A Privacy-Preserving Secure Data Processing
Scheme for the Internet of Medical Things
Ying Huang and Yongmei Su
The Internet of Medical Things (IoMT) offers
diverse application support through monitoring, analysis, and
recommendations. This application paradigm relies on sensitive
internal and external data to meet user needs. This article
introduces a secure data processing scheme for leveraging the
IoMT application performance. This scheme is named Persuaded
Data Processing with Digital Security (PDP-DS), ensuring user
and data privacy. This scheme focuses on IoMT-aided remote
monitoring application security where data openness is high and
false data chances are high. During the application support, the
blockchain concept is applied for data authentication. In this
scheme, user-verified digital signatures are used for
authentication. This scheme provides data processing recommendations
based on the deep learning paradigm. This output is
authenticated alone using a password/ PIN-based digital signature.
The learning process identifies the processing required and
security-filtered instances using the recursive states identified. The
proposed scheme ensures fewer false data processing based on its
attributes and recommendation factor. PDP-PS reduces the
considered metrics to 9.95% (for process delay), 10.19% (for
service delay), 10.6% (for replication factor), 10.44% (for false
rate), and 7.39% (for backlogs).