Blockchain‐Powered IoT Healthcare Framework With Dandelion Depthwise Separable Convolutional Neural Network for Enhanced Security

View at publisher Summarise with VIRAT
Authors: Harish Kumar Taluja, Anuradha Taluja, Bhuvana Suganthi D, Loganathan Guganathan
Cited by: 0
References: 33

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

ABSTRACT Technological trends are evolving fairly quickly within healthcare systems with blockchain and Deep Learning Hybrid technologies seen as at the pinnacle of making patient care, scalability and security better. Indeed, challenges such as Interoperability, privacy, and data integrity are some of the challenges that normal healthcare systems face, especially in the IoT paradigm. Worse still, secure and decentralized management of data is what is needed. Using a combination of deep learning architectures for IoT security and scalability, as well as data protection through blockchain technology, this study aims at designing a new secure healthcare system that can be implemented using the IoT network. In the present work, a Triple Attention Depthwise Separable Convolutional Neural Network (TADSCNN) is designed with the help of Dandelion Optimizer (DO) incorporated with blockchain. Thus, the proposed system achieved F1‐score of 0.993, accuracy of 0.999, precision of 0.992, and recall of 0.994, which means that the system's performance is quite high. Furthermore, it supports 220 kbps of throughput and 85 s latency, and 2.9 s processing time for the protocol while providing data secrecy of 99.12%. This framework offers a viable, scalable, and secure means of addressing Internet of Things health care system.

Fields of Study & Subjects

Blockchain Technology Applications and Security Internet of Things and AI IoT and Edge/Fog Computing

Publication details

Journal / source
Transactions on Emerging Telecommunications Technologies
Volume
37
Issue
4
Publication date
22 March 2026
Language
EN