A stacked convolutional sparse denoising autoencoder model for underwater heterogeneous information data

•A novel stacked convolutional sparse denoising autoencoder (SCSDA) model is proposed.•The unrelated dataset was developed to simulate the underwater heterogeneous information data as the training set.•The blind denoising performance of underwater heterogeneous information data is studied. Deep lear...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	Applied acoustics Ročník 167; s. 107391
Hlavní autoři:	Wang, Xingmei, Zhao, Yixu, Teng, Xuyang, Sun, Weiqi
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Elsevier Ltd 01.10.2020
Témata:	Blind denoising Convolutional neural network Deep learning Stacked sparse denoising autoencoder Underwater heterogeneous information data Stacked sparse denoising autoencoder Deep learning Underwater heterogeneous information data Blind denoising Convolutional neural network
ISSN:	0003-682X, 1872-910X
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	•A novel stacked convolutional sparse denoising autoencoder (SCSDA) model is proposed.•The unrelated dataset was developed to simulate the underwater heterogeneous information data as the training set.•The blind denoising performance of underwater heterogeneous information data is studied. Deep learning denoising models can automatically extract underwater heterogeneous information data features to improve denoising performance through an internal network structure. In the present study, a novel stacked convolutional sparse denoising autoencoder (SCSDA) model was proposed in this paper to complete the blind denoising task of underwater heterogeneous information data. Specifically, for the first time, the stacked sparse denoising autoencoder (SSDA) was constructed by three sparse denoising autoencoders (SDA) to extract overcomplete sparse features. Then, the output of the last encoding layer of the SSDA was used as the input of the convolutional neural network (CNN) to further extract the deep features. Finally, in order to solve the lack of the pure underwater heterogenous information data during the acquisition and transmission process, the unrelated dataset was developed to simulate the underwater heterogeneous information data as the training set in proposed SCSDA model. Compared with the existing other algorithms, the experiment results demonstrate that the proposed SCSDA model combines the advantages of SSDA and CNN, which has great blind denoising ability. It can process faster and preserves more edge features of underwater heterogeneous information data. Also, it has a certain degree of robustness and effectiveness.
ISSN:	0003-682X 1872-910X
DOI:	10.1016/j.apacoust.2020.107391