Browsing by Author "Gamage, N. D. U"

Now showing 1 - 10 of 10

Embargo
A Deep Learning Model Optimized with Genetic Algorithms for Resource Allocation of Virtualized Network Functions
(IEEE, 2021-12-01) Rankothge, W. H; Gamage, N. D. U; Suhail, S. A. A; Ariyawansa, M. M. T. R.; Dewwiman, H. G. H; Senevirathne, M. D. B. P
Software Defined Networking (SDN) has gained a significant attention of Cloud Service providers (CSPs) for managing their network infrastructure. With the popularity of services such as virtualized applications and Virtualized Network Functions (VNFs), many organizations are outsourcing their entire data centers to the CSPs. From the perspective of CSPs, effective and efficient cloud resource management plays an important role, in terms of continuing a successful business model. This research focuses on proposing a resource allocation algorithm for a cloud platform where VNFs are offered as a service. It is a tier-based resource allocation approach, where different resource tiers are defined in terms of network bandwidth, processor speed, RAM, vCPUs and number of users. Once the client's request is submitted for VNFs, we have used a deep learning approach (a Keras model which was optimized using Genetic Algorithms) to forecast the most suitable resource tier. Our results show that the proposed resource allocation algorithms can forecasts the most suitable resource tier for given scenario, in the order of seconds, with high accuracy.
Embargo
Document Reader for Vision Impaired Elementary School Children to Identify Printed Images
(IEEE, 2019-12-05) Gamage, N. D. U; Jayadewa, K. W. C; Jayakody, A
Vision Impairment is a severe reduction of one or more functions of the eye. The print disability prevents a person from gaining information from printed material in the standard way and requires them to utilize alternative methods to access the information. World Health Organization estimated that nineteen (19) million children are visually impaired worldwide. As they are the future of the world it is necessary to eradicate barriers to the journey of gaining knowledge. Hence, this paper presents a mobile-based application targeting elementary school students to read textual documents, which contains a graphical image. The mobile application provides audio assistance to navigate through a mobile application, autofocused image capturing of printed papers, store captured images, classify selected text, images, and read-aloud generated digitized text. Therefore, “Schmoozer” would allow visually impaired individuals to read unbraided documents without others' interaction. Furthermore, this paper discusses the test results and evaluations to justify the feasibility of the proposed solution.
Embargo
Document Reader for Vision Impaired Elementary School Children to Identify Printed Images
(IEEE, 2019-12-05) Gamage, N. D. U; Jayadewa, K. W. C; Jayakody, J. A. D. C. A
Vision Impairment is a severe reduction of one or more functions of the eye. The print disability prevents a person from gaining information from printed material in the standard way and requires them to utilize alternative methods to access the information. World Health Organization estimated that nineteen (19) million children are visually impaired worldwide. As they are the future of the world it is necessary to eradicate barriers to the journey of gaining knowledge. Hence, this paper presents a mobile-based application targeting elementary school students to read textual documents, which contains a graphical image. The mobile application provides audio assistance to navigate through a mobile application, autofocused image capturing of printed papers, store captured images, classify selected text, images, and read-aloud generated digitized text. Therefore, “Schmoozer” would allow visually impaired individuals to read unbraided documents without others' interaction. Furthermore, this paper discusses the test results and evaluations to justify the feasibility of the proposed solution.
Embargo
E-tongue -A smart tool to predict safe consumption of groundwater
(IEEE, 2020) Alahakoon, A. M. P. B; Nibraz, M. M; Gunarathna, P. M. S. S. B; Thenuja, S; Kahandawaarchchi, K. A. D. C. P; Gamage, N. D. U
— In Sri Lanka, reportedly 59% of the population depends on water from natural sources. The government has taken necessary action to provide a quality water, there has always been a need to educate people about the importance of maintaining water quality, the importance of using betterquality water, and necessary precautions to be taken to avoid the Chronic Kidney Disease (CKD). Prior studies of the problems that has to induce to implement an E-Tongue: a smart device to predict safe consumption of groundwater, which is identify the quality of a groundwater in real-time by designing an Internet of Things (IoT) device to read the value of water quality parameters and GPS to fetch location which will be then transferred to cloud environment for an easy access by the machine learning model to process and identify the Water Quality Index (WQI). It will then predict the water quality parameter levels that could be changed in the future and check the possibility of CKD. All the outputs will be finally displayed via the mobile application with 73% accuracy.
Embargo
E-tongue-A smart tool to predict safe consumption of groundwater
(IEEE, 2020-11-04) Alahakoon, A. M. P. B; Nibraz, M. M; Gunarathna, P. M. S. S. B; Thenuja, S; Kahandawaarchchi, K. A. D. C. P; Gamage, N. D. U
In Sri Lanka, reportedly 59% of the population depends on water from natural sources. The government has taken necessary action to provide a quality water, there has always been a need to educate people about the importance of maintaining water quality, the importance of using better-quality water, and necessary precautions to be taken to avoid the Chronic Kidney Disease (CKD). Prior studies of the problems that has to induce to implement an E-Tongue: a smart device to predict safe consumption of groundwater, which is identify the quality of a groundwater in real-time by designing an Internet of Things (IoT) device to read the value of water quality parameters and GPS to fetch location which will be then transferred to cloud environment for an easy access by the machine learning model to process and identify the Water Quality Index (WQI). It will then predict the water quality parameter levels that could be changed in the future and check the possibility of CKD. All the outputs will be finally displayed via the mobile application with 73% accuracy.
