Internet of Medical Things (IoMT) and Reflective Belief Design-Based Big Data Analytics with Convolution Neural...

Area of Science:

• Medical Informatics
• Artificial Intelligence
• Big Data Analytics

Background:

• The Internet of Medical Things (IoMT) offers dynamic patient health monitoring for early disease detection.
• Big data generated from diverse sources presents challenges for traditional analytical methods.
• Metaheuristic algorithms are powerful tools for complex optimization and classification tasks.

Purpose of the Study:

• To develop a metaheuristic optimization algorithm for big data analysis within the IoMT framework.
• To enhance the prediction accuracy of diabetes and associated cardiac risks using advanced AI techniques.

Main Methods:

• Implementation of the Gravitational Search Optimization Algorithm (GSOA) for data optimization.
• Utilizing a Deep Belief Network with Convolutional Neural Networks (DBN-CNNs) for data classification and prediction.
• Employing Support Vector Machines (SVM) for cardiac risk prediction based on diabetes classification.

Main Results:

• The GSOA-DBN-CNN model demonstrated superior performance in disease prediction.
• Significant improvements were observed in accuracy, precision, recall, F1-score, and Peak Signal-to-Noise Ratio (PSNR).

Conclusions:

• The proposed GSOA-DBN-CNN model is effective for big data analysis in IoMT for disease prediction.
• This approach shows promise for improving diagnostic capabilities in intelligent healthcare systems.