检索结果-内蒙古大学图书馆

sparse autoencoder-based Multi-head Deep Neural Networks for Machinery Fault Diagnostics with Detection of Novelties

引用

Chinese Journal of Mechanical Engineering 2021年第3期34卷 146-157页

作者： Zhe Yang Dejan Gjorgjevikj Jianyu Long Yanyang Zi Shaohui Zhang Chuan Li School of Mechanical Engineering Dongguan University of TechnologyDongguan 523808China School of Mechanical Engineering Xi’an Jiaotong UniversityXi’an 710049China Faculty of Computer Science and Engineering Ss.Cyril and Methodius UniversitySkopjeMacedonia

Supervised fault diagnosis typically assumes that all the types of machinery failures are ***,in practice unknown types of defect,i.e.,novelties,may occur,whose detection is a challenging *** this paper,a novel fault diagnostic method is developed for both diagnostics and detection of *** this end,a sparse autoencoder-based multi-head Deep Neural Network(DNN)is presented to jointly learn a shared encoding representation for both unsupervised reconstruction and supervised classification of the monitoring *** detection of novelties is based on the reconstruction ***,the computational burden is reduced by directly training the multi-head DNN with rectified linear unit activation function,instead of performing the pre-training and fine-tuning phases required for classical *** addressed method is applied to a benchmark bearing case study and to experimental data acquired from a delta 3D *** results show that its performance is satisfactory both in detection of novelties and fault diagnosis,outperforming other state-of-the-art *** research proposes a novel fault diagnostics method which can not only diagnose the known type of defect,but also detect unknown types of defects.

关键词： Deep learning Fault diagnostics Novelty detection Multi-head deep neural network sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder for social image understanding

引用

NEUROCOMPUTING 2019年 369卷 122-133页

作者： Liu, Jianran Wang, Shiping Yang, Wenyuan Minnan Normal Univ Fujian Key Lab Granular Comp & Applicat Zhangzhou 363000 Peoples R China Fuzhou Univ Fujian Prov Key Lab Network Comp & Intelligent In Fuzhou 350000 Fujian Peoples R China

The rapid increase of social media images has made organizing these resources effectively a huge problem. Labeling unlabeled images becomes the crucial division of social image understanding. However, the enhancement of social image sharpness leads to the increase of surface feature dimension. These multidimensional complex features leads to the curse of dimensionality and the difficulty of feature extraction. In this paper, sparse autoencoder is studied to solve the problem of social image understanding, because sparse autoencoder can make these features represent the original data in a refined way, thus avoiding curse of dimensionality as much as possible and significantly improve the understanding effect. First, we explore the dimensional reduction capability of sparse autoencoder, and use sparse autoencoder to get low-dimensional features. Second, for low-dimensional features, an enhanced multi-label classifier is utilized to assign labels with the help of cosine similarity about tags correlation. The ability of dimensionality reduction of sparse autoencoder is proved by mapping matrix of image-label. Finally, we test our approach on several publicly available social media datasets. The results demonstrate that our proposed method is superior to lots of non-deep learning method among three evaluation indexes of social image understanding. (C) 2019 Elsevier B.V. All rights reserved.

关键词： Machine learning Dimensionality reduction Image understanding sparse autoencoder Multi-label predict

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder with Attention Mechanism for Speech Emotion Recognition 1

Sparse Autoencoder with Attention Mechanism for Speech Emoti...

引用

1st IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS)

作者： Sun, Ting-Wei Wu, An-Yeu (Andy) Natl Taiwan Univ Grad Inst Elect Engn Taipei Taiwan

ISBN: (纸本)9781538678848

There has been a lot of previous works on speech emotion with machine learning method. However, most of them rely on the effectiveness of labelled speech data. In this paper, we propose a novel algorithm which combines both sparse autoencoder and attention mechanism. The aim is to benefit from labeled and unlabeled data with autoencoder, and to apply attention mechanism to focus on speech frames which have strong emotional information. We can also ignore other speech frames which do not carry emotional content. The proposed algorithm is evaluated on three public databases with cross-language system. Experimental results show that the proposed algorithm provide significantly higher accurate predictions compare to existing speech emotion recognition algorithms.

关键词： Affective computing Speech Emotion sparse autoencoder Attention Mechanism

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder based deep neural network for voxelwise detection of cerebral microbleed 22

Sparse Autoencoder based deep neural network for voxelwise d...

