期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 16, 期 10, 页码 6663-6672出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2019.2962844
关键词
Data models; Data collection; Quality of service; Cloud computing; Data privacy; Indexes; Edge computing; Deep learning; federated learning; Internet of vehicles (IoV); semisupervised learning
类别
资金
- General Projects of Social Sciences in Fujian Province [FJ2018B038]
- Natural Science Foundation of Fujian Province of China [2018J01092]
- National Natural Science Foundation of China [61872154, 61972352, 61772148, 61874120, TII-19-4449]
The development of smart cities and deep learning technology is changing our physical world to a cyber world. As one of the main applications, the Internet of Vehicles has been developing rapidly. However, privacy leakage and delay problem for data collection remain as the key concerns behind the fast development of the cyber intelligence technologies. If the original data collected are directly uploaded to the cloud for processing, it will bring huge load pressure and delay to the network communication. Moreover, during this process, it will lead to the leakage of data privacy. To this end, in this article we design a data collection and preprocessing scheme based on deep learning, which adopts the semisupervised learning algorithm of data augmentation and label guessing. Data filtering is performed at the edge layer, and a large amount of similar data and irrelevant data are cleared. If the edge device cannot process some complex data independently, it will send the processed and reliable data to the cloud for further processing, which maximizes the protection of user privacy. Our method significantly reduces the amount of data uploaded to the cloud, and meanwhile protects the user's data privacy effectively.
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