检索结果-内蒙古大学图书馆

Weighted time series fault diagnosis based on a stacked sparse autoencoder

JOURNAL OF CHEMOMETRICS 2017年第9期31卷 2912,2-16-2912,2-16页

作者： Lv, Feiya Wen, Chenglin Liu, Meiqin Bao, Zhejing Zhejiang Univ Coll Elect Engn Hangzhou 310027 Zhejiang Peoples R China Hangzhou Dianzi Univ Sch Automat Hangzhou 310018 Zhejiang Peoples R China

Most statistical analysis technologies use detection thresholds for fault diagnosis, which often cannot effectively characterize some specific faults in a statistical manner. However, the details and small changes in the faults can be exploited by deep learning-based feature representation. In this paper, we present a weighted time series fault diagnosis method to learn the deep correlations of faults and reduce the loss of fault information. Our model includes 2 key novel properties: (1) It can learn high-level abstract features of faults and the underlying fault patterns, which is particularly efficient for detecting incipient faults;(2) a mathematical framework of stacked sparse autoencoder-based fault diagnosis, with capabilities of multiple nonlinear mapping and complex function approximation, is presented. The monitoring performance was compared with multivariate statistical methods and conventional artificial intelligence methods on the Tennessee Eastman process data set, which is a well-known chemical industrial benchmark. The experimental results showed its performance gain over existing methods, especially for incipient faults that are difficult to detect with traditional technologies. As the details and small changes in the faults can be exploited by deep learning-based feature representation, we present a weighted time series fault diagnosis method. Our model includes 2 key novel properties: (1) It can learn high-level abstract features of faults and the underlying fault patterns, which is particularly efficient for detecting incipient faults;(2) a mathematical framework of stacked sparse auto-encoder (SSAE) -based fault diagnosis, with capabilities of multiple nonlinear mapping and complex function approximation, is presented.

关键词： fault diagnosis feature representation incipient fault stacked sparse autoencoder weighted time series

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction Based on stacked sparse autoencoder and Echo State Network

Remaining Useful Life Prediction Based on Stacked Sparse Aut...

引用

第三十九届中国控制会议

作者： Yinghua Yang Dandan Yao Xiaozhi Liu College of Information Science and Engineering Northeastern University

Nowadays, the prediction of industry components’ remaining useful life（RUL） has already become a hot topic. In this paper, a RUL prediction method based on stacked sparse autoencoder（SAE） and echo state network（ESN） is ***（AE） is an unsupervised learning method that can be used for feature extraction to obtain a health index（HI）. To enhance the performance of the HI, a sparse constraint is added and a stacked structure is used to increase depth. The RUL of the industry components is then predicted using a method that maps directly to the RUL value based on the health factor curve. With the capability of encapsulating dynamic time behavior and saving historical information of input data, ESN is selected as the prediction network. The proposed method is verified using the C-MPASS dataset. The experimental results show that the method has better performance than the stacked AE based method.

关键词： Remaining useful life stacked sparse autoencoder echo state network

来源：评论

学校读者我要写书评

暂无评论

Vertebrae Segmentation via stacked sparse autoencoder from Computed Tomography Images

Vertebrae Segmentation via Stacked Sparse Autoencoder from C...

引用

2019第十一届数字图像处理国际会议

作者： Syed Furqan Qadri Zhiqi Zhao Danni Ai Mubashir Ahmad Yongtian Wang School of Computer Science and Technology Beijing Institute of Technology Beijing Engineering Research Center of Mixed Reality and Advanced Display School of Optics and PhotonicsBeijing Institute of Technology AICFVE of Beijing Film Academy

An accurate vertebrae segmentation in the spine is an essential pre-requisite in many applications of image-based spine assessment,surgical planning,clinical diagnostic treatment,and biomechanical *** this paper,we present the stacked sparse autoencoder（SSAE） model for the segmentation of vertebrae from CT *** the preprocessing step,we extracted overlapped patches from the vertebrae CT images as the inputs of our proposed *** SSAE model was trained in an unsupervised way to learn high-level features from the input pixels of the unlabeled images *** improve the discriminability of the learned features,we further refined the feature representation in a supervised fashion and fine-tuned the whole model by using the feedforward neural network parameters for classifying the overlapped *** then validated our model on a publicly available MICCAI CSI2014 dataset and found that our model outperforms the other state-of-the-art methods.

