检索结果-内蒙古大学图书馆

Locality-Constrained sparse auto-encoder for Image Classification

IEEE SIGNAL PROCESSING LETTERS 2015年第8期22卷 1070-1073页

作者： Luo, Wei Yang, Jian Xu, Wei Fu, Tao Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Jiangsu Peoples R China

We propose a locality-constrained sparse auto-encoder (LSAE) for image classification in this letter. Previous work has shown that the locality is more essential than sparsity for classification task. We here introduce the concept of locality into the auto-encoder, which enables the auto-encoder to encode similar inputs using similar features. The proposed LSAE can be trained by the existing backprop algorithm;no complicated optimization is involved. Experiments on the CIFAR-10, STL-10 and Caltech-101 datasets validate the effectiveness of LSAE for classification task.

关键词： Feature learning image classification sparse auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Deep sparse auto-encoder Features Learning for Arabic Text Recognition

引用

IEEE ACCESS 2021年 9卷 18569-18584页

作者： Rahal, Najoua Tounsi, Maroua Hussain, Amir Alimi, Adel M. Tunis El Manar Univ Fac Sci Tunis Tunis 2092 Tunisia Univ Sfax Natl Engn Sch Sfax ENIS REs Grp Intelligent Machines REGIM Lab Sfax 3038 Tunisia Edinburgh Napier Univ Sch Comp Edinburgh EH10 5DT Midlothian Scotland

One of the most recent challenging issues of pattern recognition and artificial intelligence is Arabic text recognition. This research topic is still a pervasive and unaddressed research field, because of several factors. Complications arise due to the cursive nature of the Arabic writing, character similarities, unlimited vocabulary, use of multi-size and mixed-fonts, etc. To handle these challenges, an automatic Arabic text recognition requires building a robust system by computing discriminative features and applying a rigorous classifier together to achieve an improved performance. In this work, we introduce a new deep learning based system that recognizes Arabic text contained in images. We propose a novel hybrid network, combining a Bag-of-Feature (BoF) framework for feature extraction based on a deep sparse auto-encoder (SAE), and Hidden Markov Models (HMMs), for sequence recognition. Our proposed system, termed BoF-deep SAE-HMM, is tested on four datasets, namely the printed Arabic line images Printed KHATT (P-KHATT), the benchmark printed word images Arabic Printed Text Image (APTI), the benchmark handwritten Arabic word images IFN/ENIT, and the benchmark handwritten digits images Modified National Institute of Standards and Technology (MNIST).

关键词： Text recognition Feature extraction Hidden Markov models Image segmentation Dictionaries Visualization Optical character recognition software Arabic text recognition feature learning bag of features sparse auto-encoder hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

A sparse auto-encoder method based on compressed sensing and wavelet packet energy entropy for rolling bearing intelligent fault diagnosis

引用

JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY 2020年第4期34卷 1445-1458页

作者： Shi, Peiming Guo, Xiaoci Han, Dongying Fu, Rongrong Yanshan Univ Sch Elect Engn Qinhuangdao 066004 Hebei Peoples R China Yanshan Univ Sch Vehicles & Energy Qinhuangdao 066004 Hebei Peoples R China

Improving diagnostic efficiency and shortening diagnostic time is important for improving the reliability and safety of rotating machinery, and has received more and more attention. When using intelligent diagnostic methods to diagnose bearing faults, the increasingly complex working conditions and the huge amount of data make it a great challenge to diagnose fault quickly and effectively. In this paper, a novel fault diagnosis method based on sparse auto-encoder (SAE), combined with compression sensing (CS) and wavelet packet energy entropy (WPEE) for feature dimension reduction is proposed. Firstly, vibration signals of each fault type are projected linearly through compressed sensing to obtain compressed signals, which are merged into a low-dimensional compressed signal matrix of multiple fault types. Secondly, the WPEE of low-dimensional compressed signal matrix of multi-fault type is determined, and the eigenvector matrix of bearing fault diagnosis is formed, which greatly reduces the dimension of the eigenvector matrix. Finally, SAE are constructed by adding sparse penalty to auto-encoder (AE) for high-level feature learning and bearing fault classification, and it not only further learns the high-level features of data, but also reduces the feature dimension. Compared with traditional feature extraction methods and the standard deep learning method, the proposed method not only guarantees high accuracy, but also greatly reduces the diagnosis time.

