Secure Cloud-Integrated IoT Framework for Diabetes Detection | ||||
| Delta University Scientific Journal | ||||
| Volume 8, Issue 1, April 2025, Page 309-321 PDF (889.43 K) | ||||
| Document Type: Original research papers | ||||
| DOI: 10.21608/dusj.2024.433474 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
Dalia Ebrahim Hamid  1; Hanan M. Amer2; Hossam El-Din Salah Moustafa2; Hanaa Salem Marie3
| ||||
| 1Electronics and Communications Department, Faculty of Engineering, Delta University for Science and Technology, Gamsaa, Egypt | ||||
| 2Electronics and Communication Engineering Department, Faculty of Engineering, Mansoura University, Mansoura, Egypt | ||||
| 3Faculty of Artificial Intelligence, Delta University for Science and Technology, Gamsaa, Egypt. | ||||
| Abstract | ||||
| The Internet of Things (IoT) and the smart health devices have enhanced healthcare platforms by enabling the remote monitoring of patients' health. Given the unpredictable rise in the diabetes patients number, it is crucial to regularly assess their health conditions to prevent serious illnesses. However, the transmission of a massive volume of sensitive health data brings significant IoT data security challenges. This paper introduces a secure and remote system for diabetes monitoring that employs the Advanced Encryption Standard (AES) to protect patients' sensitive data on cloud-based IoT platforms. In this model, machine learning (ML) methods analyse health data collected by smart health IoT devices to predict critical situations and determine patients' health statuses. The results show that the AES method provides the fastest encryption and decryption times for data files sent from IoT devices to cloud storage. Additionally, the Support Vector Machine (SVM) classification method demonstrates high performance, with an accuracy of 96%, precision of 92.4%, F-score of 95.3%, and recall of 94.3%. Based on these results, the proposed system successfully establishes a efficient and secure platform for health monitoring. | ||||
| Keywords | ||||
| Internet of Things; healthcare; cloud computing; machine learning; classification; security | ||||
|
Statistics Article View: 50 PDF Download: 37 |
||||
