Improved security for IoT-based remote healthcare systems using deep learning with jellyfish search optimization...

Area of Science:

• Biomedical Engineering
• Computer Science
• Artificial Intelligence

Background:

• Rising chronic diseases and aging populations necessitate advanced remote health monitoring solutions.
• Internet of Things (IoT) offers potential for remote patient care but faces challenges in bandwidth and energy constraints.
• Efficient resource application requires balancing machine analysis and human insight while minimizing data transmission.

Purpose of the Study:

• To propose an Enhanced Security Mechanism for Human-Centered Systems using Deep Learning with Jellyfish Search Optimizer (ESHCS-DLJSO) for IoT healthcare applications.
• To enable secure medical data transmission and early health problem recognition in human-machine interfaces.
• To address the critical threats posed by bandwidth or energy constraints in remote monitoring environments.

Main Methods:

• Utilized min-max normalization for data preprocessing.
• Employed bacterial foraging optimization algorithm (BFOA) for feature extraction.
• Implemented a convolutional neural network with long short-term memory (CNN-LSTM-Attention) for disease detection and classification.
• Applied jellyfish search optimizer (JSO) for hyperparameter tuning.

Main Results:

• The ESHCS-DLJSO technique demonstrated superior performance on an IoT healthcare security dataset.
• Achieved a high accuracy of 99.43%, outperforming existing approaches.
• Successfully enabled secure data communication and early disease identification.

Conclusions:

• The ESHCS-DLJSO approach provides an effective solution for secure and efficient remote health monitoring in IoT healthcare.
• The integration of deep learning and optimization algorithms enhances disease detection and system security.
• This method offers a promising pathway for improving patient care and reducing healthcare costs.