期刊
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
卷 69, 期 8, 页码 9031-9040出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TVT.2020.2999566
关键词
Wireless sensor networks; Security; Cloud computing; Entropy; Uncertainty; Heuristic algorithms; Decision trees; UWSNs; trust evaluation; trust update; C4; 5 decision tree
资金
- National Key Research and Development Program [2018YFC0407900]
- Jiangsu Provincial Six Talent Peaks Project [XYDXX-012]
- National Natural Science Foundation of China [61971206]
- Open Fund of StateKeyLaboratory of Acoustics [SKLA201901]
At present, Underwater Wireless Sensor Networks (UWSNs) have been widely used in enormous applications, and simultaneously face many security threats. The trust management mechanism plays an important role in protecting network security. Many theories, e.g., subjective logic, Bayesian, cloud model, entropy theory, evidence theory, etc., have been adopted to evaluate the node trust of wireless sensor networks. However, due to the unique characteristics of the underwater dynamic environment, the existing trust mechanisms used in traditional networks (such as P2P networks, Ad-hoc networks, etc.) cannot be directly used in UWSNs. Therefore, this paper proposes a new trust evaluation and update mechanism for underwater wireless sensor networks based on the C4.5 decision tree algorithm (TEUC). In the TEUC, trust evidences are first collected including data-based, link-based and node-based trust evidences. Then, the collected trust evidences are used to train the C4.5 decision tree. In addition, the reward and penalty factors are defined to update trust based on the sliding time window. Finally, simulation results demonstrate that the proposed algorithm outperforms the traditional ones in a dynamic network environment in terms of malicious node detection and energy consumption.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据