Browsing by Author "Bandara, B"

Now showing 1 - 2 of 2

Embargo
Application of Federated Learning in Health Care Sector for Malware Detection and Mitigation Using Software Defined Networking Approach
(IEEE, 2022-10-11) Panagoda, D; Malinda, C; Wijetunga, C; Rupasinghe, L; Bandara, B; Liyanapathirana, C
This research takes us forward with the concepts of Federated Learning and SDN to introduce an efficient malware detection technique and provide a mitigation mechanism to give birth to a resilient and automated healthcare sector network system by also adding the feature of extended privacy preservation. Due to the daily transformation of new malware attacks on hospital ICEs, the healthcare industry is at an undefinable peak of never knowing its continuity direction. The state of blindness by the array of indispensable opportunities that new medical device inventions and their connected coordination offer daily, a factor that should be focused driven is not yet entirely understood by most healthcare operators and patients. This solution has the involvement of four clients in the form of hospital networks to build up the federated learning experimentation architectural structure with different geographical participation to reach the most reasonable accuracy rate with privacy preservation. While the logistic regression with cross-entropy conveys the detection, SDN comes in handy in the second half of the research to stack up the initial development phases of the system with malware mitigation based on policy implementation. The overall evaluation sums up with a system that proves the accuracy with the added privacy. It is no longer needed to continue with traditional centralized systems that offer almost everything but not privacy.
Embargo
Criminal investigation and management system using CCTV footage - "Eagle Eye"
(IEEE, 2021-12-02) Fernando, K. P. P. E; Perera, H. G. G. M; Gunatilleke, C. K. De. S; Fernando, W. S. D; Bandara, B; Wikramasinghe, L
Automated criminal identification is not a very popular topic in Sri Lanka. To identify criminals, the methods which authorities are using are unnecessarily time-consuming. To make this process immovable, identifying a wanted person using an automated system would be a better alternative rather than the current practices. Current practices and techniques such as gathering records from eyewitnesses are not highly reliable. Even though scanning through CCTV camera footage manually is again laborious. Using modern technologies such as biometrics would be the best way to achieve this task in terms of accuracy. We will also use abnormal behavioral detection accompanied by Threatening weapons. As biometric techniques, using face recognition and figure recognition will provide the most promising result. Along with the modified image enhancement method that we are suggesting, the system will be able to capture and process the task in a much better way. Although biometric systems have already been used in society, there is no such system which can be used to identify and verify criminals. we used algorithms such as CNN, DNN, LBPH and Deep learning. As a final result, the system will automatically identify the entire crime incident to improve the quality of the footage, detect the abnormal behaviors accompanied by threatening weapons, identity & recognize the registered criminals using faces and their figures automatically with a minimum amount of time and higher accuracy level.