A survey on deep learning for big data

Zhang, Qingchen; Yang, Laurence T.; Chen, Zhikui; Li, Peng

doi:10.1016/j.inffus.2017.10.006

Cited by 929 publications

(409 citation statements)

References 46 publications

Supporting

Mentioning

402

Contrasting

Unclassified

Order By: Relevance

“…Combinations of model-and data-parallel schemes have also been implemented in a software framework called DistBelief [99] to deal with very large models (more than a billion parameters). GPU-based frameworks are another important method for parallel deep learning models [100,101]. When high performance computing resources (multiple CPU cores or GPUs) are not available, however, additional methods of improving training efficiency are necessary.…”

Section: Feature Learningmentioning

confidence: 99%

See 1 more Smart Citation

EMG Pattern Recognition in the Era of Big Data and Deep Learning

Phinyomark

Scheme

2018

BDCC

175

105

View full text Add to dashboard Cite

Abstract:The increasing amount of data in electromyographic (EMG) signal research has greatly increased the importance of developing advanced data analysis and machine learning techniques which are better able to handle "big data". Consequently, more advanced applications of EMG pattern recognition have been developed. This paper begins with a brief introduction to the main factors that expand EMG data resources into the era of big data, followed by the recent progress of existing shared EMG data sets. Next, we provide a review of recent research and development in EMG pattern recognition methods that can be applied to big data analytics. These modern EMG signal analysis methods can be divided into two main categories: (1) methods based on feature engineering involving a promising big data exploration tool called topological data analysis; and (2) methods based on feature learning with a special emphasis on "deep learning". Finally, directions for future research in EMG pattern recognition are outlined and discussed.

show abstract

Section: Feature Learningmentioning

confidence: 99%

“…For real-time control, an incremental learning method is employed to update parameters when new samples arrive while still preserving the network structure. An extended coverage of general deep learning techniques for big data can be found in several reviews [100,101,103].…”

Section: Feature Learningmentioning

confidence: 99%

EMG Pattern Recognition in the Era of Big Data and Deep Learning

Phinyomark

Scheme

2018

BDCC

175

105

View full text Add to dashboard Cite

show abstract

“…• Using (F ||T U || W) in M o , TTP computes a new H ′ mac according to Equation 6. If H ′ mac = H mac , the integrity of the data holds.…”

Section: User Attributementioning

confidence: 99%

“…[1][2][3][4][5][6][7][8] But the data on the cloud are not under the user's physical control; illegal users can try to get the information contained in the data by the unauthorized access. [1][2][3][4][5][6][7][8] But the data on the cloud are not under the user's physical control; illegal users can try to get the information contained in the data by the unauthorized access.…”

Section: Introductionmentioning

confidence: 99%

Multiuser access control searchable privacy‐preserving scheme in cloud storage

Cao

Wang

Dong³

et al. 2018

Int J Communication

View full text Add to dashboard Cite

Searchable encryption scheme-based ciphertext-policy attribute-based encryption (CP-ABE) is a effective scheme for providing multiuser to search over the encrypted data on cloud storage environment. However, most of the existing search schemes lack the privacy protection of the data owner and have higher computation time cost. In this paper, we propose a multiuser access control searchable privacy-preserving scheme in cloud storage. First, the data owner only encrypts the data file and sets the access control list of multiuser and multiattribute for search data file. And the computing operation, which generates the attribute keys of the users ′ access control and the keyword index, is given trusted third party to perform for reducing the computation time of the data owner. Second, using CP-ABE scheme, trusted third party embeds the users' access control attributes into their attribute keys. Only when those embedded attributes satisfy the access control list, the ciphertext can be decrypted accordingly. Finally, when the user searches data file, the keyword trap door is no longer generated by the user, and it is handed to the proxy server to finish. Also, the ciphertext is predecrypted by the proxy sever before the user performs decryption. In this way, the flaw of the client's limited computation resource can be solved. Security analysis results show that this scheme has the data privacy, the privacy of the search process, and the collusion-resistance attack, and experimental results demonstrate that the proposed scheme can effectively reduce the computation time of the data owner and the users. KEYWORDS attribute-based encryption, cloud storage, multiuser, privacy preserving, searchable encryption Int J Commun Syst. 2018;31:e3548.wileyonlinelibrary.com/journal/dac

show abstract

“…The deep learning model uses multiple samples to extract high-level features and learns hierarchical representations by combining low-level inputs more effectively. The learned features characterize more intrinsic features of the data, avoiding the process of artificial feature design and selection, and have the characteristics of many varieties and high accuracy [12]. …”

Section: Introductionmentioning

confidence: 99%

Research on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases

Guo

Zhang

et al. 2018

Journal of Healthcare Engineering

View full text Add to dashboard Cite

Quantitative analysis and prediction can help to reduce the risk of cardiovascular disease. Quantitative prediction based on traditional model has low accuracy. The variance of model prediction based on shallow neural network is larger. In this paper, cardiovascular disease prediction model based on improved deep belief network (DBN) is proposed. Using the reconstruction error, the network depth is determined independently, and unsupervised training and supervised optimization are combined. It ensures the accuracy of model prediction while guaranteeing stability. Thirty experiments were performed independently on the Statlog (Heart) and Heart Disease Database data sets in the UCI database. Experimental results showed that the mean of prediction accuracy was 91.26% and 89.78%, respectively. The variance of prediction accuracy was 5.78 and 4.46, respectively.

show abstract

A survey on deep learning for big data

Cited by 929 publications

References 46 publications

EMG Pattern Recognition in the Era of Big Data and Deep Learning

EMG Pattern Recognition in the Era of Big Data and Deep Learning

Multiuser access control searchable privacy‐preserving scheme in cloud storage

Research on Improved Depth Belief Network-Based Prediction of Cardiovascular Diseases

Contact Info

Product

Resources

About