الفهرس 
Chapter 1 IntroductionOnly 14 pages are availabe for public view
 |  | from | 109 |  |  |
| | | from | 109 | | |
Abstract
This thesis focuses on the development of a secure remote diabetes monitoring (SR-DM) model that utilizes smart medical devices and the internet of things (IoT) to enhance healthcare systems. With the growing number of diabetes patients, it is crucial to regularly evaluate their health conditions in order to detect and prevent significant illnesses. However, the transmission of large volumes of sensitive medical data poses challenges in terms of IoT data security. To address these challenges, the proposed SR-DM model incorporates hybrid encryption, specifically combining the advanced encryption standard (AES) and elliptic curve cryptography (ECC). This hybrid encryption approach ensures that patients’ sensitive data remains protected within IoT platforms that are based on cloud infrastructure. By leveraging this secure encryption technique, the SR-DM model aims to safeguard patient privacy and data integrity. In addition to data security, the SR-DM model utilizes machine learning (ML) algorithms to analyze medical data captured by smart health IoT devices and predict critical situations related to patients’ health statuses. Among various ML algorithms, the random forest (RF) classification method outperforms others such as K-nearest neighbors (KNN), naïve bayes (NB), decision tree (DT), and support vector machine (SVM) classifiers. With an accuracy of 90.4%, precision of 89.7%, recall of 85.4%, and an average area under curve (AUC) of 94.8%, the RF classifier demonstrates superior performance in predicting critical health situations. The results of the study indicate that the proposed SR-DM model, employing the hybrid encryption approach (AES&ECC) and RF classification, offers several advantages. Firstly, it exhibits a significantly reduced time for encrypting and decrypting data files transmitted from IoT devices to cloud storage when compared to alternative techniques proposed in previous research. This indicates the efficiency and effectiveness of the proposed encryption method in securing IoT data. Secondly, the RF classifier demonstrates high accuracy and reliability in analyzing medical data, enabling the detection of critical health conditions promptly. Consequently, the proposed SR-DM model effectively addresses the challenges of secure data sharing in cloud environments, providing a viable solution for maintaining data privacy and protection. By establishing a secure remote health monitoring system that relies on cloud-based platforms for data storage and management, this model contributes to improving healthcare outcomes for diabetes.