Advances in Complex Systems · 2021 · 13 citations · 24 references
ComputingCloud ComputingComputer ScienceCryptographyEdge ComputingInternet Of ThingsCryptographic ArchitectureData EncryptionEdge SecurityIot Data ManagementIot PrivacyIot SecurityBlockchain CryptographyBlockchain SecurityBlockchain-based Data SecurityBlockchain-based SecurityCryptographic AuthenticationEncryptionInternet Of Things PrivacyIot Security Architecture
Today, artificial intelligence (AI) can use the most powerful edge computing systems in the Internet of Things (IoT) for finding the information extracted from vast sensory data such as cyber effects or models in physical environments for classification, identification, and prediction. Heterogeneous IoT devices produce isolated and dispersed information parts, and knowledge sharing and exchange in IoT intelligent applications with several selfish nodes are necessary for complex tasks. In both academia and business, IoT is driving a digital revolution. However, protection and IoT privacy problems are challenged. It offers comfort for everyday lives. Blockchain, a shared cryptographic database, is a promising IoT encryption solution for several manufacturing, finance, and trade sectors. The IoT-based blockchain architecture is an interesting contrast to the conventional, centralized paradigm that struggles to fulfill specific IoT requirements. New concepts for applying data and resources management protection procedures in distributed networks and cloud computing are introduced. Cloud management services can be linked to the application through blockchain technology and distributed leader, a stable cognitive information system that facilitates management operations and securing data. This document provides many ideas for applying personal and behavioral characteristics to security and cryptography protocols, blockchain based on the cognitive cloud computing (BC-CCC) pattern. The simulation result shows that the proposed strategy can significantly enhance data transmission rate (96.2%), security ratio (94.5%), throughput ratio (92.4%), scalability ratio (91.5%), trust rate (93.8%), data trading ratio (96.2%), and reduce storage cost rate (25.1%) compared to other existing methods.
24
Machine Learning Based Workload Prediction in Cloud Computing
Jiechao Gao, Haoyu Wang, Haiying Shen · 2020 · 302 citations
A Machine Learning Security Framework for Iot Systems
Miloud Bagaa, Tarik Taleb, Jorge Bernal Bernabé et al. · IEEE Access · 2020 · 263 citations · Full text