检索结果-内蒙古大学图书馆

Non-Mutually Exclusive Deep Neural Network Classifier for Combined Modes of Bearing Fault Diagnosis

SENSORS 2018年第4期18卷 1129-1129页

作者： Duong, Bach Phi Kim, Jong-Myon Univ Ulsan Sch Elect Elect & Comp Engn Ulsan 44610 South Korea

The simultaneous occurrence of various types of defects in bearings makes their diagnosis more challenging owing to the resultant complexity of the constituent parts of the acoustic emission (AE) signals. To address this issue, a new approach is proposed in this paper for the detection of multiple combined faults in bearings. The proposed methodology uses a deep neural network (DNN) architecture to effectively diagnose the combined defects. The DNN structure is based on the stacked denoising autoencoder non-mutually exclusive classifier (NMEC) method for combined modes. The NMEC-DNN is trained using data for a single fault and it classifies both single faults and multiple combined faults. The results of experiments conducted on AE data collected through an experimental test-bed demonstrate that the DNN achieves good classification performance with a maximum accuracy of 95%. The proposed method is compared with a multi-class classifier based on support vector machines (SVMs). The NMEC-DNN yields better diagnostic performance in comparison to the multi-class classifier based on SVM. The NMEC-DNN reduces the number of necessary data collections and improves the bearing fault diagnosis performance.

关键词： bearing fault diagnosis combined mode classification deep neural network stacked denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Day-ahead Wind Power Forecasting Based on Single Point Clustering

Day-ahead Wind Power Forecasting Based on Single Point Clust...

引用

第37届中国控制会议

作者： Song Jiakang Peng Yonggang Xia Yanghong College of Electrical Engineering Zhejiang University

Wind power forecasting is significant for the security and economy of the power system. For the better robustness and accuracy, various clustering-based forecasting methods have been proposed. However, most of them utilize clustering on a daily sample basis usually called day clustering, which mainly exploits daily features of numerical weather prediction(NWP) and meets some limitations. In this paper, a single point clustering method is proposed to enhance the performance of day-ahead forecasting, which is conducted on a point sample basis through K-means algorithm. First, the extraction of clustering features is optimized. Being different from the commonly used clustering features, the high-order features extracted from NWP is used for the proposed method based on stacked denoising autoencoder(SDAE). Then, both the compactness within the single group and the separation among the multiple groups are enhanced, which is realized through choosing the number of clusters to maximize silhouette. In the case study, the proposed method is compared to the conventional day clustering method with two types of features and the single point clustering with the commonly used clustering features of NWP. Through the results, it is shown that the proposed method performs better than the other comparative methods.

关键词： Day-ahead forecasting single point clustering stacked denoising autoencoder silhouette K-means

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Data Reduction in Quantum State Tomography

Machine Learning for Data Reduction in Quantum State Tomogra...

引用

第37届中国控制会议

作者： Ximin Liu Sicong Lu Rebing Wu Institute of Microelectronics Tsinghua University Department of Automation Tsinghua University

The purpose of quantum state tomography（QST） is to obtain a complete quantum state by reconstructing a density matrix from experimental data and therefore gives researchers a powerful tool to analyze complex synthetic quantum *** the past decades,many methods have been developed to improve the efficiency of quantum state tomography（QST）,such as old methods: compress sensing on almost pure state and low-rank systems,new method: using restricted Boltzmann machine on systems of quantum ***,they are both limited to some certain *** this paper,we introduce an universal method using deep neural networks based on stacked denoising autoencoder,which probably can help finish QST on all types of systems with a much smaller number of measurements and therefore is very efficient.

关键词： quantum state tomography deep neural networks stacked denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

The research of underwater target recognition method based on deep learning 7

The research of underwater target recognition method based o...

引用

IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)

作者： Chen, Yuechao Xu, Xiaonan Hangzhou Appl Acoust Res Inst Natl Key Lab Sci & Technol Sonar Hangzhou Zhejiang Peoples R China

ISBN: (纸本)9781538631423

The deep learning is a popular research direction in machine learning field now. In this paper, the deep learning algorithms are used to recognize the underwater target radiated noises. The deep belief network (DBN) model and the stacked denoising autoencoder (SDAE) model are built respectively. Then the underwater acoustic simulated data of different types of targets as well as different states of one target and experimental data of different states of one target were recognized by these models, and the support vector machine (SVM), general regression neural network (GRNN) and probabilistic neural network (PNN) are selected as the comparison algorithms. The spectrum features extracted from the target radiated noises are used as the input data of the recognition models. The results show that the recognition accuracy of DBN and that of SDAE are all higher than that of the other three methods for all situations, which shows that the deep learning algorithms can effectively improve the underwater target recognition effect.

