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 ...
详细信息
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.
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 ...
详细信息
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.
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 combine...
详细信息
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.
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 u...
详细信息
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.
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 implementin...
详细信息
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.
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 ...
详细信息
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.
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 formidabl...
详细信息
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.
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 t...
详细信息
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.
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 frame...
详细信息
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.
In order to detect the cerebral microbleed (CMB) voxels within brain, we used susceptibility weighted imaging to scan the subjects. Then, we used undersampling to solve the accuracy paradox caused from the imbalanced ...
详细信息
In order to detect the cerebral microbleed (CMB) voxels within brain, we used susceptibility weighted imaging to scan the subjects. Then, we used undersampling to solve the accuracy paradox caused from the imbalanced data between CMB voxels and non-CMB voxels. we developed a seven-layer deep neural network (DNN), which includes one input layer, four sparse autoencoder layers, one softmax layer, and one output layer. Our simulation showed this method achieved a sensitivity of 95.13%, a specificity of 93.33%, and an accuracy of 94.23%. The result is better than three state-of-the-art approaches.
暂无评论