检索结果-内蒙古大学图书馆

3rd IEEE Advanced Information Technology, Electronic and automation Control Conference (IAEAC)

作者： Wang, Botao Ma, Baohui Xu, Kexing Zheng, Tingting Xi An Jiao Tong Univ Sch Elect Engn Xian 710049 Shaanxi Peoples R China State Key Lab Large Elect Drive Syst & Equipment Tianshui 741020 Gansu Peoples R China

ISBN: (纸本)9781538645093

Motor is one of the most frequently used machines in industry. Ensuring the reliability of motor and timely identifying the fault type of motor can guarantee the properly working and prevent the great loss. In this paper, a turn-to-turn short circuit of motor stator and unbalance power supply fault diagnosis system based on Deep sparse auto-encoder and Soft-max Classifier is proposed. The selection of neural network parameters and their influence are systematic given. A new method where dropout rates of sparse auto-encoder are various in each layer is adopted to increase the stability and convergence speed of training process. Finally, the proposed system is applied to an experiment on a motor in laboratory. The conclusion shows the ability to identify the fault type of motor at the continuous state that the accuracy reaches 100%, when only the data from motor at discrete state point are used in training, which makes the system extensible and promising.

关键词： Fault Diagnosis sparse auto-encoder Soft-max Classifier Parameter Selection and Optimization

来源：评论

学校读者我要写书评

暂无评论

Double Regularization-Based RVFL and edRVFL Networks for sparse-Dataset Classification 29th

Double Regularization-Based RVFL and edRVFL Networks for Spa...

引用

29th International Conference on Neural Information Processing

作者： Shi, Qiushi Suganthan, Ponnuthurai Nagaratnam Nanyang Technol Univ Sch Elect & Elect Engn 50 Nanyang Ave Singapore 639798 Singapore Qatar Univ Coll Engn KINDI Ctr Comp Res Doha Qatar

ISBN: (纸本)9783031301049;9783031301056

In our previous work, the random vector functional link network (RVFL) and the ensemble deep RVFL network (edRVFL) have been proven to be competitive for tabular-dataset classification, and their sparse pre-trained versions (SP-RVFL and SP-edRVFL) perform well for sparse-dataset (datasets with a large number of features) classification. However, the sparse auto-encoder-based versions suffer from a time-consuming problem. Therefore, we need to find an alternative way to have similar performance and faster training time. In this paper, we propose the double regularization-based RVFL (2R-RVFL) and edRVFL networks (2R-edRVFL). Two different regularization parameters are assigned to the input and hidden features, respectively. The experiments on 12 sparse datasets show that the 2R-RVFL and 2R-edRVFL networks have similar performance as the SP-RVFL and SP-edRVFL networks, and the double regularized variants have a huge training time advantage. Thus, we believe the newly proposed 2R-RVFL and 2R-edRVFL networks are more suitable for sparse dataset classification.

关键词： Random vector functional link network (RVFL) Ensemble deep RVFL network (edRVFL) sparse auto-encoder Double regularization Training time advantage sparse-dataset classification

来源：评论

学校读者我要写书评

暂无评论

A FAULT DETECTION METHOD BASED ON STACKING THE SAE-SRBM FOR NONSTATIONARY AND STATIONARY HYBRID PROCESSES

引用

INTERNATIONAL JOURNAL OF APPLIED MATHEMATICS AND COMPUTER SCIENCE 2021年第1期31卷 29-43页

作者： Huang, Lei Ren, Hao Chai, Yi Qu, Jianfeng Huaiyin Normal Univ Sch Comp Sci & Technol Huaian City 223300 Jiangsu Peoples R China Chongqing Univ Sch Automat Chongqing 400044 Peoples R China Peng Cheng Lab Shenzhen 518000 Guangdong Peoples R China Minist Educ Key Lab Complex Syst Safety & Control Chongqing 400044 Peoples R China

This paper proposes a fault detection method by extracting nonlinear features for nonstationary and stationary hybrid industrial processes. The method is mainly built on the basis of a sparse auto-encoder and a sparse restricted Boltzmann machine (SAE-SRBM), so as to take advantages of their adaptive extraction and fusion on strong nonlinear symptoms. In the present work, SAEs are employed to reconstruct inputs and accomplish feature extraction by unsupervised mode, and their outputs present a knotty problem of an unknown probability distribution. In order to solve it, SRBMs are naturally used to fuse these unknown probability distribution features by transforming them into energy characteristics. The contribution of this method is the capability of further mining and learning of nonlinear features without considering the nonstationary problem. Also, this paper introduces a method of constructing labeled and unlabeled training samples while maintaining time series features. Unlabeled samples can be adopted to train the part for feature extraction and fusion, while labeled samples can be used to train the classification part. Finally, a simulation on the Tennessee Eastman process is carried out to demonstrate the effectiveness and excellent performance on fault detection for nonstationary and stationary hybrid industrial processes.