Embargo
An Expermental Study on Load Balancing for a Software Defined Network based Virtualized Network Functions Platform
(IEEE, 2021-12-06) Senevirathne, M. D. B. P; Rankothge, W. H; Gamage, N. D. U; Ariyawansa, M. M. T. R; Dewwiman, H. G. H; Suhail, A
Network functionalities in conventional computer networks have been facilitated by implementing hardware middle-boxes. However, with the introduction of Virtualized Network Functions (VNFs) technologies, Cloud Service providers (CSPs) are able to offer VNFs as services to clients, along with general virtualized applications. CSPs provision and allocate resources to the VNFs, as required by the clients. An efficient cloud resource management approach plays an important role, in terms of continuing a successful CSP business model. To meet client Service Level Agreement (SLA) for Quality of Service (QoS), CSP is required to ensure that the virtualized entities are not overloaded with the processing, and workload is divided among virtualized entities adequately. Therefore, load balancing plays an important role, when offering VNFs as services to clients. This research focuses on exploring a load balancing algorithm for a cloud platform where VNFs are offered as a service. As the initial stage, we have used Weighted Round-Robin and Least Connection approaches and conducted an experimental study to compare the performances of the two approaches. Our results show that the weighted round robin algorithm performs better in terms of the workload distribution and average response time.
Open Access
IOT-based Monitoring System for Oyster Mushroom Farms in Sri Lanka
(KDU IRC, 2022-01-10) Surige, Y. D; Perera, W. S. M; Gunarathna, P. K. M; Ariyarathna, K. P. W; Gamage, N. D. U; Nawinna, D. P
Oyster Mushrooms are a type of a fungus which is very sensitive to the environmental factors and vulnerable to diseases and pest attacks which directly effects local trade and export strength. Mushroom is a climacteric type of food which continues its cycle even after harvesting. The mushroom farming process still uses manual mode such as the identification of diseases uses a farmers eye visually, harvesting of mushrooms are decided based on the visual appearance while the environmental factors are decided based on gut feelings. These methods has its limitations which requires more potential to improve both the quality and capacity of mushroom production. With the advancements of technology, this farming process can be performed with the aid of an IoT device and deep learning model. This research applies Convolutional Neural Networks (CNN) with Mobile Net V2 model to detect mushroom harvest time and any disease spread with an accuracy of 92% and 99% respectively. Long Short-Term memory (LSTM) to analyze the detected environmental factors with an accuracy of 89% and this system predicts the yield of mushroom production with the support of LSTM model with an accuracy of 97%. This developed system which aids mushroom farming activities is connected with the farmers through s mobile application
Embargo
NetEye: Network Monitoring for a Software Defined Network based Virtualized Network Functions Platform
(IEEE, 2021-12-01) Rankothge, W. H; Gamage, N. D. U; Ariyawansa, M. M. T. R; Suhail, S. A. A; Dewwiman, H. G. H.; Senevirathne, M. D. B. P
With the introduction of Virtualized Network Functions Virtualization (VNFs), Cloud Service Providers (CSPs) allocate resources and deploy network functions as virtualized entities in the cloud. With the dynamic changes in the traffic and workload, initially allocated resources have to be increased or decreased to maintain the Service Level Agreement (SLA). Therefore, CSPs rely on network monitoring approaches to maintain an effective and efficient resource management process. However, the monitoring process itself creates an overhead to the performance of the network. Monitoring algorithms consume the CPU and memory resources of the cloud infrastructure during their execution. Therefore, selecting an appropriate monitoring approach is important, especially in a resource-constrained network. In this research, we have explored two monitoring approaches: continuous and periodic, and compared their performances in terms of memory and CPU utilization.
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
Press plus-interactive mobile application for effective news reading
(IEEE, 2017-08-22) Gamage, N. D. U; Udeshitha, K. L. A. D; Jayadewa, K. W. C; Senanayake, S. M. N. K. B; Samarakoon, S. M. U. P; Hennayake, T. M
Presently younger generation relies more on mobile applications to acquire information instead of traditional methods. Hence, customary approaches of information distribution required to reinforce by modern technology. Especially newspaper industry needs a certain technology enhancement to make the reading experience more interesting and pleasurable for readers. The “Press Plus” is an application to form an association between the newspaper and modern technology to promote newspaper reading by allowing the user to watch news related videos via their smartphone. This application uses scanning and retrieving data through QR code technology with the collaboration of mobile & web application. The mobile application provides three main facilities; Video playback controller; which allows users to scan printed QR code and play news related videos, Top list; which permit users to rate and view top rated videos and live stream; which facilitate users to watch live events independent from location and time. Additionally to the application, a separate survey was conducted to evaluate newspapers reading habits of youth in Sri Lankan context. Survey results indicate that a large number of individuals prefer newspapers reading via modern technologies such as mobile applications. “Press Plus” is beneficial to both newspaper readers and publishers in many ways. It helps to enhance a number of newspaper readers by making it more attractive and pleasurable. In addition, readers get a novel experience while reading newspapers. Publishers indirectly can gain revenue through branding, marketing and event promotions via this application.