Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM Algorithm

With the rapid development of information technology and the advancement of medical informatization, medical big data plays an increasingly important role in diagnosis, treatment, health management, and other aspects. However, the high sensitivity and privacy of medical data also bring serious secur...

Full description

Saved in:
Bibliographic Details
Main Authors: Xiaoliang Zhang, Tianwei Guo
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10703048/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850283153661362176
author Xiaoliang Zhang
Tianwei Guo
author_facet Xiaoliang Zhang
Tianwei Guo
author_sort Xiaoliang Zhang
collection DOAJ
description With the rapid development of information technology and the advancement of medical informatization, medical big data plays an increasingly important role in diagnosis, treatment, health management, and other aspects. However, the high sensitivity and privacy of medical data also bring serious security challenges. A privacy risk assessment model combining information entropy and fuzzy C-means clustering algorithm is proposed to address this issue. This model is based on information entropy to construct an access control model and quantify the privacy risks of user access behavior. Cluster analysis is conducted on users using the fuzzy C-means clustering algorithm, and different permissions are assigned based on their access habits. The experimental results show that when the iteration number is 120, the root mean square error value of the improved fuzzy C-means clustering model is 0.08, and the accuracy is 0.98. When the dataset is 100, it can be seen that each model can learn the information in the dataset relatively completely. When the dataset reaches 800, the judgment time of the improved fuzzy C-means clustering model is 0.6 seconds. When the number of users reaches 100, the judgment time of the improved fuzzy C-means clustering model is 1.8 seconds. The research results indicate that the proposed medical big data privacy risk assessment model, which combines information entropy and improved fuzzy C-means clustering algorithm, has excellent performance and can provide new technical means for medical data privacy protection, enhancing the security and reliability of medical information systems.
format Article
id doaj-art-dd2175c9abb84c54824d95c3dab977ca
institution OA Journals
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-dd2175c9abb84c54824d95c3dab977ca2025-08-20T01:47:50ZengIEEEIEEE Access2169-35362024-01-011214819014820010.1109/ACCESS.2024.347203710703048Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM AlgorithmXiaoliang Zhang0Tianwei Guo1https://orcid.org/0009-0002-2418-8960School of Cyber Science and Engineering, Southeast University, Nanjing, ChinaInformation Statistics Centre, Huai’an Second People’s Hospital, Huaian, ChinaWith the rapid development of information technology and the advancement of medical informatization, medical big data plays an increasingly important role in diagnosis, treatment, health management, and other aspects. However, the high sensitivity and privacy of medical data also bring serious security challenges. A privacy risk assessment model combining information entropy and fuzzy C-means clustering algorithm is proposed to address this issue. This model is based on information entropy to construct an access control model and quantify the privacy risks of user access behavior. Cluster analysis is conducted on users using the fuzzy C-means clustering algorithm, and different permissions are assigned based on their access habits. The experimental results show that when the iteration number is 120, the root mean square error value of the improved fuzzy C-means clustering model is 0.08, and the accuracy is 0.98. When the dataset is 100, it can be seen that each model can learn the information in the dataset relatively completely. When the dataset reaches 800, the judgment time of the improved fuzzy C-means clustering model is 0.6 seconds. When the number of users reaches 100, the judgment time of the improved fuzzy C-means clustering model is 1.8 seconds. The research results indicate that the proposed medical big data privacy risk assessment model, which combines information entropy and improved fuzzy C-means clustering algorithm, has excellent performance and can provide new technical means for medical data privacy protection, enhancing the security and reliability of medical information systems.https://ieeexplore.ieee.org/document/10703048/Medical carebig datarisk assessmentinformation entropyFCMprivacy protection
spellingShingle Xiaoliang Zhang
Tianwei Guo
Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM Algorithm
IEEE Access
Medical care
big data
risk assessment
information entropy
FCM
privacy protection
title Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM Algorithm
title_full Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM Algorithm
title_fullStr Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM Algorithm
title_full_unstemmed Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM Algorithm
title_short Privacy Risk Assessment of Medical Big Data Based on Information Entropy and FCM Algorithm
title_sort privacy risk assessment of medical big data based on information entropy and fcm algorithm
topic Medical care
big data
risk assessment
information entropy
FCM
privacy protection
url https://ieeexplore.ieee.org/document/10703048/
work_keys_str_mv AT xiaoliangzhang privacyriskassessmentofmedicalbigdatabasedoninformationentropyandfcmalgorithm
AT tianweiguo privacyriskassessmentofmedicalbigdatabasedoninformationentropyandfcmalgorithm