关键词： fault detection sparse auto-encoder sparse restricted Boltzmann machine hybrid industrial processes

来源：评论

学校读者我要写书评

暂无评论

Subset based deep learning for RGB-D object recognition

引用

NEUROCOMPUTING 2015年 165卷 280-292页

作者： Bai, Jing Wu, Yan Zhang, Junming Chen, Fuqiang Tongji Univ Coll Elect & Informat Engn Shanghai 201804 Peoples R China

RGB-D camera can easily record both color and depth images and previous works have proved that combining them together could dramatically improve the RGB-D based object recognition accuracy. In this paper, a new method based on a subset approach was introduced to learn higher level features from the raw data. The raw RGB and depth images were divided into several subsets according to their shapes and colors, guaranteeing that any two different objects in each subset are nearly not similar. Then a RGB-Subset-sparse auto-encoder was trained to extract features from RGB images and a Depth-Subset-sparse auto-encoder was trained to extract features from depth images for each subset. Then the learned features were transmitted to recursive neural networks (RNNs) to reduce the dimensionality of the features and learn robust hierarchical feature representations. The feature representations learned from RGB images and depth images were concatenated as the final features and then sent to a softmax classifier for classification. The proposed method is evaluated on three benchmark RGB-D datasets, RGB-D dataset of Lai et al., 2D3D dataset of Browatzki et al. and Aharon dataset of Aharon et al. Compared with other methods, ours achieves state-of-the-art performance on the first two datasets. Furthermore, to validate the generalization of our subset approach, we also do some extra experiments of applying the subsets approach to several previous works, these accuracies improved significantly. (C) 2015 Elsevier B.V. All rights reserved.

关键词： RGB-D object recognition Subset based feature extracting sparse auto-encoder Recursive neural networks Deep learning

来源：评论

学校读者我要写书评

暂无评论

Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots

引用

JOURNAL OF MANUFACTURING SYSTEMS 2021年 61卷 736-745页

作者： Long, Jianyu Mou, Jindong Zhang, Liangwei Zhang, Shaohui Li, Chuan Dongguan Univ Technol Sch Mech Engn Dongguan 523808 Peoples R China

Monitoring the transmission status of multi-joint industrial robots is very important for the accuracy of the robot motion. The fault diagnosis information is an indispensable basis for the collaborative maintenance of the robots in industry 4.0. In this paper, an attitude data-based intelligent fault diagnosis approach is proposed for multi-joint industrial robots. Based on the analysis of the transmission mechanism, the attitude change of the last joint is employed to reflect the transmission fault of robot components. An economical data acquisition strategy is performed by only installing one attitude sensor on the last joint of the multi-joint robot. Considering the characteristics of attitude data, a hybrid sparse auto-encoder (SAE) and support vector machine (SVM) approach, namely SAE-SVM, is subsequently presented to construct an intelligent fault diagnosis model by learning from the attitude dataset with multiple fault information. Experimental results show that the proposed fault diagnosis approach has promising performance in identifying different faults related to the reducer of a 6-axial multi-joint industrial robot accurately and reliably.

关键词： Fault diagnosis Multi-joint industrial robot sparse auto-encoder Support vector machine Attitude data

来源：评论

学校读者我要写书评

暂无评论

Online porosity prediction in laser welding of aluminum alloys based on a multi-fidelity deep learning framework

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2024年第1期35卷 55-73页

作者： Ma, Deyuan Jiang, Ping Shu, Leshi Gong, Zhaoliang Wang, Yilin Geng, Shaoning Huazhong Univ Sci & Technol Sch Mech Sci & Engn State Key Lab Digital Mfg Equipment & Technol Wuhan 430074 Hubei Peoples R China

Pore is one kind of the typical defects in aluminum alloys laser welding. Porosity is an important indicator for evaluating welding quality, and porosity assessment has attracted increasing attention. This paper presents a multi-fidelity deep learning framework (MFDLF) that enables online porosity prediction without post-weld destructive inspection or radioactive detection. In the proposed approach, the maximum temperature on the bottom wall of the keyhole acquired by numerical simulation is used as the data of fidelity 1 (F1), and the coherent optical measurement technology is used to acquire the keyhole depth as the data of fidelity 2 (F2). After extracting the respective four fluctuation characteristics of the multi-fidelity data separately, a sparse auto-encoder (SAE) is used to fuse the four characteristics into an overall feature. Based on the obvious correspondence between porosity and multi-fidelity fusion features, the MFDLF is constructed with tandem two deep belief network (DBN) models, where the former DBN utilizes process parameters to predict the overall feature of F1 data (Feature 1) that is difficult to obtain in real time. Feature 1 is combined with the overall feature of F2 data (Feature 2) that can be obtained online to predict porosity through the latter DBN. The results show that the MFDLF can predict porosity with significantly higher accuracy than the models constructed using only single-fidelity data.

