Welcome to the InfoSci Platform
Reference Hub41
Secured and Privacy-Based IDS for Healthcare Systems on E-Medical Data Using Machine Learning Approach

Secured and Privacy-Based IDS for Healthcare Systems on E-Medical Data Using Machine Learning Approach

Sudhakar Sengan, Osamah Ibrahim Khalaf, Vidya Sagar P., Dilip Kumar Sharma, Arokia Jesu Prabhu L., Abdulsattar Abdullah Hamad
Copyright: © 2022 |Volume: 11 |Issue: 3 |Pages: 11
ISSN: 2160-9551|EISSN: 2160-956X|EISBN13: 9781683182597|DOI: 10.4018/IJRQEH.289175
Cite Article Cite Article

MLA

Sengan, Sudhakar, et al. "Secured and Privacy-Based IDS for Healthcare Systems on E-Medical Data Using Machine Learning Approach." IJRQEH vol.11, no.3 2022: pp.1-11. http://doi.org/10.4018/IJRQEH.289175

APA

Sengan, S., Khalaf, O. I., Vidya Sagar P., Sharma, D. K., Arokia Jesu Prabhu L., & Hamad, A. A. (2022). Secured and Privacy-Based IDS for Healthcare Systems on E-Medical Data Using Machine Learning Approach. International Journal of Reliable and Quality E-Healthcare (IJRQEH), 11(3), 1-11. http://doi.org/10.4018/IJRQEH.289175

Chicago

Sengan, Sudhakar, et al. "Secured and Privacy-Based IDS for Healthcare Systems on E-Medical Data Using Machine Learning Approach," International Journal of Reliable and Quality E-Healthcare (IJRQEH) 11, no.3: 1-11. http://doi.org/10.4018/IJRQEH.289175

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Existing methods use static path identifiers, making it easy for attackers to conduct DDoS flooding attacks. Create a system using Dynamic Secure aware Routing by Machine Learning (DAR-ML) to solve healthcare data. A DoS detection system by ML algorithm is proposed in this paper. First, to access the user to see the authorized process. Next, after the user registration, users can compare path information through correlation factors between nodes. Then, choose the device that will automatically activate and decrypt the data key. The DAR-ML is traced back to all healthcare data in the end module. In the next module, the users and admin can describe the results. These are the outcomes of using the network to make it easy. Through a time interval of 21.19% of data traffic, the findings demonstrate an attack detection accuracy of over 98.19%, with high precision and a probability of false alarm.