关键词： Intelligent diagnosis Rolling bearing Compressed sensing sparse auto-encoder Wavelet packet energy entropy

来源：评论

学校读者我要写书评

暂无评论

Rolling bearing fault severity identification using deep sparse auto-encoder network with noise added sample expansion

引用

PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART O-JOURNAL OF RISK AND RELIABILITY 2017年第6期231卷 666-679页

作者： Chen, Renxiang Chen, Siyang He, Miao He, David Tang, Baoping Chongqing Jiaotong Univ Sch Mechatron & Vehicle Engn Chongqing Peoples R China Sichuan Univ Sch Aeronaut & Astronaut Chengdu Sichuan Peoples R China Univ Illinois Dept Mech & Ind Engn Chicago IL USA Northeastern Univ Minist Educ Key Lab Vibrat & Control Aero Prop Syst Shenyang Liaoning Peoples R China Northeastern Univ Sch Mech Engn & Automat Shenyang Liaoning Peoples R China Chongqing Univ State Key Lab Mech Transmiss Chongqing Peoples R China

This article presents a rolling bearing fault severity identification methodology that aims to adaptively extract fault severity features and intelligently identify the fault severity. The presented method is developed based on a deep sparse auto-encoder network trained with noise added sample expansion. A sparse auto-encoder is a learning algorithm that is capable of performing unsupervised learning of the inner structure and characters of source data. However, even though the original shallow structure of the sparse auto-encoders is capable of extracting the features, they do not have the capability for fault and severity classification. By stacking multiple sparse auto-encoders with a classifier layer, a deep sparse auto-encoder network with the ability of fault severity feature extraction and intelligent severity identification can be obtained. After unsupervised layer-wise self-learning and supervised fine-tuning, the designed deep sparse auto-encoder network can perform severity identification with automatically extracted fault features. Also, to overcome the issue of overfitting caused by limited number of training samples and stacked structure with numerous neurons and layers in a deep sparse auto-encoder network, Gaussian noises are added into the training samples to train the deep sparse auto-encoder network. Using deep sparse auto-encoder network for rolling bearing fault severity identification, the overfitting phenomenon can be retrained to increase the robustness of the network. The performance of the presented method is validated using bearing fault datasets that contain different levels of bearing severity and bearing life stages and compared with other methods. In comparison with recent solutions developed using deep learning approaches, the advantages of the presented method are that it does not require any pre-processing of the vibration data and provides a more robust diagnostic performance.

关键词： Rolling bearing fault severity identification deep learning sparse auto-encoder noise added samples

来源：评论

学校读者我要写书评

暂无评论

A novel SSD fault detection method using GRU-based sparse auto-encoder for dimensionality reduction

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2022年第4期43卷 4929-4946页

作者： Wang, Yufei Dong, Xiaoshe Wang, Longxiang Chen, Weiduo Chen, Heng Xi An Jiao Tong Univ Xian Ning West Rd 28 Xian 710049 Shaanxi Peoples R China