关键词： Aluminum alloys laser welding Porosity prediction Multi-fidelity deep learning framework sparse auto-encoder Fusion features Deep belief network

来源：评论

学校读者我要写书评

暂无评论

Classification of medical images based on deep stacked patched auto-encoders

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2020年第35-36期79卷 25237-25257页

作者： Ben Ali, Ramzi Ejbali, Ridha Zaied, Mourad Univ Gabes ENIG Res Team Intelligent Machines RTIM Zrig 6029 Gabes Tunisia RTIM Gabes Tunisia

The concept of artificial intelligence is not new. Without going into details of the evolution of artificial intelligence, we can confess that recent techniques of deep neural networks have considerably relaunched the trend with a significant advance namely the ability to automatically learn high-level concepts. However, a great step has been taken in deep learning to help researchers perform segmentation, feature extraction, classification and detection from raw medical images. This paper concerns the automatic classification of medical images with deep neural networks. We aimed at developing a system for automatic classification of medical images and detection of anomalies in order to provide a decision-making tool for the doctor. In this component we proposed a method for classifying medical images based on deep neural network using sparse coding and wavelet analysis. Serval real databases are used to test the proposed methods: MIAS and DDSM for mammogram images, LIDC-IDRI for lung images and dental dataset images. Classifications rates given by our approach show a clear improvement compared to those cited in this article.

关键词： Images classification Pattern recognition Deep learning Wavelet network Deep neural wavelets network sparse auto-encoder

来源：评论

学校读者我要写书评

暂无评论

SVM or deep learning? A comparative study on remote sensing image classification

引用

SOFT COMPUTING 2017年第23期21卷 7053-7065页

作者： Liu, Peng Choo, Kim-Kwang Raymond Wang, Lizhe Huang, Fang Chinese Acad Sci Inst Remote Sensing & Digital Earth 9 Dengzhuang South Rd Beijing 100094 Peoples R China China Univ Geosci Sch Comp Sci Wuhan 430074 Peoples R China Univ South Australia Sch Informat Technol & Math Sci Adelaide SA Australia Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 611731 Sichuan Peoples R China

With constant advancements in remote sensing technologies resulting in higher image resolution, there is a corresponding need to be able to mine useful data and information from remote sensing images. In this paper, we study auto-encoder (SAE) and support vector machine (SVM), and to examine their sensitivity, we include additional umber of training samples using the active learning frame. We then conduct a comparative evaluation. When classifying remote sensing images, SVM can also perform better than SAE in some circumstances, and active learning schemes can be used to achieve high classification accuracy in both methods.

关键词： Spatial big data sparse auto-encoder Support vector machine Active learning Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Person-independent eye gaze prediction from eye images using patch-based features

引用

NEUROCOMPUTING 2016年 182卷 10-17页

作者： Lu, Feng Chen, Xiaowu Beihang Univ Sch Comp Sci & Engn Beijing 100191 Peoples R China Beihang Univ Int Res Inst Multidisciplinary Sci Beijing 100191 Peoples R China Beihang Univ Sch Comp Sci & Engn State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China

This paper delivers a preliminary attempt towards person-independent appearance-based gaze estimation. Conventional methods need to assume training and test data collected from the same person, otherwise eye shape difference due to individuality will affect the estimation severely. To solve this problem, the key idea in this paper is to extract from eye images more advanced eye features, which helps learn a person-independent relationship between eye gaze change and eye appearance variation. To this end, we propose employing the advantages of recent sparse auto-encoding techniques. We partition any eye image into small patches which can overlap with each other. With patches from many images, we learn a codebook comprising a set of bases, which can reconstruct any eye image patch with sparse coefficients. By examining these coefficients, we can analyze the eye shape more effectively. Finally, we produce the eye features by pooling the coefficients at different scales, and then combine these subfeatures from different codebooks. Experimental results show that the proposed method achieves good accuracy on a public dataset and it also outperforms conventional methods by a large margin. (C) 2015 Elsevier B.V. All rights reserved.

关键词： Gaze estimation Eye image sparse auto-encoder Gaze direction classification

来源：评论

学校读者我要写书评

暂无评论

Lossless-constraint Denoising based auto-encoders

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2018年 63卷 92-99页

作者： Zhang, Jinsong Zhang, Yi Bai, Lianfa Han, Jing Nanjing Univ Sci & Technol Jiangsu Key Lab Spectral Imaging & Intelltgart Se Nanjing 210094 Jiangsu Peoples R China

In this paper, we address the poor generalization ability problem of tradidonal auto-encoder on noise data, and propose a Lossless-constraint Denoising (LD) method, which can enhance the anti-noise ability and robustness of auto-encoders. We respectively utilize the denoising capability of Denoising auto-encoder (DAE) and sparse auto-encoder (SAE), design two auto-encoders of better noise immunity: Lossless-constraint Denoising auto-encoder (LDAE) and Lossless-constraint Denoising sparse auto-encoder (LDSAE).

关键词： sparse auto-encoder Denoising auto-encoder Neural networks and deep learning

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：