Browsing by Author "Jayasinghe, D"

Now showing 1 - 5 of 5

Embargo
Computer Vision for Autonomous Driving
(IEEE, 2021-12-09) Kanchana, B; Peiris, R; Perera, D; Jayasinghe, D; Kasthurirathna, D
Computer vision in self-driving vehicles can lead to research and development of futuristic vehicles that can mitigate the road accidents and assist in a safer driving environment. By using the self-driving technology, the riders can be roamed to their destinations without using human interaction. But in recent times self-driving vehicle technology is still at the early stage. Mostly in the rushed areas like cities it becomes challenging to deploy such autonomous systems because even a small amount of data can cause a critical accident situation. In Order to increase the autonomous driving conditions computer vision and deep learning-based approaches are tended to be used. Finding the obstacles on the road and analyzing the current traffic flow are mainly focused areas using computer vision-based approaches. As well as many researchers using deep learning-based approaches like convolutional neural networks to enhance the autonomous driving conditions. This research paper focused on the evaluation of computer vision used in self-driving vehicles.
Embargo
Enhancing Conversational AI Model Performance and Explainability for Sinhala-English Bilingual Speakers
(IEEE, 2022-12-09) Dissanayake, I; Hameed, S; Sakalasooriya, A; Jayasinghe, D; Abeywardhana, L; Wijendra, D
Natural language processing has become essential to modern conversational tools and dialogue engines, including Chatbots. However, applying natural language processing to low-resource languages is challenging due to their lack of digital presence. Sinhala is the native language of approximately nineteen million people in Sri Lanka and is one of many low-resource languages. Moreover, the increase in using code-switching: alternating two or more languages within the same conversation, and code-mixing: the practice of representing words of a language using characters of another language, has become another major issue when processing natural languages. Apart from natural language processing, the explainability of opaque machine learning models utilized in chatbots has become another prominent concern. None of the existing modern chatbot development platforms supports explainability and relies on a performance score such as accuracy or f1-score. This paper proposes a no-code chatbot development platform with a series of built-in novel natural language processing, model evaluation, and explainability tools to tackle the problems of processing Sinhala-English code-switching and code-mixing natural language data and model evaluation in modern chatbot development platforms.
Open Access
Fast Tail Index Estimation for Power Law Distributions in R
(2020-06-18) Munasinghe, R; Kossinna, P; Jayasinghe, D; Wijeratne, D
Power law distributions, in particular Pareto distributions, describe data across diverse areas of study. We have developed a package in R to estimate the tail index for such datasets focusing on speed (in particular with large datasets), keeping in mind ease of use, as well as accuracy. In this short article, we provide a user guide to our package along with the results obtained highlighting the speed advantages of our package.
Embargo
Network Traffic Prediction for a Software Defined Network Based Virtualized Security Functions Platform
(IEEE, 2021-12-06) Jayasinghe, D; Rankothge, W. H; Gamage, N. D. U; Gamage, T. C. T; Amarasinghe, D. A. H. M; Uwanpriya, S. D. L. S
Software-Defined Networking (SDN) has become a popular and widely used approach with Cloud Service Providers (CSPs). With the introduction of Virtualized Security Functions (VSFs), and offering them as a service, CSPs are exploring effective and efficient approaches for resource management in the cloud infrastructure, considering specific requirements of VSFs. Network traffic prediction is an important component of cloud resource management, as prediction helps CSPs to take necessary proactive management actions, specifically for VSFs. This research focuses on introducing an algorithm to predict the network traffic traverse via a cloud platform where VSFs are offered as a service, by using the Auto-Regressive Integrated Moving Average (ARIMA) model. In this paper, the implementation and performance of the traffic prediction algorithm are presented. The results show that the network traffic in cloud environments can be effectively predicted by using the introduced algorithm with an accuracy of 96.49%.
Embargo
Traffic Monitoring Related Experimental Study for a Software-Defined Network Based Virtualized Security Functions Platform
(IEEE, 2021-12-01) Gamage, T. C. T.; Rankothge, W. H.; Gamage, N. D. U.; Jayasinghe, D; Uwanpriya, S. D. L. S.; Amarasinghe, D. A.
Cloud computing and virtualization technologies are rapidly evolving with new capabilities being added all the time. Security Functions Virtualization (SFV) is the latest addition to cloud services, where Virtualized Security Functions (VSFs) are offered as services by Cloud Service Providers (CSPs). CSPs are focusing more on implementing effective resource management approaches for the cloud infrastructure, considering specific requirements of VSFs. Network traffic monitoring is one of the most crucial aspects of cloud resource management, as monitoring helps CSPs to have a global view of the resource utilization and take necessary proactive management actions, specifically for VSFs.This experimental study focuses on exploring network traffic and resource monitoring for the traffic traverse via a cloud platform where VSFs are offered as a service. We have considered two approaches: periodic monitoring and continuous monitoring. The network traffic is monitored continuously, and resource utilization is monitored periodically. With the implemented monitored framework, CSPs are able to take proactive decisions on resource management, specially towards scale-out/in decisions and security management.