检索结果-内蒙古大学图书馆

Transformer Fault Diagnosis Using Self-Powered RFID Sensor and Deep Learning Approach

IEEE SENSORS JOURNAL 2018年第15期18卷 6399-6411页

作者： Wang, Tao He, Yigang Li, Bing Shi, Tiancheng Hefei Univ Technol Sch Elect Engn & Automat Hefei 230009 Anhui Peoples R China Wuhan Univ Sch Elect Engn Wuhan 430072 Hubei Peoples R China

This paper introduces a novel fault diagnosis approach for transformer based on self-powered radio-frequency identification (RFID) sensor and deep learning technique. The exploited RFID sensor tag with functionalities of signal collection, data storage, and wireless transmission employs surrounding electromagnetic field as power source. A customized power management circuit, including ac-dc converter, supercapacitor, and its corresponding charging circuit, is presented to guarantee constant de power for the sensor tag. The measured vibration signal contains miscellaneous noises and is characterized as nonlinearity and nonstationarity, so it is difficult to extract robust and useful features by using traditional feature extraction approaches. As one of the deep learning techniques, stacked denoising autoencoder (SDA) shows satisfactory performance in learning robust features from complex signal. Hence, in this paper, SDA approach is employed to learn robust and discriminative features from measured signals. The experimental results show that the presented power supply can generate 2.5-V de voltage, which is the rated operating voltage for the rest of the sensor tag. The developed sensor tag can achieve a reliable communication distance of 173 m in the test environment. Furthermore, the SDA approach shows satisfactory performance in learning robust and discriminative features. Experimental results indicate that the presented approach is effective and time-saving in terms of fault diagnosis for transformer winding and core.

关键词： Transformer fault diagnosis self-powered RFID sensor tag stacked denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Image-based mains signal disaggregation and load recognition

引用

COMPLEX & INTELLIGENT SYSTEMS 2021年第2期7卷 901-927页

作者： Matindife, Liston Sun, Yanxia Wang, Zenghui Univ Johannesburg Dept Elect & Elect Engn Sci ZA-2006 Auckland Pk South Africa Univ South Africa Dept Elect & Min Engn ZA-1710 Florida South Africa

The mains signal is a complex fusion of various electrical equipment load signals in a building. In the non-intrusive load monitoring recognition, our main aim is to be able to extract as much load features as possible from the complex aggregate mains signal in a simpler way through a computer vision-based approach as opposed to the powers series signal approach. Power series methods, which are one dimensional in nature, suffer from poor aggregate and load signal feature localization necessitating a larger training dataset spanning very long time periods and normally require signal formatting and pre-processing. We use Gramian angular summation fields to transform the power series into a reduced image dataset that contains a rich set of localized signal features. A computer vision approach allows us to capture as much information as possible, and then propose an image-based mains load recognition system with high performance. In this paper for the entire recognition system, we use convolutional neural networks that very well adapted to vision recognition. The load signal image disaggregation is achieved through the powerful stacked denoising autoencoder noise extraction network. To test the proposed system, some simulations and comparisons are carried out and the results show that our easier to handle method can achieve acceptable performance.

关键词： Image disaggregation Mains supply load recognition Convolutional neural network stacked denoising autoencoder Image recognition

来源：评论

学校读者我要写书评

暂无评论

A Network Attack Detection Method Using SDA and Deep Neural Network Based on Internet of Things

引用

INTERNATIONAL JOURNAL OF WIRELESS INFORMATION NETWORKS 2020年第2期27卷 209-214页

作者： Li, Jingwei Sun, Bo Henan Inst Technol Coll Comp Sci & Technol Xinxiang 453002 Henan Peoples R China

Aiming at the deficiency of network attack detection, a network attack detection method based on deep neural network is proposed. Firstly, the deep neural network technology is used to study the self-adaptive identification method of the security state, intelligently discriminate the security index of the network, recall comparative learning based on historical data, and establish the classification and identification database of network security. Then, according to the information of security classification and identification database, the corresponding state risk assessment system is mapped. Based on the risk intensity, different levels of early warnings are given. Finally, experimental simulation analysis is carried out to demonstrate the effectiveness of the proposed method. The simulation results show that the proposed method can actively send out early warning before the network is attacked, which obtains a high accuracy of early warning.

关键词： Internet of Things Deep neural network Network attack Security early warning stacked denoising autoencoder Unsupervised feature learning

来源：评论

学校读者我要写书评

暂无评论

Query-by-example surgical activity detection

引用

INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY 2016年第6期11卷 987-996页

作者： Gao, Yixin Vedula, S. Swaroop Lee, Gyusung I. Lee, Mija R. Khudanpur, Sanjeev Hager, Gregory D. Johns Hopkins Univ Dept Comp Sci Whiting Sch Engn Baltimore MD 21218 USA Johns Hopkins Univ Sch Med Dept Surg Baltimore MD 21287 USA Johns Hopkins Univ Dept Elect & Comp Engn Whiting Sch Engn Baltimore MD 21218 USA

