Deep Learning-Based Privacy Preservation and Data Analytics for IoT Enabled Healthcare

Abstract

With the development of the industrial Internet of Things (IIoT), intelligent healthcare aims to build a platform to monitor users’ health-related information based on wearable devices remotely. The evolution of blockchain and artificial intelligence technology also promotes the progress of secure intelligent healthcare. However, since the data are stored in the cloud server, it still faces the risk of being attacked and privacy leakage. Note that little attention has been paid to the security issue of privacy information mixed in raw data collected from large number of distributed and heterogeneous wearable healthcare devices. To solve this problem, in this article, we design a deep learning-based privacy preservation and data analytics system for IoT enabled healthcare. At the user end, we collect raw data and separate the users’ privacy information in the privacy-isolation zone. At the cloud end, we analyze the health-related data without users’ privacy information and construct a delicate security module based on the convolutional neural network. We also deploy and evaluate the prototype system, where extensive experiments prove its effectiveness and robustness.