关键词： Vertebrae segmentation deep learning stacked sparse autoencoder CT images

来源：评论

学校读者我要写书评

暂无评论

Deep network approach with stacked sparse autoencoders in detection of DDoS attacks on SDN-based VANET

引用

IET COMMUNICATIONS 2020年第22期14卷 4089-4100页

作者： Polat, Huseyin Turkoglu, Muammer Polat, Onur Gazi Univ Fac Technol Dept Comp Engn TR-06500 Ankara Turkey Bingol Univ Dept Comp Engn TR-12400 Bingol Turkey

Software-defined network (SDN)-based vehicular ad hoc network (VANET) is an outstanding technology for smart transportation as it increases traffic safety, efficiency, comfort, and manageability. However, despite all its benefits and good performance, SDN-based VANET is vulnerable to attack threats such as distributed denial of service (DDoS). When SDN-based VANET systems are exposed to DDoS attacks, this may affect traffic safety, causing traffic accidents and deaths. Therefore, the relevant security threats need to be addressed before integrating the SDN-based VANETs into smart transportation systems. In this study, the stacked sparse autoencoder (SSAE) + Softmax classifier deep network model is proposed to detect DDoS attacks targeting SDN-based VANETs. The features in the dataset obtained from the SDN-based VANET were reduced dimensionally utilising SSAE, and the most significant features were obtained. Then, these features were used as input into the Softmax classifier. According to the experimental results, the best accuracy scores were calculated as 96.9% using the four-layer SSAE + Softmax classifier deep network model proposed. When compared, the results demonstrate the SSAE + Softmax classifier deep network model proposed can obtain better results in the classification of DDoS attacks and is more successful than the other machine learning classifiers.

关键词： computer network security road safety road traffic neural nets vehicular ad hoc networks road accidents intelligent transportation systems software defined networking traffic safety SDN‐ based VANET systems DDoS attacks stacked sparse autoencoder four‐ layer SSAE plus Softmax classifier deep network model software‐ defined network‐ based vehicular ad hoc network deep network approach distributed denial of service attacks smart transportation systems traffic accidents

来源：评论

学校读者我要写书评

暂无评论

Automated Nuclei Detection in Serous Effusion Cytology with stacked sparse autoencoders 26

Automated Nuclei Detection in Serous Effusion Cytology with ...

引用

26th IEEE Signal Processing and Communications Applications Conference (SIU)

作者： Baykal, Elif Dogan, Hulya Ercin, Mustafa Emre Ersoz, Safak Ekinci, Murat Karadeniz Tech Univ Bilgisayar Muhendisligi Bolumu Trabzon Turkey Karadeniz Tech Univ Tibbi Patol Bolumu Trabzon Turkey

ISBN: (纸本)9781538615010

Serous effusion is frequently encountered specimen type in (cyto)pathological assessment. However, this assessment is time-consuming and leads to variability among pathologists. The cell nuclei is seen as the corner stone for diagnostic purposes in automatic analysis of cytopathological images. In this paper, a stacked sparse autoencoder (SSAE) is proposed for nuclei detection in serous effusion cytology. SSAE is an unsupervised deep learning method which learns high-level features from just pixel intensities alone in order to identify distinguishing features of nuclei. High-level features, obtained via the autoencoder, are then subsequently fed to a softmax classifier which categorizes each patch as nuclei or non-nuclei. With a detection rate of 98.3% based on images of serous effusion cytology, proposed method shows good performance.

