Dynamic Q-Learning Optimization for Anomaly-Aware Intelligent Healthcare Access Security Framework

View at publisher Summarise with VIRAT
Authors: G. Sivagamidevi, C. Pabitha
Cited by: 0
References: 24

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The demand for intelligent, flexible, and safe access control systems has grown due to the quick expansion of cloud- based healthcare applications. Unauthorized access behaviors and developing abnormalities are often missed by traditional rule-based security frameworks. An intelligent healthcare access security system with adaptive learning and real-time anomaly detection capabilities is proposed in this research using a DQ-NAC (Deep Q-Network with Adaptive Clustering). To dynamically modify authorizations, spot suspicious activity, and provide secure access choices, the platform combines behavioral data analysis and reinforcement learning. Compared to traditional access monitoring techniques, experimental testing shows major improvements in anomaly detection accuracy, reaction speed, and flexibility. The results demonstrate Q-Learning’s efficacy as a lightweight, self-sufficient security optimizer for upcoming healthcare systems.

Fields of Study & Subjects

Access Control and Trust Network Security and Intrusion Detection User Authentication and Security Systems

Publication details

Journal / source
International Conference on Image Processing and Capsule Networks (ICIPCN)
Pages
1254–1261
Publication date
27 January 2026
Language
EN