Easy acquisition of surgical data opens many opportunities to automate skill evaluation and teaching. Current technology to search tool motion data for surgical activity segments of interest is limited by the need for manual pre-processing, which can be prohibitive at scale. We developed a content-based information retrieval method, query-by-example (QBE), to automatically detect activity segments within surgical data recordings of long duration that match a query. The example segment of interest (query) and the surgical data recording (target trial) are time series of kinematics. Our approach includes an unsupervised feature learning module using a stacked denoising autoencoder (SDAE), two scoring modules based on asymmetric subsequence dynamic time warping (AS-DTW) and template matching, respectively, and a detection module. A distance matrix of the query against the trial is computed using the SDAE features, followed by AS-DTW combined with template scoring, to generate a ranked list of candidate subsequences (substrings). To evaluate the quality of the ranked list against the ground-truth, thresholding conventional DTW distances and bipartite matching are applied. We computed the recall, precision, F1-score, and a Jaccard index-based score on three experimental setups. We evaluated our QBE method using a suture throw maneuver as the query, on two tool motion datasets (JIGSAWS and MISTIC-SL) captured in a training laboratory. We observed a recall of 93, 90 and 87 % and a precision of 93, 91, and 88 % with same surgeon same trial (SSST), same surgeon different trial (SSDT) and different surgeon (DS) experiment setups on JIGSAWS, and a recall of 87, 81 and 75 % and a precision of 72, 61, and 53 % with SSST, SSDT and DS experiment setups on MISTIC-SL, respectively. We developed a novel, content-based information retrieval method to automatically detect multiple instances of an activity within long surgical recordings. Our method demonstrated adequate recall across d

关键词： Query-by-example stacked denoising autoencoder Asymmetric subsequence dynamic time warping Surgical data indexing Surgical activity detection

来源：评论

学校读者我要写书评

暂无评论

Semisupervised learning using denoising autoencoders for brain lesion detection and segmentation

引用

JOURNAL OF MEDICAL IMAGING 2017年第4期4卷 041311页

作者： Alex, Varghese Vaidhya, Kiran Thirunavukkarasu, Subramaniam Kesavadas, Chandrasekharan Krishnamurthi, Ganapathy Indian Inst Technol Madras Dept Engn Design Madras Tamil Nadu India Sree Chitra Tirunal Inst Med Sci & Technol Dept Radiol Trivandrum Kerala India

The work explores the use of denoising autoencoders (DAEs) for brain lesion detection, segmentation, and false-positive reduction. stacked denoising autoencoders (SDAEs) were pretrained using a large number of unlabeled patient volumes and fine-tuned with patches drawn from a limited number of patients (n = 20, 40, 65). The results show negligible loss in performance even when SDAE was fine-tuned using 20 labeled patients. Low grade glioma (LGG) segmentation was achieved using a transfer learning approach in which a network pretrained with high grade glioma data was fine-tuned using LGG image patches. The networks were also shown to generalize well and provide good segmentation on unseen BraTS 2013 and BraTS 2015 test data. The manuscript also includes the use of a single layer DAE, referred to as novelty detector (ND). ND was trained to accurately reconstruct nonlesion patches. The reconstruction error maps of test data were used to localize lesions. The error maps were shown to assign unique error distributions to various constituents of the glioma, enabling localization. The ND learns the nonlesion brain accurately as it was also shown to provide good segmentation performance on ischemic brain lesions in images from a different database. (c) 2017 Society of Photo-Optical Instrumentation Engineers (SPIE).

关键词： brain lesion gliomas magnetic resonance imaging deep learning stacked denoising autoencoder denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

A deep learning ensemble approach for crude oil price forecasting

引用

ENERGY ECONOMICS 2017年 66卷 9-16页

作者： Zhao, Yang Li, Jianping Yu, Lean Chinese Acad Sci Inst Policy & Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Beijing Univ Chem Technol Sch Econ & Management Beijing Peoples R China

As crude oil price is influenced by numerous factors, capturing its behavior precisely is quite challenging, and thus leads to the difficulty of forecasting. In this study, a deep learning ensemble approach is proposed to deal with this problem. In our approach, two techniques are utilized. One is an advanced deep neural network model named stacked denoising autoencoders (SDAE) which is used to model the nonlinear and complex relationships of oil price with its factors. The other is a powerful ensemble method named bootstrap aggregation (bagging) which generates multiple data sets for training a set of base models (SDAEs). Our approach combines the merits of these two techniques and is especially suitable for oil price forecasting. In the empirical study, the WTI crude oil price series are investigated and 198 economic series are used as exogenous variables. Our approach is tested against some competing approaches and shows superior forecasting ability that is statistically proved by three tests. (C) 2017 ElsevierB.V. All rights reserved.