In recent years, with the development of flash memory technology, storage systems in large data centers are typically built upon thousands or even millions of solid-state drives (SSDs). Therefore, the failure of SSDs is inevitable. An SSD failure may cause unrecoverable data loss or unavailable system service, resulting in catastrophic results. Active fault detection technologies are able to detect device problems in advance, so it is gaining popularity. Recent trends have turned toward applying AI algorithms based on SSD SMART data for fault detection. However, SMART data of new SSDs contains a large number of features, and the high dimension of data features results in poor accuracy of AI algorithms for fault detection. To tackle the above problems, we improve the structure of traditional auto-encoder (AE) based on GRU and propose an SSD fault detection method - GAL based on dimensionality reduction with Gated Recurrent Unit (GRU) sparse autoencoder (GRUAE) by combining the temporal characteristics of SSD SMART data. The proposed method trains the GRUAE model with SSD SMART data firstly, and then adopts the encoder of GRUAE model as the dimensionality reduction tool to reduce the original high-dimensional SSD SMART data, aiming at reducing the influence of noise features in original SSD SAMRT data and highlight the features more relevant to data characteristics to improve the accuracy of fault detection. Finally, LSTM is adopted for fault detection with low-dimensional SSDSMART data. Experimental results on real SSD dataset from Alibaba show that the fault detection accuracy of various AI algorithms can be improved by varying degrees after dimensionality reduction with the proposed method, and GAL performs best among all methods.

关键词： Fault detection dimensionality reduction sparse auto-encoder solid state drives gated recurrent unit

来源：评论

学校读者我要写书评

暂无评论

A sparse auto-encoder-based deep neural network approach for induction motor faults classification

引用

MEASUREMENT 2016年 89卷 171-178页

作者： Sun, Wenjun Shao, Siyu Zhao, Rui Yan, Ruqiang Zhang, Xingwu Chen, Xuefeng Southeast Univ Sch Instrument Sci & Engn Nanjing 210096 Jiangsu Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Nanyang Ave Singapore 639798 Singapore Xi An Jiao Tong Univ Collaborat Innovat Ctr High End Mfg Equipment Xian 710049 Peoples R China

This paper presents a deep neural network (DNN) approach for induction motor fault diagnosis. The approach utilizes sparse auto-encoder (SAE) to learn features, which belongs to unsupervised feature learning that only requires unlabeled measurement data. With the help of the denoising coding, partial corruption is added into the input of the SAE to improve robustness of feature representation. Features learned from the SAE are then used to train a neural network classifier for identifying induction motor faults. In addition, to prevent overfitting during the training process, a recently developed regularization method called "dropout" which has been proved to be very effective in neural network was employed. An experiment performed on a machine fault simulator indicates that compared with traditional neural network, the SAE-based DNN can achieve superior performance for feature learning and classification in the field of induction motor fault diagnosis. (C) 2016 Elsevier Ltd. All rights reserved.

关键词： sparse auto-encoder Deep neural network Fault diagnosis Denoising Dropout

来源：评论

学校读者我要写书评

暂无评论

A novel method of diagnosing premature ventricular contraction based on sparse auto-encoder and softmax regression

引用

BIO-MEDICAL MATERIALS AND ENGINEERING 2015年第Sup1期26卷 S1549-S1558页

作者： Yang, Jianli Bai, Yang Li, Guojun Liu, Ming Liu, Xiuling Hebei Univ Coll Elect & Informat Engn Key Lab Digital Med Engn Hebei Prov Baoding 071000 Hebei Peoples R China

Premature ventricular contraction (PVC) is one of the most serious arrhythmias. Without early diagnosis and proper treatment, PVC can result in significant complications. In this paper, a novel feature extraction method based on a sparse auto-encoder (SAE) and softmax regression (SR) classifier was used to differentiate PVCs from other common Non-PVC rhythms, including normal sinus (N), left bundle branch block (LBBB), right bundle branch block (RBBB), atrial premature contraction (APC), and paced beat (PB) rhythms. The proposed method was analyzed using 40 ECG records obtained from the MIT-BIH Arrhythmia Database. The proposed method exhibited an overall accuracy of 99.4%, with a PVC recognition sensitivity and positive predictability of 97.9% and 91.8%, respectively.