引用

22nd IEEE International Conference on Parallel and Distributed Systems (ICPADS)

作者： Zhang, Yu-Dong Hou, Xiao-Xia Lv, Yi-Ding Chen, Hong Zhang, Yin Wang, Shui-Hua Nanjing Normal Univ Sch Comp Sci & Technol Nanjing 210023 Jiangsu Peoples R China Hunan Prov Key Lab Network Invest Technol Changsha 410138 Hunan Peoples R China Nanjing Med Univ Affiliated Hosp 1 Dept Neurol Nanjing 210029 Jiangsu Peoples R China Nanjing Med Univ Dept Psychiat Nanjing 210029 Jiangsu Peoples R China Zhongnan Univ Econ & Law Sch Informat & Safety Engn Wuhan 430073 Hubei Peoples R China CUNY City Coll New York Dept Elect Engn New York NY 10031 USA

ISBN: (纸本)9781509044573

In order to detect cerebral microbleed more efficiently, we developed a novel computer-aided detection method based on susceptibility-weighted imaging. We enrolled five CADASIL patients and five healthy controls. We used a 20x20 neighboring window to generate samples on each slice of the volumetric brain images. The sparse autoencoder (SAE) was used to unsupervised feature learning. Then, a deep neural network was established using the learned features. The results over 10x10-fold cross validation showed our method yielded a sensitivity of 93.20 +/- 1.37%, a specificity of 93.25 +/- 1.38%, and an accuracy of 93.22 +/- 1.37%. Our result is better than Roy's method, which was proposed in 2015.

关键词： sparse autoencoder deep neural network cerebral microbleed cross validation susceptibility weighted imaging

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder BASED HYPERSPECTRAL ANOMALY DETECTION WITH THE SINGULAR SPECTRUM ANALYSIS BASED SPECTRAL DENOISING

SPARSE AUTOENCODER BASED HYPERSPECTRAL ANOMALY DETECTION WIT...

引用

IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Li, Yinhe Ren, Jinchang Gao, Zhi Sun, Genyun Robert Gordon Univ Natl Subsea Ctr Aberdeen Scotland Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan Peoples R China China Univ Petr East China Coll Oceanog & Space Informat Qingdao Peoples R China

ISBN: (纸本)9798350360332;9798350360325

As an effective tool for monitoring surface irregularities in remote sensing, hyperspectral anomaly detection (HAD) has garnered increasing attention. However, how to improve the detection accuracy remains a formidable challenge, due mainly to the noise and variations in the spectral domain, especially when there is lack of the labelled data for training. To tackle these difficulties, a novel unsupervised HAD method is proposed. First, 1-D Singular Spectrum Analysis (SSA) is employed to eliminate outliers in the spectral domain. Second, the SSA-smoothed hypercube undergoes a sparse autoencoder for background reconstruction, where the reconstruction error is used to extract anomalous pixels. Finally, the RX algorithm is employed to segment anomalous pixels from the background. Comprehensive experiments on four publicly available datasets have validated the superior performance of our method in effectively enhancing the separability between anomaly pixels and their respective backgrounds, outperforming a few state-of-the-art methods, particularly in terms of the detection accuracy.

关键词： Hyperspectral images anomaly detection singular spectrum analysis sparse autoencoder RX.

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder-based Feature Transfer Learning for Speech Emotion Recognition

Sparse Autoencoder-based Feature Transfer Learning for Speec...

引用

5th Biannual Conference of the Humaine-Association on Affective Computing and Intelligent Interaction (ACII)

作者： Deng, Jun Zhang, Zixing Marchi, Erik Schuller, Bjoern Tech Univ Munich MMK Machine Intelligence & Signal Proc Grp D-80290 Munich Germany

ISBN: (纸本)9780769550480

In speech emotion recognition, training and test data used for system development usually tend to fit each other perfectly, but further 'similar' data may be available. Transfer learning helps to exploit such similar data for training despite the inherent dissimilarities in order to boost a recogniser's performance. In this context, this paper presents a sparse autoencoder method for feature transfer learning for speech emotion recognition. In our proposed method, a common emotion-specific mapping rule is learnt from a small set of labelled data in a target domain. Then, newly reconstructed data are obtained by applying this rule on the emotion-specific data in a different domain. The experimental results evaluated on six standard databases show that our approach significantly improves the performance relative to learning each source domain independently.

关键词： speech emotion recognition transfer learning sparse autoencoder deep neural networks

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder Based Feature Learning for Unmanned Aerial Vehicle Landforms Image Classification 8

Sparse Autoencoder Based Feature Learning for Unmanned Aeria...

