.png){kind=icon}
返回
Capuchin Search Algorithm With Deep Learning-Based Data Edge Verification for Blockchain-Assisted IoT Environment
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3346437.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Internet of Things (IoT) devices generate enormous quantities of data, and ensuring the authenticity and integrity of this data is essential. Blockchain (BC) serves as a transparent and secure ledger for recording each data transaction, which prevents unauthorized modification and provides a trust layer for the IoT ecosystem. Data edge verification for BC-enabled IoT platforms is a fundamental aspect of ensuring data trustworthiness, integrity, and security in the system. In such an environment, IoT devices generate vast amounts of data, and BC technology can be used to create a decentralized and immutable ledger that records all the transactions and data exchanges Machine learning (ML) in the context of BC and the IoT offers a powerful toolkit for optimizing and securing these technologies. It enables the analysis of vast and complex data generated by IoT devices, allowing for predictive maintenance, anomaly detection, and pattern recognition. ML also enhances security by developing intrusion detection systems and supporting smart contracts in BC networks. This article introduces a new Capuchin Search Algorithm with a Deep Learning based Data Edge Verification model (CSADL-DEVM) for the Blockchain assisted IoT platform. The purpose of the CSADL-DEVM technique is to integrate the BC with DL and hyperparameter tuning concepts for data edge verification in the IoT environment. In addition, IoT devices comprise a considerable level of decentralized decision-making ability, which accomplishes a consensus on the performance of intra-block transactions. In addition, the CSADL-DEVM technique applies the Elman recurrent neural network (ERNN) model for the identification and classification of faults. Moreover, the hyperparameters related to the ERNN model can be adjusted by the use of CSA which in turn better the detection results. A comprehensive set of simulations has been conducted to exhibit the enhanced results of the CSADL-DEVM method. The obtained outcomes exhibit the superior outcome of the CSADL-DEVM algorithm.
Keyword:
Blockchain
edge verification
deep learning
parameter selection
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Stimulated Raman Scattering in Cubic NaClO3 Crystal at Room Temperature under Picosecond Excitation
PREAI
分享收藏Networking Integrated Cloud-Edge-End in IoT: A Blockchain-Assisted Collective Q-Learning Approach
PREAI
分享收藏Blockchain-Incentivized D2D and Mobile Edge Caching: A Deep Reinforcement Learning Approach.png)
IEEE NETWORK
IEEE NETWORKIF6.3
PREAI
分享收藏A Blockchain-Facilitated Secure Sensing Data Processing and Logging System一种基于区块链的安全传感数据处理和记录系统IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏Cooperative Task Offloading and Block Mining in Blockchain-Based Edge Computing With Multi-Agent Deep Reinforcement Learning基于多Agent深度强化学习的区块链边缘计算协同任务卸载和区块挖掘OAAI
OAAI分享收藏Deep Reinforcement Learning for energy-aware task offloading in join SDN-Blockchain 5G massive IoT edge network深度强化学习在join SDN区块链5g massive IoT edge网络中实现能量感知任务卸载
PREAI
分享收藏
查看更多内容