On signal encryption at MapReduce and collaborative attribute-based access with ECAs for a preprocessed data set with ML in a privacy-preserving health 4.0

Latest Industry 4.0 developments and data science advances have transformed traditional hospital-centric patient care into a Healthcare 4.0 system that uses advanced technology-driven decision-making involving several low resource constraints electronic devices such as Personal Digital Assistants (P...

Full description

Saved in:
Bibliographic Details
Main Authors: Arnab Mitra, Anabik Pal
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:e-Prime: Advances in Electrical Engineering, Electronics and Energy
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772671125000907
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Latest Industry 4.0 developments and data science advances have transformed traditional hospital-centric patient care into a Healthcare 4.0 system that uses advanced technology-driven decision-making involving several low resource constraints electronic devices such as Personal Digital Assistants (PDAs), Smartphones, Tablets, etc. In a healthcare system, the data is the key fuel for such improved technology, which presently is an instance of big data. However, due to several data protection laws and regulations, the confidentiality and security of healthcare data are a big concern. To support the cost-effectiveness modeling of data security and privacy in Healthcare 4.0 scenarios, the Privacy-Preserving Health 4.0 (PPH 4.0) framework was proposed by integrating Machine Learning (ML) and Elementary Cellular Automata (ECAs). The ML techniques were proposed to offer effective data pre-processing and dimensionality reduction. In contrast, ECAs were proposed to offer an integral parallelism and very-large-scale-integration (VLSI) capability at a low cost for its physical implementation and low power consumption towards data security and privacy of such big data in PPH 4.0. The presented research presents signal encryption at MapReduce with ECAs generated pseudo-random noise signal and collaborative attribute-based access with ECAs for a preprocessed data set with ML in PPH 4.0. Experimental results and analysis of the proposed approach reveal its true nature and suitability are for an enhanced Healthcare 4.0 system, i.e., PPH 4.0.
ISSN:2772-6711