引用

IEEE International Conference on Cybernetics and Intelligent Systems (CIS) / IEEE Conference on Robotics, Automation and Mechatronics (RAM)

作者： Liu, Fang Lu, Lixia Huang, Guangwei Beijing Univ Technol Coll Informat & Commun Engn Beijing 100124 Peoples R China

ISBN: (纸本)9781538631355

A new algorithm of unmanned aerial vehicle landforms image classification based on sparse autoencoder(SAE) is proposed in view of the drawbacks of single layer sparse autoencoder for feature learning that it is easy to lose the deep abstract feature and the feature lacks the robustness. In this paper, first, by constructing the deep sparse autoencoder, the image layer by layer learning and automatically extract each layer features. Then, in order to improve the feature representations, the each layer feature weights and the reorganized feature set are obtained according to the feature set weighting method. Finally, combining the strong global search ability of genetic algorithm (GA) and the excellent performance of support vector machine (SVM), the image classification is completed efficiently and accurately. The experimental results show that the proposed algorithm can automatically learn the deep feature of the image, and the reorganized feature has high discriminations image representations, which effectively improves the image classification accuracy.

关键词： sparse autoencoder feature learning genetic algorithm support vector machine image classification

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder for sparse Code Multiple Access 3

Sparse Autoencoder for Sparse Code Multiple Access

引用

3rd International Conference on Artificial Intelligence in Information and Communication (IEEE ICAIIC)

作者： Singh, Medini Mishra, Deepak Vanidevi, M. Indian Inst Space Sci & Technol Dept Avionics Thiruvananthapuram Kerala India

ISBN: (纸本)9781728176383

In the forthcoming 5G technology, sparse Code Multiple Access (SCMA) is the most promising scheme that aims at improving spectral efficiency further and providing massive connectivity. The challenge behind implementing SCMA scheme is: constructing optimized codebooks in order to obtain minimum BER while keeping the receiver complexity minimum. To address this problem, we resort to the usage of an efficient deep learning technique, autoencoders, that club the encoder and the decoder part and automatically learn the most optimum codeword that could give the least BER. In this paper, SCMA sparse autoencoder, which is a variant of the autoencoder, is proposed. that has better BER performance than a conventional autoencoder, without paying in terms of computational complexity.

关键词： 5G SCMA autoencoder sparse autoencoder BER

来源：评论

学校读者我要写书评

暂无评论

sparse autoencoder for Facial Expression Recognition 12

Sparse Autoencoder for Facial Expression Recognition

引用

12th IEEE Int Conf Ubiquitous Intelligence & Comp/12th IEEE Int Conf Autonom & Trusted Comp/15th IEEE Int Conf Scalable Comp & Commun & Associated Workshops/IEEE Int Conf Cloud & Big Data Comp/IEEE Int Conf Internet People

作者： Huang, Binbin Ying, Zilu Wuyi Univ Sch Informat Engn Jiangmen Peoples R China

ISBN: (纸本)9781467372114

Facial expression recognition has become one of the most interesting topics in human computer interaction. A lot of methods have been proposed and studied for facial expression recognition. Among some of these methods, feature extraction is very important. However, feature extraction in these methods involves human intervention more or less which may make the recognition task unstable and not suitable for practical application. To overcome these problems, a deep learning method for facial expression recognition is proposed. First, it divides the training images to 7 groups correspond to 7 expressions to train 7 sparse autoencoder networks. Then, it lets each training group gets thought the network that have been trained by this group, and each training image gets 150 outputs as the training features. In testing step, a testing image is input into the 7 trained networks and gets 150 outputs as the testing features of each network. Comparing the square of error between testing features with the training features in each network, and classifying the testing image into the class with the minimum error. Experiments on JAFFE database has proved the effectiveness of the proposed method.

关键词： Facial expression sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

A Framework for Automatically Extracting Overvoltage Features Based on sparse autoencoder

引用

IEEE TRANSACTIONS ON SMART GRID 2018年第2期9卷 594-604页

作者： Chen, Kunjin Hu, Jun He, Jinliang Tsinghua Univ Dept Elect Engn State Key Lab Power Syst Beijing 100084 Peoples R China

With the development of smart grid, it is of increasing significance to identify and cope with various types of overvoltages, faults and power quality disturbances effectively and automatically. In this paper, a framework for overvoltage identification and classification based on sparse autoencoder is proposed. By using single-layer and stacked sparse autoencoders, dimensionality reduction and automatic feature extraction of ferroresonance overvoltage waveforms in power distribution systems are achieved as an example, which does not require feature engineering to produce a series of features. Classification of different ferroresonance modes is then implemented with a softmax classifier, and favorable classification results are obtained after parameters of feature extraction and classifier models are determined. Application of the proposed framework in smart grids is discussed. The proposed framework provides a brand new idea for establishing a smart identification and classification system for overvoltages, which can be generalized to classification of faults and power quality disturbances.

关键词： sparse autoencoder softmax regression feature extraction dimensionality reduction ferroresonance overvoltage

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：