ICT-Guided Glycemic Information Sharing Through Artificial Neural Telecare Network.

Area of Science:

• Health Informatics
• Cybersecurity
• Artificial Intelligence

Background:

• The COVID-19 pandemic accelerated the adoption of telecare and highlighted the need for secure health data sharing.
• Increased consumption of high Glycemic Index (GI) foods during lockdowns is linked to various health issues, including diabetes and dental problems.
• Existing methods for securing health data may be vulnerable to sophisticated cyberattacks.

Purpose of the Study:

• To develop and evaluate a novel, secure method for sharing glycemic information in telecare settings.
• To enhance the security of patient data against Man-In-The-Middle attacks using advanced encryption techniques.
• To assess the efficacy and cryptographic performance of the proposed system for managing glycemic data.

Main Methods:

• Implementation of a secure information sharing technique using artificial neural computational learning suite.
• Generation of a salp swarm-based session key for modular encryption of glycemic data.
• Utilizing symmetric Tree Parity Machines (TPMs) for synchronized weight vector updates without full session key exchange.

Main Results:

• The proposed encryption method demonstrated high resistance to Man-In-The-Middle attacks.
• Mathematical tests confirmed the efficacy and acceptance of the developed technique.
• The cryptographic time for four GI modules was recorded at 0.956 ms, 0.468 ms, 0.643 ms, and 0.771 ms, indicating efficient processing.

Conclusions:

• The developed secure glycemic information sharing technique is effective and robust for telecare applications.
• The salp swarm-based key generation and TPM synchronization offer enhanced security and efficiency.
• This approach supports better management of health data, particularly concerning diet-related diseases exacerbated by lifestyle changes.