关键词： Deep belief network stacked denoising autoencoder Underwater target recognition Spectrum feature

来源：评论

学校读者我要写书评

暂无评论

A DEEP LEARNING APPROACH FOR CANCER DETECTION AND RELEVANT GENE IDENTIFICATION 22nd

A DEEP LEARNING APPROACH FOR CANCER DETECTION AND RELEVANT G...

引用

22nd Pacific Symposium on Biocomputing (PSB)

作者： Danaee, Padideh Ghaeini, Reza Hendrix, David A. Oregon State Univ Sch Elect Engn & Comp Sci Corvallis OR 97330 USA Oregon State Univ Sch Elect Engn & Comp Sci Dept Biochem & Biophys Corvallis OR 97330 USA

ISBN: (纸本)9789813207813;9789813207806

Cancer detection from gene expression data continues to pose a challenge due to the high dimensionality and complexity of these data. After decades of research there is still uncertainty in the clinical diagnosis of cancer and the identification of tumor-specific markers. Here we present a deep learning approach to cancer detection, and to the identification of genes critical for the diagnosis of breast cancer. First, we used stacked denoising autoencoder (SDAE) to deeply extract functional features from high dimensional gene expression profiles. Next, we evaluated the performance of the extracted representation through supervised classification models to verify the usefulness of the new features in cancer detection. Lastly, we identified a set of highly interactive genes by analyzing the SDAE connectivity matrices. Our results and analysis illustrate that these highly interactive genes could be useful cancer biomarkers for the detection of breast cancer that deserve further studies.

关键词： Cancer Detection RNA-seq Expression Deep Learning Dimensionality Reduction stacked denoising autoencoder Classification

来源：评论

学校读者我要写书评

暂无评论

Transfer learning for short-term wind speed prediction with deep neural networks

引用

RENEWABLE ENERGY 2016年第Jan.期85卷 83-95页

作者： Hu, Qinghua Zhang, Rujia Zhou, Yucan Tianjin Univ Sch Comp Sci & Technol Tianjin 300072 Peoples R China

As a type of clean and renewable energy source, wind power is widely used. However, owing to the uncertainty of wind speed, it is essential to build an accurate forecasting model for large-scale wind power penetration. Numerical weather prediction (NWP) and data-driven modeling are two typical paradigms. NWP is usually unavailable or spatially insufficient. Data-driven modeling is an effective candidate. As to some newly-built wind farms, sufficient historical data is not available for training an accurate model, while some older wind farms may have long-term wind speed records. A question arises regarding whether the prediction model trained by data coming from older farms is also effective for a newly-built farm. In this paper, we propose an interesting trial of transferring the information obtained from data-rich farms to a newly-built farm. It is well known that deep learning can extract a high-level representation of raw data. We introduce deep neural networks, trained by data from data-rich farms, to extract wind speed patterns, and then finely tune the mapping with data coming from newly-built farms. In this way, the trained network transfers information from one farm to another. The experimental results show that prediction errors are significantly reduced using the proposed technique. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： Wind speed prediction Transfer learning Deep neural networks stacked denoising autoencoder

来源：评论

学校读者我要写书评

暂无评论

Change detection based on deep feature representation and mapping transformation for multi-spatial-resolution remote sensing images

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING 2016年第Jun.期116卷 24-41页

作者： Zhang, Puzhao Gong, Maoguo Su, Linzhi Liu, Jia Li, Zhizhou Xidian Univ Key Lab Intelligent Percept & Image Understanding Minist Educ Int Res Ctr Intelligent Percept & Computat Xian 710071 Shaanxi Provinc Peoples R China

Multi-spatial-resolution change detection is a newly proposed issue and it is of great significance in remote sensing, environmental and land use monitoring, etc. Though multi-spatial-resolution image pair are two kinds of representations of the same reality, they are often incommensurable superficially due to their different modalities and properties. In this paper, we present a novel multi-spatial resolution change detection framework, which incorporates deep-architecture-based unsupervised feature learning and mapping-based feature change analysis. Firstly, we transform multi-resolution image-pair into the same pixel-resolution through co-registration, followed by details recovery, which is designed to remedy the spatial details lost in the registration. Secondly, the denoising autoencoder is stacked to learn local and high-level representation/feature from the local neighborhood of the given pixel, in an unsupervised fashion. Thirdly, motivated by the fact that multi-resolution image-pair share the same reality in the unchanged regions, we try to explore the inner relationships between them by building a mapping neural network. And it can be used to learn a mapping function based on the most-unlikely-changed feature-pairs, which are selected from all the feature-pairs via a coarse initial change map generated in advance. The learned mapping function can bridge the different representations and highlight changes. Finally, we can build a robust and contractive change map through feature similarity analysis, and the change detection result is obtained through the segmentation of the final change map. Experiments are carried out on four real datasets, and the results confirmed the effectiveness and superiority of the proposed method. (C) 2016 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.

关键词： Change detection Spatial-resolution denoising autoencoder stacked denoising autoencoder Deep neural networks Feature transformation

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

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：