Stacked sparse autoencoder and history of binary motion image for human activity recognition

Gnouma, Mariem; Ladjailia, Ammar; Ejbali, Ridha; Zaied, Mourad

doi:10.1007/s11042-018-6273-1

Cited by 39 publications

(17 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The adjacency matrix A can be reconstructed as matrix X (shown in Equations (8)) by Algorithm 2. for j = 1 to n (11) Calculate the Euclidean distance between node vi and node vj. (12) end for (13) Find and Set node j_neighbor from the neighbor node selection method as node vi.…”

Section: Reconstruction Methodsmentioning

confidence: 99%

“…• The two neurons in the convolutional layer which are   12 , hh can be calculated by Equations (9) and (10). • The four neurons in the output layer which are   1 2 3 4, , , x x x x     can be calculated by Equations(11),(12),(13) and(14).Preprints (www.preprints.org) | NOT PEER-REVIEWED | Posted: 3 November 2019 doi:10.20944/preprints201911.0019.v1 The loss function analyzes the mean squared errors by Equation(15) to optimize the neural network.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Deep Community Detection Method for Social Networks

Wu¹,

Q²,

Chen³

2019

Preprint

View full text Add to dashboard Cite

With the fast development of the mobile Internet, the online platforms of social networks have rapidly been developing for the purpose of making friends, sharing information, etc. In these online platforms, users being related to each other forms social networks. Literature reviews have shown that social networks have community structure. Through the studies of community structure, the characteristics and functions of networks structure and the dynamical evolution mechanism of networks can be used for predicting user behaviours and controlling information dissemination. Therefore, this study proposes a deep community detection method which includes (1) matrix reconstruction method, (2) spatial feature extraction method and (3) community detection method. The original adjacency matrix in social network is reconstructed based on the opinion leader and nearer neighbors for obtaining spatial proximity matrix. The spatial eigenvector of reconstructed adjacency matrix can be extracted by an auto-encoder based on convolution neural network for the improvement of modularity. In experiments, four open datasets of practical social networks were selected to evaluate the proposed method, and the experimental results show that the proposed deep community detection method obtained higher modularity than other methods. Therefore, the proposed deep community detection method can effectively detect high quality communities in social networks.

show abstract

Section: Reconstruction Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Deep Community Detection Method for Social Networks

Wu¹,

Q²,

Chen³

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…If the starting layer is trained, so, the second is trained considering the outputs of the starting layer as the inputs for the next layer. It is greedy since each layer improves its cost independently the cost of the next layers [12].…”

Section: Stacked Sparse Auto-encodersmentioning

confidence: 99%

Sparse Wavelet Auto-encoder for Covid-19 Cases Identification

Lazrag

Ali

Ejbali

2021

Hybrid Intelligent Systems

Self Cite

View full text Add to dashboard Cite

Diagnosis and understanding of disease progression require an interpretation of medical images, would take a lot of time in manual interpretation of the large amount of medical images accumulated. Thus, the automatic analysis and understanding of the medical images becomes an active research topic. In this case, feature extraction from the medical images plays an important role in obtaining diagnostic performance . In this context, we propose a Covid-19 cases identification based on sparse coding, wavelet analysis for feature extraction and AE for feature modeling. Our approach is based on sparse coding and wavelet analysis techniques for image representation and it is tested with the COVID-19 dataset. The experimental results demonstrate the performance of our system.

show abstract

“…Here, features were removed with PCA to diminish the dimensionality of facial images. FFBBL provides accuracy of (98.33, 98.80) with (40,50) characteristics, while Elman provides (98. 33, 95.14) with (40,50) characteristics.…”

Section: Literature Reviewmentioning

confidence: 99%

Human emotion recognition based on block patterns of image and wavelet transform

2021

IJATEE

View full text Add to dashboard Cite

Stacked sparse autoencoder and history of binary motion image for human activity recognition

Cited by 39 publications

References 35 publications

Deep Community Detection Method for Social Networks

Deep Community Detection Method for Social Networks

Sparse Wavelet Auto-encoder for Covid-19 Cases Identification

Human emotion recognition based on block patterns of image and wavelet transform

Contact Info

Product

Resources

About