Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder

Fan, Zunlin; Du-yan, BI; He, Linyuan; Ma, Shiping; Gao, Shan; Cheng, Li

doi:10.1016/j.neucom.2017.02.066

Cited by 34 publications

(10 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using these values directly are not applicable. Previous work showed that the Denoising Autoencoder (DAE) network can be exploited for noise and correlation reduction, feature extraction [ 29 , 30 ]. Therefore, we employ DAE to extract the numerical features.…”

Section: Methodsmentioning

confidence: 99%

Prediction of blood culture outcome using hybrid neural network model based on electronic health records

Cheng

Zhao

Ding

et al. 2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Blood cultures are often performed to detect patients who has a serious illness without infections and patients with bloodstream infections. Early positive blood culture prediction is important, as bloodstream infections may cause inflammation of the body, even organ failure or death. However, existing work mainly adopts statistical models with laboratory indicators, and fails to make full use of textual description information from EHRs. Methods We study the problem of positive blood culture prediction by using neural network model. Specifically, we first construct dataset from raw EHRs. Then we propose a hybrid neural network which incorporates attention based Bi-directional Long Short-Term Memory and Autoencoder networks to fully capture the information in EHRs. Results In order to evaluate the proposed method, we constructe a dataset which consists of totally 5963 patients who had one or more blood cultures tests during hospitalization. Experimental results show that the proposed neural model gets 91.23% F-measure for this task. Conclusions The comparison results of different models demonstrated the effectiveness of our model. The proposed model outperformed traditional statistical models.

show abstract

Section: Methodsmentioning

confidence: 99%

Prediction of blood culture outcome using hybrid neural network model based on electronic health records

Cheng

Zhao

Ding

et al. 2020

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…Using these values directly may affect the performance of the task. Previous work shows that the denoising Autoencoder network can be utilized to reduce the high dimensionality and eliminate correlation [35]. Therefore, we employ this model to handle the numerical features.…”

Section: Methodsmentioning

confidence: 99%

A hybrid neural network model for predicting kidney disease in hypertension patients based on electronic health records

Ren

Hao

Liang

et al. 2019

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Disease prediction based on Electronic Health Records (EHR) has become one hot research topic in biomedical community. Existing work mainly focuses on the prediction of one target disease, and little work is proposed for multiple associated diseases prediction. Meanwhile, a piece of EHR usually contains two main information: the textual description and physical indicators. However, existing work largely adopts statistical models with discrete features from numerical physical indicators in EHR, and fails to make full use of textual description information. Methods In this paper, we study the problem of kidney disease prediction in hypertension patients by using neural network model. Specifically, we first model the prediction problem as a binary classification task. Then we propose a hybrid neural network which incorporates Bidirectional Long Short-Term Memory (BiLSTM) and Autoencoder networks to fully capture the information in EHR. Results We construct a dataset based on a large number of raw EHR data. The dataset consists of totally 35,332 records from hypertension patients. Experimental results show that the proposed neural model achieves 89.7% accuracy for the task. Conclusions A hybrid neural network model was presented. Based on the constructed dataset, the comparison results of different models demonstrated the effectiveness of the proposed neural model. The proposed model outperformed traditional statistical models with discrete features and neural baseline systems.

show abstract

“…In the feature extraction phase, the image is divided into segments and then each segment is processed in order to convert the pixels to their equal numerical values [37]. From these multi-dimensional values, important features are extracted from each segment one by one.…”

Section: Features Extractionmentioning

confidence: 99%

An Efficient Normalized Restricted Boltzmann Machine for Solving Multiclass Classification Problems

Aamir¹,

Mohd²,

Wahid³

et al. 2019

IJACSA

View full text Add to dashboard Cite

Multiclass classification based on unlabeled images using computer vision and image processing is currently an important issue. In this research, we focused on the phenomena of constructing high-level features detector for class-driven unlabeled data. We proposed a normalized restricted Boltzmann machine (NRBM) to form a robust network model. The proposed NRBM is developed to achieve the goal of dimensionality reduction and provide better feature extraction with enhancement in learning more appropriate features of the data. For increment in learning convergence rate and reduction in complexity of the NRBM, we add Polyak Averaging method when training update parameters. We train the proposed NRBM network model on five variants of Modified National Institute of Standards and Technology database (MNIST) benchmark dataset. The conducted experiments showed that the proposed NRBM is more robust to noisy data as compared to state-of-art approaches.

show abstract

Low-level structure feature extraction for image processing via stacked sparse denoising autoencoder

Cited by 34 publications

References 17 publications

Prediction of blood culture outcome using hybrid neural network model based on electronic health records

Prediction of blood culture outcome using hybrid neural network model based on electronic health records

A hybrid neural network model for predicting kidney disease in hypertension patients based on electronic health records

An Efficient Normalized Restricted Boltzmann Machine for Solving Multiclass Classification Problems

Contact Info

Product

Resources

About