|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
Healthcare is the only sector where machine learning (ML) have several uses. Due to the internet's rapid development and expansion, traditional patient service methods were supplanted by electronic healthcare systems. Machine learning algorithms is of greater advantage in various domains to make the life easier and better. We can carry out medical dispersed data analysis as a boon to the networked connection of these devices. The diversity of machine learning technology has been applied in the health sector applying typical centralised learning algorithms to the decentralised data collected from the devices offers a challenging dilemma. With no access to user personal information, a convolutional neural network is used to analyse the health-related data in the cloud. As a result, a safe access control module is introduced for the Healthcare system by machine learning models that is based on user attributes. The suggested CNN classifier achieves a 95% accuracy, recall, and F1 score. Higher performance is gained as the training set's size is increased. The system functions better without data augmentation when it is added. Furthermore, a higher user count enables accuracy of about 98% to be attained. Experimental research shows that the proposed solution is reliable and efficient in terms of little privacy leakage and good data integrity.
Keyword
Machine learning, model, Health care, application of machine learning, emerging technologies, CNN
PDF Download (click here)
|
|
|
|
|