Data Mining and Machine Learning-Based Healthcare Monitoring in Cloud-IoT

Healthcare monitoring Cloud-IoT systems use data mining and machine learning methods to analyse patient data in real-time from linked devices. By offering insights for the early diagnosis of anomalies and individualized treatment suggestions, this strategy improves healthcare management. In this research first the Collect and Load the Clevant Heart Disease Dataset for Data Collection Process. Next, preprocess the loaded data using the Synthetic Minority Oversampling Technique (SMOTE), and then the feature extraction process is done using the Principal Component Analysis (PCA) Method. In this case, the characteristic must be extracted by feeding a specific column. The classification procedure is then carried out using Generative Adversarial Networks (GAN) and an optimization approach called Adaptive Moment Estimation. This is where the model executes GAN operations, and the output will be produced. The data is then transferred to an edge-cloud environment to minimize storage problems and provide instant access to critical data. This process starts with the encryption and decryption of data using Homomorphic encryption with the Laplacian technique. In addition, have taken the generat