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

Hongliang Bi, Jiajia Liu, Nei Kato

Research output: Contribution to journalArticlepeer-review

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 is 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, 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 (CNN). We also deploy and evaluate the prototype system, where extensive experiments prove its effectiveness and robustness.

Original languageEnglish
JournalIEEE Transactions on Industrial Informatics
DOIs
Publication statusAccepted/In press - 2021
Externally publishedYes

Keywords

  • Biomedical monitoring
  • Cloud computing
  • data analytics
  • Data privacy
  • deep learning
  • IoT enabled healthcare
  • Legged locomotion
  • Medical services
  • Privacy
  • privacy preservation
  • Security

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Information Systems
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Deep Learning-based Privacy Preservation and Data Analytics for IoT Enabled Healthcare'. Together they form a unique fingerprint.

Cite this