Internet of Things and Cloud Computing-based Disease Diagnosis using Optimized Improved Generative Adversarial...

Area of Science:

• Artificial Intelligence in Healthcare
• Internet of Things (IoT) for Health Monitoring
• Cloud Computing for Medical Data Management

Background:

• Integration of IoT and cloud services improves healthcare communication and quality of life.
• AI and deep learning enable proactive healthcare through predictive analytics.
• Recurrent neural networks on electronic health records enhance disease prediction accuracy.

Purpose of the Study:

• To propose an Internet of Things and Cloud Computing-based Disease Diagnosis (IOT-CC-DD) system.
• To utilize an Optimized Improved Generative Adversarial Network (IGAN) for disease classification.
• To enhance smart healthcare systems with accurate and efficient disease prediction.

Main Methods:

• IoT devices and wearable sensors collect patient data (diabetes, CKD, heart disease) and store it in the cloud.
• Data preprocessing is performed on cloud-stored patient data.
• An Improved Generative Adversarial Network (IGAN), optimized with the Flamingo Search Optimization Algorithm (FSOA), classifies data as disease-free or diseased.

Main Results:

• The proposed IOT-CC-DD-OICAN-SHS method demonstrates superior accuracy and specificity.
• Achieves lower execution time compared to existing methods (IoT-C-SHMS-HDP-DL, PPEDL-MDTC, CSO-CLSTM-DD-SHS).
• Validated using performance metrics in a simulated environment using Cloud Sim.

Conclusions:

• The proposed IOT-CC-DD-OICAN-SHS offers a significant advancement in smart healthcare diagnostics.
• Optimized IGAN effectively classifies diseases from large, complex patient datasets.
• The system provides a foundation for timely intervention and preventative care in healthcare.