Text feature extraction based on stacked variational autoencoder

Che, Lei; Yang, Xiaoping; Wang, Liang

doi:10.1016/j.micpro.2020.103063

Cited by 15 publications

(6 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to the randomness of sample selection, each algorithm is executed 10 times to observe their identification results. According to previous studies, their model parameters are specifically summarized as follows: (1) In the traditional deep VAE [ 30 ], the network structure is set as 2048–512–64–32–10, which includes one input layer, three hidden layers and one output layer. (2) In the SDAE model [ 31 ], the network structure is set as 2048–200–100–80–10, which includes one input layer, three hidden layers and one output layer.…”

Section: Experimental Verification and Discussionmentioning

confidence: 99%

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Yan

She

et al. 2021

Entropy

View full text Add to dashboard Cite

Variational auto-encoders (VAE) have recently been successfully applied in the intelligent fault diagnosis of rolling bearings due to its self-learning ability and robustness. However, the hyper-parameters of VAEs depend, to a significant extent, on artificial settings, which is regarded as a common and key problem in existing deep learning models. Additionally, its anti-noise capability may face a decline when VAE is used to analyze bearing vibration data under loud environmental noise. Therefore, in order to improve the anti-noise performance of the VAE model and adaptively select its parameters, this paper proposes an optimized stacked variational denoising autoencoder (OSVDAE) for the reliable fault diagnosis of bearings. Within the proposed method, a robust network, named variational denoising auto-encoder (VDAE), is, first, designed by integrating VAE and a denoising auto-encoder (DAE). Subsequently, a stacked variational denoising auto-encoder (SVDAE) architecture is constructed to extract the robust and discriminative latent fault features via stacking VDAE networks layer on layer, wherein the important parameters of the SVDAE model are automatically determined by employing a novel meta-heuristic intelligent optimizer known as the seagull optimization algorithm (SOA). Finally, the extracted latent features are imported into a softmax classifier to obtain the results of fault recognition in rolling bearings. Experiments are conducted to validate the effectiveness of the proposed method. The results of analysis indicate that the proposed method not only can achieve a high identification accuracy for different bearing health conditions, but also outperforms some representative deep learning methods.

show abstract

Section: Experimental Verification and Discussionmentioning

confidence: 99%

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Yan

She

et al. 2021

Entropy

View full text Add to dashboard Cite

show abstract

“…8 , AE is built by encoder and decoder, which is helpful for dimensionality reduction of data (Chen et al, 2018 ), feature extraction (Meng et al, 2017) and anomaly detection (Han et al, 2020 ). It also has some variants like undercomplete autoencoder (Buongiorno et al, 2019 ), regularized autoencoder (Hong et al, 2020 ) and variational autoencoder (Che et al, 2020 ).…”

Section: Frequently-used Deep Learning Models In Economics Applicationsmentioning

confidence: 99%

Deep learning in economics: a systematic and critical review

2023

View full text Add to dashboard Cite

From the perspective of historical review, the methodology of economics develops from qualitative to quantitative, from a small sampling of data to a vast amount of data. Because of the superiority in learning inherent law and representative level, deep learning models assist in realizing intelligent decision-making in economics. After presenting some statistical results of relevant researches, this paper systematically investigates deep learning in economics, including a survey of frequently-used deep learning models in economics, several applications of deep learning models used in economics. Then, some critical reviews of deep learning in economics are provided, including models and applications, why and how to implement deep learning in economics, research gap and future challenges, respectively. It is obvious that several deep learning models and their variants have been widely applied in different subfields of economics, e.g., financial economics, macroeconomics and monetary economics, agricultural and natural resource economics, industrial organization, urban, rural, regional, real estate and transportation economics, health, education and welfare, business administration and microeconomics, etc. We are very confident that decision-making in economics will be more intelligent with the development of deep learning, because the research of deep learning in economics has become a hot and important topic recently.

show abstract

“…Ashok [15] et al compared GloVe with Word2vec (Word to Vector), and experiments proved that using GloVe has better text feature construction capabilities. The research on text feature extraction methods mainly focuses on deep learning, such as Stacked Variational Autoencoder (SVAE) [16], Convolutional Neural Network (CNN) [17][18], Long Short-Term Memory Network (LSTM) [19], etc. Many documents have proved the superiority of deep learning in text feature extraction.…”

Section: Text Data Feature Extractionmentioning

confidence: 99%

Multi-source Heterogeneous Data Fusion Model Based on FC-SAE

Zhang¹,

Zhang²,

Jiang³

et al. 2022

Journal of Internet Technology

View full text Add to dashboard Cite

<p>Multi-source heterogeneous data has different degrees of data correlation or data conflict. How to fuse this data and fully mine its inherent meanings to obtain more accurate decision information is a problem that needs to be solved urgently. This paper proposes a multi-source heterogeneous data fusion model based on fully connected layers and sparse autoencoders (short for FC-SAE) to solve the above problem. This model can effectively improve the time series forecasting performance compared with the traditional time series forecasting model. The MAE value is reduced by 4.4% and the RMSE value is reduced by 3.7%. In terms of fusion strategy, the method that uses the sparse autoencoder as the fusion strategy reduces the MAE value by 1.7% and the RMSE value by 2.3% compared with the method that uses the fully connected layer as the fusion strategy.</p> <p> </p>

show abstract

Text feature extraction based on stacked variational autoencoder

Cited by 15 publications

References 6 publications

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Reliable Fault Diagnosis of Bearings Using an Optimized Stacked Variational Denoising Auto-Encoder

Deep learning in economics: a systematic and critical review

Multi-source Heterogeneous Data Fusion Model Based on FC-SAE

Contact Info

Product

Resources

About