.png){kind=icon}
.png){kind=icon}
Return
Optimized Adaboost Support Vector Machine-Based Encryption for Securing IoT-Cloud Healthcare Data
.png){kind=icon}
OA
AI
DOI：10.3390/s25030731.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The Internet of Things (IoT) connects various medical devices that enable remote monitoring, which can improve patient outcomes and help healthcare providers deliver precise diagnoses and better service to patients. However, IoT-based healthcare management systems face significant challenges in data security, such as maintaining a triad of confidentiality, integrity, and availability (CIA) and securing data transmission. This paper proposes a novel AdaBoost support vector machine (ASVM) based on the grey wolf optimization and international data encryption algorithm (ASVM-based GWO-IDEA) to secure medical data in an IoT-enabled healthcare system. The primary objective of this work was to prevent possible cyberattacks, unauthorized access, and tampering with the security of such healthcare systems. The proposed scheme encodes the healthcare data before transmitting them, protecting them from unauthorized access and other network vulnerabilities. The scheme was implemented in Python, and its efficiency was evaluated using a Kaggle-based public healthcare dataset. The performance of the model/scheme was evaluated with existing strategies in the context of effective security parameters, such as the confidentiality rate and throughput. When using the suggested methodology, the data transmission process was improved and achieved a high throughput of 97.86%, an improved resource utilization degree of 98.45%, and a high efficiency of 93.45% during data transmission.
Keywords:
machine learning
cloud computing
medical applications
healthcare data management
data encryption
data decryption
encryption time
decryption time
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.5
Papers:
7.1W
Citations:
20.9W