Journal
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
Volume 17, Issue 4, Pages 2794-2801Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3006616
Keywords
Access; concurrency; healthcare; deep learning; distributed cloud computing environment; retrieval and storage-based indexing framework (RSIF)
Categories
Funding
- doctoral research foundation of North China University of Science and Technology
Ask authors/readers for more resources
This article introduces a retrieval and storage-based indexing framework (RSIF) to enhance the concurrency of user and service provider access to cloud-stored healthcare data using deep learning for constraint classification.
Distributed cloud computing environments rely on sophisticated communication and sharing paradigms for ease of access, information processing, and analysis. The challenging characteristic of such cloud computing environments is the concurrency and access as both the service provider and end-user rely on the common sharing platform. In this article, retrieval and storage-based indexing framework (RSIF) is designed to improve the concurrency of user and service provider access to the cloud-stored healthcare data. Concurrency is achieved through replication-free and continuous indexing and time-constrained retrieval of stored information. The process of classifying the constraints for data augmentation and update is performed using deep learning for all the storage instances. Through conditional assessment, the learning process determines the approximation of indexing and ordering for storing and retrieval, respectively. This helps to reduce the time for access and retrieval concurrently, provided the process is not dependent. The simulation analysis using the metrics discontinuous indexing, replicated data, retrieval time, and cost proves the reliability of the proposed framework.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available