入藏号: WOS:000382046500001
入藏号: WOS:000382664100001

Deep Convolutional Extreme Learning Machine and Its Application in Handwritten Digit Classification
作者ang, S (Pang, Shan)[ 1 ] ; Yang, XY (Yang, Xinyi)[ 2 ]
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
文献号: 3049632
DOI: 10.1155/2016/3049632
出版年: 2016
查看期刊信息
摘要
In recent years, some deep learning methods have been developed and applied to image classification applications, such as convolutional neuron network (CNN) and deep belief network (DBN). However they are suffering from some problems like local minima, slow convergence rate, and intensive human intervention. In this paper, we propose a rapid learning method, namely, deep convolutional extreme learning machine (DC-ELM), which combines the power of CNN and fast training of ELM. It uses multiple alternate convolution layers and pooling layers to effectively abstract high level features from input images. Then the abstracted features are fed to an ELM classifier, which leads to better generalization performance with faster learning speed. DC-ELM also introduces stochastic pooling in the last hidden layer to reduce dimensionality of features greatly, thus saving much training time and computation resources. We systematically evaluated the performance of DC-ELM on two handwritten digit data sets: MNIST and USPS. Experimental results show that our method achieved better testing accuracy with significantly shorter training time in comparison with deep learning methods and other ELM methods.
关键词
KeyWords Plus:IMAGE RECOGNITION; BELIEF NETWORKS; NEURAL-NETWORKS; EFFICIENT
作者信息
通讯作者地址: Pang, S (通讯作者)
显示增强组织信息的名称        Ludong Univ, Coll Elect & Informat Engn, Yantai 264025, Peoples R China.
地址:
显示增强组织信息的名称        [ 1 ] Ludong Univ, Coll Elect & Informat Engn, Yantai 264025, Peoples R China
              [ 2 ] Naval Aeronaut & Astronaut Univ, Dept Aircraft Engn, Yantai 264001, Peoples R China
电子邮件地址:pangshanpp@163.com
出版商
HINDAWI PUBLISHING CORP, 315 MADISON AVE 3RD FLR, STE 3070, NEW YORK, NY 10017 USA
类别 / 分类
研究方向:Mathematical & Computational Biology; Neurosciences & Neurology
Web of Science 类别:Mathematical & Computational Biology; Neurosciences
文献信息
文献类型:Article
语种:English
入藏号: WOS:000382046500001
ISSN: 1687-5265
eISSN: 1687-5273
期刊信息
Impact Factor (影响因子): Journal Citation Reports®
其他信息
IDS 号: DU2MZ
Web of Science 核心合集中的 "引用的参考文献": 31
Web of Science 核心合集中的 "被引频次": 0，

Aero Engine Component Fault Diagnosis Using Multi-Hidden-Layer Extreme Learning Machine with Optimized Structure
作者ang, S (Pang, Shan)[ 1 ] ; Yang, XY (Yang, Xinyi)[ 2 ] ; Zhang, XF (Zhang, Xiaofeng)[ 1 ]
INTERNATIONAL JOURNAL OF AEROSPACE ENGINEERING
文献号: 1329561
DOI: 10.1155/2016/1329561
出版年: 2016
查看期刊信息
摘要
A new aero gas turbine engine gas path component fault diagnosis method based on multi-hidden-layer extreme learning machine with optimized structure (OM-ELM) was proposed. OM-ELM employs quantum-behaved particle swarm optimization to automatically obtain the optimal network structure according to both the root mean square error on training data set and the norm of output weights. The proposed method is applied to handwritten recognition data set and a gas turbine engine diagnostic application and is compared with basic ELM, multi-hidden-layer ELM, and two state-of-the-art deep learning algorithms: deep belief network and the stacked denoising autoencoder. Results show that, with optimized network structure, OM-ELM obtains better test accuracy in both applications and is more robust to sensor noise. Meanwhile it controls the model complexity and needs far less hidden nodes than multi-hidden-layer ELM, thus saving computer memory and making it more efficient to implement. All these advantages make our method an effective and reliable tool for engine component fault diagnosis tool.
关键词
KeyWords PlusEEP BELIEF NETWORKS; NEURAL-NETWORKS
作者信息
通讯作者地址: Pang, S (通讯作者)
显示增强组织信息的名称        Ludong Univ, Coll Informat & Elect Engn, Yantai 264025, Peoples R China.
地址:
显示增强组织信息的名称        [ 1 ] Ludong Univ, Coll Informat & Elect Engn, Yantai 264025, Peoples R China
              [ 2 ] Naval Aeronaut & Astronaut Univ, Dept Aircraft Engn, Yantai 264001, Peoples R China
电子邮件地址:pangshanpp@163.com
出版商
HINDAWI PUBLISHING CORP, 315 MADISON AVE 3RD FLR, STE 3070, NEW YORK, NY 10017 USA
类别 / 分类
研究方向:Engineering
Web of Science 类别:Engineering, Aerospace
文献信息
文献类型:Article
语种:English
入藏号: WOS:000382664100001
ISSN: 1687-5966
eISSN: 1687-5974
期刊信息
Impact Factor (影响因子): Journal Citation Reports®
其他信息
IDS 号: DV1EX
Web of Science 核心合集中的 "引用的参考文献": 26
Web of Science 核心合集中的 "被引频次": 0

楼主，这两篇文章的pdf版检索信息，请见附件。