关键词： Crude oil price forecasting Deep leaming Ensemble learning stacked denoising autoencoder Bagging Multivariate forecasting

来源：评论

学校读者我要写书评

暂无评论

Attention neural collaboration filtering based on GRU for recommender systems

引用

COMPLEX & INTELLIGENT SYSTEMS 2021年第3期7卷 1367-1379页

作者： Xia, Hongbin Luo, Yang Liu, Yuan Jiangnan Univ Sch Artificial Intelligence & Comp Sci Wuxi Jiangsu Peoples R China Jiangsu Key Lab Media Design & Software Technol Wuxi Jiangsu Peoples R China

The collaborative filtering method is widely used in the traditional recommendation system. The collaborative filtering method based on matrix factorization treats the user's preference for the item as a linear combination of the user and the item latent vectors, and cannot learn a deeper feature representation. In addition, the cold start and data sparsity remain major problems for collaborative filtering. To tackle these problems, some scholars have proposed to use deep neural network to extract text information, but did not consider the impact of long-distance dependent information and key information on their models. In this paper, we propose a neural collaborative filtering recommender method that integrates user and item auxiliary information. This method fully integrates user-item rating information, user assistance information and item text assistance information for feature extraction. First, stacked denoising Auto Encoder is used to extract user features, and Gated Recurrent Unit with auxiliary information is used to extract items' latent vectors, respectively. The attention mechanism is used to learn key information when extracting text features. Second, the latent vectors learned by deep learning techniques are used in multi-layer nonlinear networks to learn more abstract and deeper feature representations to predict user preferences. According to the verification results on the MovieLens data set, the proposed model outperforms other traditional approaches and deep learning models making it state of the art.

关键词： stacked denoising autoencoder Gated recurrent unit Attention mechanism Collaborative filtering Auxiliary information

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Object Tracking using CNN and SDAE

A Comparative Study of Object Tracking using CNN and SDAE

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yang, Wei Wang, Wei Gao, Yang Jin, Zhanpeng SUNY Binghamton Dept Elect & Comp Engn Binghamton NY 13902 USA Univ Buffalo SUNY Dept Comp Sci & Engn New York NY 14260 USA

ISBN: (纸本)9781509060146

Object tracking which refers to automatic estimation of the trajectory is a challenging problem. To track the object robustly and efficiently, we explored an autonomous object tracking methodological framework that adopts the deep learning architectures, specifically the convolutional neural network (CNN) and the stacked denoising autoencoder (SDAE), as opposed to the most frequently used tracking algorithms that only learn the appearance of the tracked object. Moreover, we conduct a comparative study of both approaches in terms of tracking accuracy and efficiency. The results show that the features learned by both CNN and SDAE are very supportive in object tracking problem and the detailed comparisons are demonstrated in this work.

关键词： object tracking convolutional neural network stacked denoising autoencoder particle filter

来源：评论

学校读者我要写书评

暂无评论

A multi-label Hyperspectral image classification method with deep learning features 16

A multi-label Hyperspectral image classification method with...

引用

8th International Conference on Internet Multimedia Computing and Service (ICIMCS)

作者： Wang, Cong Zhang, Peng Zhang, Yanning Zhang, Lei Wei, Wei Northwestern Polytech Univ Sch Comp Sci & Technol Xian 710072 Peoples R China

ISBN: (纸本)9781450348508

Hyperspectral image (HSI) classification is an important application of HSI analysis, which aims at assigning a class label to each pixel. However, considering that mixed pixels commonly exist in HSI, assigning a unique label to each pixel is imprecise. To better analysis the scene imaged in an HSI, we propose a multi-label hyperspectral image classification approach based on deep learning in this study. First, stacked denoising autoencoder (SDAE) method is used to extract deep features for each pixel without supervision, which can well represent the nonlinearity of the mixed pixels in a high dimensional feature space. Then, multi-label logistic regression method assigns each pixel multi labels. Experimental results on the synthetic data, real hyperspectral data and down-sampling hyperspectral data demonstrate the effectiveness of the proposed method.

关键词： stacked denoising autoencoder logistic regression hyperspectral image multi-label classification

来源：评论

学校读者我要写书评

暂无评论

Deep Feature Learning for Pulmonary Nodule Classification in a Lung CT 4

Deep Feature Learning for Pulmonary Nodule Classification in...

引用

4th International Winter Conference on Brain-Computer Interface (BCI)

作者： Kim, Bum-Chae Sung, Yu Sub Suk, Heung-Il Korea Univ Dept Brain & Cognit Engn Seoul South Korea Asan Med Ctr Dept Radiol Biomed Imaging Infrastruct Seoul South Korea

ISBN: (纸本)9781467378413

In this paper, we propose a novel method of identifying pulmonary nodules in a lung CT. Specifically, we devise a deep neural network by which we extract abstract information inherent in raw hand-crafted imaging features. We then combine the deep learned representations with the original raw imaging features into a long feature vector. By taking the combined feature vectors, we train a classifier, preceded by a feature selection via t-test. To validate the effectiveness of the proposed method, we performed experiments on our in-house dataset of 20 subjects;3,598 pulmonary nodules (malignant: 178, benign: 3,420), which were manually segmented by a radiologist. In our experiments, we achieved the maximal accuracy of 95.5%, sensitivity of 94.4%, and AUC of 0.987, outperforming the competing method.

关键词： Pulmonary nodule classification Lung cancer Deep learning stacked denoising autoencoder

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：