Browsing by Author "Ragel, RG"

Now showing 1 - 3 of 3

item: Conference-Full-text
Control Channel Denial-of-Service Attack in SDN-Based Networks
(IEEE, 2020-07) Sriskandarajah, S; McKague, M; Foo, E; Ragel, RG; Karunarathna, SN; Jadidi, Z; Weeraddana, C; Edussooriya, CUS; Abeysooriya, RP
Software-Defined Networking (SDN) is an architectural approach that fulfils the requirement of high bandwidth and the dynamic nature of current applications. One of the key features of the SDN architecture is the separation of the control logic from data plane devices. This key feature introduces a new type of control traffic in the SDN architecture, which opens the space for new vulnerabilities to SDN-based networks. In this paper, we first present an attack model to exploit the control channel of the SDN architecture. We then experimentally evaluate the impact of the attack on the end-users of the SDNbased network using our physical experimental testbed. Our experimental results clearly show that the control channel DoS attack has a major impact on the end-users of the SDN-based networks.
item: Conference-Full-text
Detection of novel biomarker genes of alzheimer’s disease using gene expression data
(IEEE, 2020-07) Perera, S; Hewage, K; Gunarathne, C; Navarathna, R; Herath, D; Ragel, RG; Weeraddana, C; Edussooriya, CUS; Abeysooriya, RP
It is well recognized, that most common form of dementia is Alzheimer’s disease and a successful cure or medication is not discovered. A plethora of research has been conducted to understand the underlying mechanism and the pathogenesis of the Alzheimer’s disease. To explore the underlying genetic structure of the disease, gene expression data is being used by many researches and computational and statistical approaches were used to identify possible genes that are risk. In this paper, we propose a machine learning framework that can be used to identify possible bio-marker genes. Our experiments discover possible set of 14 genes, which some of them are validated by biological sources. We also present a critical analysis of the propose machine learning framework using GSE5281 gene dataset.
item: Conference-Full-text
Virtual patient simulator for skill training in dentistry and investigation of its effectiveness
(IEEE, 2023-12-09) Dharmathilaka, AVH; Jayathilaka, HADTT; Madushanki, KHHC; Jayasinghe, U; Ragel, RG; Bandara, DL; Abeysooriya, R; Adikariwattage, V; Hemachandra, K
Diagnostic errors represent a significant source of harm throughout healthcare professions. Similarly, in dentistry, these could lead to missed diagnoses, wrong or unnecessary therapies, loss of patient trust, and even life-threatening complications. Therefore, it is important to enhance the cognitive and kinetic skills of healthcare professionals to minimize or avoid errors that could happen during patient management. However, in traditional in-class clinical settings, achieving optimum training could be limited due to the unavailability of an adequate number of clinical supervisors, fewer resources, lack of opportunities for detailed attention; constructive feedback and playback systems. In contrast, Virtual patient simulators, which are computerbased software programs provide a simulated environment where health professionals can practice, learn, and study various clinical scenarios and procedures repeatedly until the required skills are gained. Yet, such systems may lack realism and are not tailormade to support educational approaches such as problem-based learning with increased guided practice at a relatively low cost. Hence, this work proposes a web-based virtual patient simulator as a supportive tool to further help students to grow and advance the required diagnostic skills in a virtual environment. The system enables students to gather the patient’s medical history, conduct physical examinations, request and analyze laboratory and imaging tests and ultimately make informed diagnostic and treatment decisions. The performance of the system was compared with the traditional teaching method and statistical data demonstrated similar performance as with the traditional method.