Hershey, Pennsylvania
New York, New YorkBeijing, China
Convolutional Neural Network-Based Secured Data Storage Mechanism for Big Data Environments

Convolutional Neural Network-Based Secured Data Storage Mechanism for Big Data Environments

Balamurugan Easwaran (University of Africa, Toru-Orua, Nigeria), Sangeetha Krishnan (University of Africa, Toru-Orua, Nigeria), Anitha P. T. (Wollega University, Ethiopia), Jackson Akpojaro (University of Africa, Toru-Orua, Nigeria), and Kirubanand V. B. (CHRIST University (Deemed), India)
Copyright: © 2022 |Pages: 18
DOI: 10.4018/978-1-7998-9308-0.ch013
OnDemand:
(Individual Chapters)
Available
$37.50
Current Special Offers
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Data types and amounts in human society are growing at an amazing speed, which is caused by emerging new services such as cloud computing and internet of things (IoT). As data has been a fundamental resource, research on big data has attracted much attention. An optimized cluster storage method for big data in IoT is proposed. First, weights of data blocks in each historical accessing period are calculated by temporal locality of data access, and the access frequencies of the data block in next period are predicted by the weights. Second, the hot spot of a data block is determined with a threshold that is calculated by previous data access. In this work, big data is divided into multiple segments based on semantic connectivity-based convolutional neural networks. Each segment will be stored in the different nodes by adapting the blockchain distributed-based local regenerative code technology called BCDLR. Experimental results demonstrate the efficiency of the proposed model in terms of packet delivery ratio, end-to-end delay, energy consumption, and throughput.
Chapter Preview
Top

2. Literature Review

This section reviews methods used for secure storage of IOTs in big data. Ding (Ding et al, 2013) proposed generic Statistical Database Clustering for Big Data Analysis in IOTs data. The study used statistical functions within DBMS kernels where complex statistical queries were transformed into conventional SQL queries. Moreover, statistics based analyses using distributed/parallel servers, resulted in increased performances in experimentations.

Tripathi (Tripathi et al, 2020) suggested metaheuristic-based clustering for handling massive data based on the power of MapReduce. The study’s suggested approach used the searching power of military dog squads to identify the best centroids where MapReduce handled voluminous data. The study tested their proposed schema against 17 benchmark functions for their efficiency in optimizations while comparing experimental results with 5 contemporary algorithms namely BOAs (bat optimization algorithms), PSOs (particle swarm optimizations), ABCs (Artificial Bee Colonies), MVOs (Multi-Verse Optimizations) and WOAs (Whale Optimization Algorithms). Moreover, the study’s parallel version used MapReduce [MapReduce-based MDBO (MR-MDBO)] for clustering large datasets of industrial IoTs.

Complete Chapter List

Search this Book:
Reset