关键词： PVC diagnosis sparse auto-encoder softmax regression feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach to Network Intrusion Detection Using a Proposed Supervised sparse auto-encoder and SVM

引用

IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF ELECTRICAL ENGINEERING 2022年第3期46卷 829-846页

作者： Ghorbani, Ali Fakhrahmad, Seyed Mostafa Shiraz Univ Sch Elect & Comp Engn Dept Comp Sci & Engn & IT Shiraz Iran

Due to the increasing use of communication technologies for data transmission, security threats have increased over the past decade. One of the essential solutions to detect threats is NIDSs. Over the past few years, much research considered unsupervised feature extraction for NIDS like sparse auto-encoders;however, there is no research on the supervised auto-encoder methods. In this work, we propose a novel supervised sparse auto-encoder, which aims to extract more useful information for classification models than unsupervised methods. The proposed approach validated using NSL-KDD, KDDCUP'99, CICIDS2017 data-sets, in the term of detection rate, and also response time. Experimental results in detection rate and test time are promising. In the case of binary classification, the accuracy of 90. 11% on NSL-KDDTest(+) and 91.21 on CICIDS2017 were achieved, which is a drastic improvement compared to state of the art with the more complex models and unsupervised representation learning models. Also, the result on 5class classification was considered.

关键词： Network intrusion detection Deep learning sparse auto-encoder Supervised auto-encoder

来源：评论

学校读者我要写书评

暂无评论

Estimation of spreading sequences in LC-DS-CDMA signals based on sparse auto-encoder

引用

EVOLUTIONARY INTELLIGENCE 2020年第2期13卷 235-246页

作者： Qiang, Fangfang Zhao, Zhijin Shang, Junna Shen, Lei Hangzhou Dianzi Univ Sch Elect & Informat Hangzhou 310018 Peoples R China Hangzhou Dianzi Univ Sch Commun Engn Hangzhou 310018 Peoples R China Zhejiang Prov Key Lab Informat Proc Commun & Netw Hangzhou 310027 Peoples R China

A method based on a sparse auto-encoder (SAE) network for the estimation of spreading sequences in long-code direct-sequence code-division multiple access (LC-DS-CDMA) signals is proposed. First, a network classification model based on SAE and softmax classifier is established. Next, the effectiveness of the proposed method is verified by estimating Walsh sequences and m sequences. To estimate the spreading sequences, the LC-DS-CDMA signal is divided into fragments. Then, each user's spreading sequence is separated by the fast independent component analysis (Fast-ICA) algorithm, and the amplitude fuzziness is eliminated by the delay-and-multiply method. Finally, the spreading sequences are estimated by the SAE model. Experimental results showed that the proposed algorithm could effectively estimate the spreading sequences of LC-DS-CDMA signals. Compared to the existing matching algorithm and Fast-ICA algorithm, the estimation time required by the proposed algorithm was shorter, and its estimation performance at low signal-to-noise ratios was superior.

关键词： Direct-sequence code-division multiple access Deep learning sparse auto-encoder Blind source separation Signal analysis

来源：评论

学校读者我要写书评

暂无评论

Application of sparse auto-encoder in Handwritten Digit Recognition 18

Application of Sparse auto-encoder in Handwritten Digit Reco...

引用

International Symposium on Big Data and Artificial Intelligence (ISBDAI)

作者： Zhou, Kaihong Qiao, Xinxin Shi, Jingkai Guilin Univ Technol Coll Mech & Control Engn Guilin 541004 Guangxi Peoples R China

ISBN: (纸本)9781450365703

Deep learning and non-supervised learning methods have a wide range of applications in image feature extraction. This article uses MATLAB to train a deep neural network to classify handwritten digital pictures. The deep neural network is formed by stacking multiple sparse auto-encoders, training the data in an unsupervised manner, initializing the weights of the network, and then fine-tuning the network with a reciprocal propagation algorithm. Finally, the images is classified using the soft-max classifier. sparse reduces the number of dimensions effectively, and the back propagation algorithm is optimized on the cost function, leading to the accuracy rate has been greatly improved, and completing the classification of handwritten numbers.

关键词： MATLAB sparse auto-encoder MNIST handwritten digits Soft-max classifier

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：