关键词： Serous effusion cytopathological assessment nuclei detection stacked sparse autoencoder unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

DSSAE-BBOA: deep learning-based weather big data analysis and visualization

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2021年第18期80卷 27471-27493页

作者： Rao, Madhukar G. Dharavath, Ramesh Indian Sch Mines Indian Inst Technol Dept Comp Sci & Engn Dhanbad 826004 Jharkhand India

The weather forecasting process is used to predict the future atmospheric condition of a specified location. The evolution of the big data era gives the chances to significantly increase the prediction accuracy of weather conditions. In this paper, a deep learning-based stacked sparse autoencoder (DSSAE) has been proposed for predicting the weather condition of a particular area. This model requires a pre-processing approach to obtain essential data from big weather data and increase the prediction model's speed. For this, the principal component analysis (PCA) is utilized to reduce dimensionality and extraction of features with more significant variance. Also, it integrates the feature selection algorithm based on Binary Butterfly Optimization Algorithm (BBOA) along with a deep stack autoencoder to improve prediction accuracy. The proposed model is validated using the weather data taken from the division of weather underground for short term and long term weather prediction. The simulation consequences illustrate that the proposed model overtakes the existing models in terms of computation time, accuracy and error rate.

关键词： Weather forecasting Feature selection Optimization stacked sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Infrared and Visible Image Fusion Based on Deep Decomposition Network and Saliency Analysis

引用

IEEE TRANSACTIONS ON MULTIMEDIA 2021年 24卷 3314-3326页

作者： Jian, Lihua Rayhana, Rakiba Ma, Ling Wu, Shaowu Liu, Zheng Jiang, Huiqin Zhengzhou Univ Sch Informat Engn Zhengzhou 450001 Henan Peoples R China Univ British Columbia Sch Engn Kelowna BC V1V 1V7 Canada Wuhan Univ Sch Comp Sci Wuhan 430072 Hubei Peoples R China

Traditional image fusion focuses on selecting an effective decomposition approach to extract representative features from the source image and attempts to find appropriate fusion rules to merge extracted features respectively. However, the existing image decomposition tools are mostly based on kernels or global energy-optimized functions limiting the performance of the wide range of image contents. This paper proposes a novel infrared and visible image fusion method based on deep decomposition network and saliency analysis (named DDNSA). First, the modified residual dense network (MRDN) is trained with a publicly available dataset to learn the decomposition process. Second, the structure and texture features of source images are separated by the trained decomposition network. Then, according to the characteristics of the above features, we construct the combination of local and global saliency maps by using stacked sparse autoencoder and visual saliency mechanism to fuse the structural features. Besides, we propose a bi-direction edge-strength fusion strategy for merging the texture features. Finally, the resultant image is reconstructed by combining the fused structure and texture features. The experimental results confirm that our proposed method outperforms the state-of-the-art methods in both visual perception and objective evaluation.

关键词： Feature extraction Image fusion Task analysis Fuses Visualization Image edge detection Data mining Bi-direction edge-strength deep decomposition network image fusion stacked sparse autoencoder visual saliency mechanism

来源：评论

学校读者我要写书评

暂无评论

Big data driven jobs remaining time prediction in discrete manufacturing system: a deep learning-based approach

引用

INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH 2020年第9期58卷 2751-2766页

作者： Fang, Weiguang Guo, Yu Liao, Wenhe Ramani, Karthik Huang, Shaohua Nanjing Univ Aeronaut & Astronaut Sch Mech & Elect Engn Nanjing Jiangsu Peoples R China Purdue Univ Sch Mech Engn W Lafayette IN 47907 USA Nanjing Univ Sci & Technol Sch Mech Engn Nanjing Jiangsu Peoples R China

Implementing advanced big data (BD) analytic is significant for successful incorporation of artificial intelligence in manufacturing. With the widespread deployment of smart sensors and internet of things (IOT) in the job shop, there is an increasing need for handling manufacturing BD for predictive manufacturing. In this study, we conceive the jobs remaining time (JRT) prediction during manufacturing execution based on deep learning (DL) with production BD. We developed a procedure for JRT prediction that includes three parts: raw data collection, candidate dataset design and predictive modelling. First, the historical production data are collected by the widely deployed IOT in the job shop. Then, the candidate dataset is formalised to capture various contributory factors for JRT prediction. Further, a DL model named stacked sparse autoencoder (S-SAE) is constructed to learn representative features from high dimensional manufacturing BD to make robust and accurate JRT prediction. Our work represents the first DL model for the JRT prediction at run time during production. The proposed methods are applied in a large-scale job shop that is equipped with 44 machine tools and produces 13 types of parts. Lastly, the experimental results show the S-SAE model has higher accuracy than previous linear regression, back-propagation network, multi-layer network and deep belief network in JRT prediction.

