文献类型：期刊文献

英文题名：Bc2FL: Double-Layer Blockchain-Driven Federated Learning Framework for Agricultural IoT

作者：Ding, Qingyang[1]; Yue, Xiaofei[2]; Zhang, Qinnan[3]; Xiong, Zehui[4]; Chang, Jinping[1]; Zheng, Hongwei[5,6]

第一作者：Ding, Qingyang

机构：[1] Beijing Union University, College of Management, Beijing, 100101, China; [2] Beijing Institute of Technology, School of Computer Science and Technology, Beijing, 100081, China; [3] Beihang University, Institute of Artificial Intelligence, Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beijing, 100191, China; [4] Singapore University of Technology and Design, Information Systems Technology and Design Pillar, 487372, Singapore; [5] Beijing Academy of Blockchain and Edge Computing [BABEC], Beijing, 100190, China; [6] Beihang University, Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beijing, 100191, China

第一机构：北京联合大学管理学院

年份：2024

外文期刊名：IEEE Internet of Things Journal

收录：EI(收录号：20244417297854);Scopus(收录号：2-s2.0-85207471083)

语种：英文

外文关键词：Smart agriculture

摘要：With the flourishing of the Agricultural Internet of Things (AIoT), analyzing large-volume sensor data has become a regular requirement for agricultural decision-making. Federated Learning (FL), which facilitates scattered AIoT devices to train models collaboratively, has gained significant attention. However, traditional FL poses challenges in AIoT scenarios, such as wide geo-distribution, heterogeneous data distribution, and high device risks. Existing works tend to be one-sided and remain unclear on how to tackle these issues thoroughly in AIoT. To fill the gap, we present, a double-layer blockchain-based FL framework, which enhances both learning efficiency and security for AIoT. The double-layer blockchain, coupled with a two-stage consensus algorithm, drives the hierarchical FL process to enable efficient and reliable agricultural knowledge-sharing. In addition, adopts an adaptive model aggregation algorithm to dynamically tune noise levels based on the model quality, further improving the learning security and model credibility. Finally, the extensive experimental results demonstrate that not only improves the model accuracy by up to 21.17% compared with the state-of-the-art baselines, but also enhances the privacy protection within an additional error of only 2.1%. ? 2014 IEEE.