, the complexity and variation of auditory cues inherent in HRTF make it difficult to set up an accurate mathematical model with the conventional methods. In this paper, we put forward an HRTF representation modeling based on convolutional auto-encoder (CAE), which is some type of auto-encoder that contains convolutional layers in the encoder part and deconvolution layers in the decoder part. The experimental evaluation on the ARI HRTF database shows that the proposed model provides very good results on dimensionality reduction of HRTF.

关键词： HRTF Representation convolutional auto-encoder Deep auto-encoder Denoising auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Multimodal Emotion Recognition Method Based on convolutional auto-encoder

引用

INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS 2019年第1期12卷 351-358页

作者： Zhou, Jian Wei, Xianwei Cheng, Chunling Yang, Qidong Li, Qun Nanjing Univ Posts & Telecommun Coll Comp 66 Xinmofan Rd Nanjing 210003 Jiangsu Peoples R China Jiangsu High Technol Res Key Lab Wireless Sensor 66 Xinmofan Rd Nanjing 210003 Jiangsu Peoples R China

Emotion recognition is of great significance to computational intelligence systems. In order to improve the accuracy of emotion recognition, electroencephalogram (EEG) signals and external physiological (EP) signals are adopted due to their perfect performance in reflecting the slight variations of emotions, wherein EEG signals consist of multiple channels signals and EP signals consist of multiple types of signals. In this paper, a multimodal emotion recognition method based on convolutional auto-encoder (CAE) is proposed. Firstly, a CAE is designed to obtain the fusion features of multichannel EEG signals and multitype EP signals. Secondly, a fully connected neural network classifier is constructed to achieve emotion recognition. Finally, experiment results show that the proposed method can improve the accuracy of emotion recognition obviously compared with other similar methods. (c) 2019 The Authors. Published by Atlantis Press SARL.

关键词： Emotion recognition convolutional auto-encoder Fully connected neural network EEG signals EP signals

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：