Reference Hub2
Distributed Database Management With Integration of Blockchain and Long Short-Term Memory

Distributed Database Management With Integration of Blockchain and Long Short-Term Memory

Siddesh G. M., S. R. Mani Sekhar, Vighnesh S., Nikhila Sai, Deepthi Sai, Sanjana D.
Copyright: © 2021 |Volume: 11 |Issue: 3 |Pages: 16
ISSN: 2155-6377|EISSN: 2155-6385|EISBN13: 9781799862000|DOI: 10.4018/IJIRR.2021070102
Cite Article Cite Article

MLA

Siddesh G. M., et al. "Distributed Database Management With Integration of Blockchain and Long Short-Term Memory." IJIRR vol.11, no.3 2021: pp.18-33. http://doi.org/10.4018/IJIRR.2021070102

APA

Siddesh G. M., Sekhar, S. R., Vighnesh S., Sai, N., Sai, D., & Sanjana D. (2021). Distributed Database Management With Integration of Blockchain and Long Short-Term Memory. International Journal of Information Retrieval Research (IJIRR), 11(3), 18-33. http://doi.org/10.4018/IJIRR.2021070102

Chicago

Siddesh G. M., et al. "Distributed Database Management With Integration of Blockchain and Long Short-Term Memory," International Journal of Information Retrieval Research (IJIRR) 11, no.3: 18-33. http://doi.org/10.4018/IJIRR.2021070102

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Supply chain management is the broad range of activities required to plan, control, and execute the flow of a product. As a less corruptible and more automated alternative to traditional databases, blockchains are well suited to the complicated record-keeping. However distributed database management system is a centralized software system; the blockchain technology can overcome the problem of synchronization between multiple databases; it also ensures that integrity problems are solved. In the proposed model, Ethereum blockchain is used to solve a few major supply chain problems to manage a distributed database. The model has incorporated techniques to predict the rise and fall of the demand for the medicine in the market by using machine learning algorithms such as linear regression and LSTM; also, the trend predicted by both the models has been compared. The result shows that while using linear regression the predicted trend is not very accurate and cannot trace the actual trend closely whereas BLSTM has performed well in predicting the trends of time series data.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.