关键词： big data job shop jobs remaining time prediction stacked sparse autoencoder deep learning

来源：评论

学校读者我要写书评

暂无评论

Deep learning decision fusion for the classification of urban remote sensing data

引用

JOURNAL OF APPLIED REMOTE SENSING 2018年第1期12卷

作者： Abdi, Ghasem Samadzadegan, Farhad Reinartz, Peter Univ Tehran Fac Surveying & Geospatial Engn Coll Engn Tehran Iran German Aerosp Ctr DLR Remote Sensing Technol Inst Dept Photogrammetry & Image Anal Wessling Germany

Multisensor data fusion is one of the most common and popular remote sensing data classification topics by considering a robust and complete description about the objects of interest. Furthermore, deep feature extraction has recently attracted significant interest and has become a hot research topic in the geoscience and remote sensing research community. A deep learning decision fusion approach is presented to perform multisensor urban remote sensing data classification. After deep features are extracted by utilizing joint spectral-spatial information, a soft-decision made classifier is applied to train high-level feature representations and to fine-tune the deep learning framework. Next, a decision-level fusion classifies objects of interest by the joint use of sensors. Finally, a context-aware object-based postprocessing is used to enhance the classification results. A series of comparative experiments are conducted on the widely used dataset of 2014 IEEE GRSS data fusion contest. The obtained results illustrate the considerable advantages of the proposed deep learning decision fusion over the traditional classifiers. (C) 2018 Society of Photo-Optical Instrumentation Engineers (SPIE)

关键词： convolutional neural network decision-level fusion deep features deep learning stacked sparse autoencoder thermal hyperspectral

来源：评论

学校读者我要写书评

暂无评论

Nondestructive evaluation of bonding quality of dual-layer coatings based on the multi-feature ultrasonic method

引用

APPLIED ACOUSTICS 2024年 224卷

作者： Fan, Shaorui Yuan, Maodan Xu, Jianlin Song, Yongfeng Chen, Yan Ji, Xuanrong Guangdong Univ Technol State Key Lab Precis Elect Mfg Technol & Equipment Guangzhou 510004 Peoples R China

Ultrasound has been extensively utilized to evaluate the bonding quality of coatings. However, current ultrasonic methods based on single temporal or spectral feature cannot accurately characterize the bonding quality within industrial coatings, especially for potential debonding at different layers. This paper proposed an ultrasonic method with multiple temporal and spectral features to evaluate the bonding condition of dual-layer coatings. Ultrasonic features were automatically extracted based on stacked sparse autoencoder (SSAE) to compare with the conventional selected features. Firstly, numerical simulations were carried out to analyze the variation of ultrasonic signals with different stiffnesses at topcoat and primer interfaces. Two temporal and three spectral features were manually extracted and show high sensitivity to different bonding conditions of the two interfaces. Meanwhile, a SSAE network was designed to automatically extract ultrasonic features. The high correlation between the manually and automatically extracted features demonstrates its effectiveness of automatic feature extraction via SSAE. Then, a 50 MHz ultrasonic pulse-echo system was applied to collect signals from 115 coating samples of laptop shell. Four sets of ultrasonic features were extracted via manual method and SSAE networks. Principal components analysis was then employed to reduce the feature space and support vector machine was applied to distinguish topcoat debonding and primer debonding from the intact coatings. The results show that the feature set including 64 temporal and spectral features extracted by SSAE exhibit the best classification with an accuracy of 95.652 %. This proposed multi-feature ultrasonic method can accurately assess the bonding quality of different interfaces in the multi-layer coatings.

关键词： Dual -layer coating Topcoat debonding Primer debonding Ultrasonic features stacked sparse autoencoder Support vector machine

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：