Browsing by Author "Wijesundara, M"

Now showing 1 - 15 of 15

Embargo
The advanced remote PC management suite
(IEEE, 2011-08-16) Wijekoon, J; Wijesundara, M; Dassanayaka, T; Samarathunga, D; Dissanayaka, R; Perera, D
Developing a system that helps system administrators to perform their administration task more effectively and efficiently is of great importance to reduce downtime, cost and man power requirement. The Advanced Remote PC Management Suite facilitates centralized management of PC infrastructure employing the Intel Active Management Technology (AMT). This technology enables the system administrators to monitor and manage computers via a dedicated channel regardless of whether the computer is powered on. This is known as Out-of-Band (OOB) management. Currently AMT is available in Desktops and Laptops with The 2nd generation Intel Core vPro processors. Using features of AMT, the The Advanced Remote PC Management Suite provides a real-time and intelligent asset management facility in addition to monitoring and administration capabilities. The system also features automated operating system deployment and centralized disk cloning mechanisms. It is also possible to isolate any computer in the network using the system, during incidents such as virus infections. Therefore, this system is able to drastically reduce the number of desk-side-visits by system administrators to setup and troubleshoot PCs in large enterprise networks.
Embargo
APlus: An Intelligent Lecture Delivery System using Artificial Intelligence Learning Analytics
(IEEE, 2021-12-09) Kodagoda, C; Madampe, V; Ekanayake, R; De Silva, N; Wijesundara, M; Atapattu, P
As technology advances, new ways of teaching and learning can be discovered. Online learning platforms are able to provide easy, informative, and effective methods of delivering information since people are getting more accustomed to the use of e-learning. With the help of Artificial Intelligence, these methods can be refined to understand the users on a deeper level and provide services that are helpful and are more tailored to each user. The purpose of this project is to design an e-learning platform equipped for both educators and students. The system will be able to allow users to record/upload lecture sessions and other related study materials to the service which in return, with the use of Artificial Intelligence, try to understand the context of each lesson, segment videos, generate questions and deliver the materials to the Learner. The system will use various inputs from the Learner including video observation time, watched duration, types of videos watched, answers for questions, etc. to build a comprehensive profile of Learners. The system will use the knowledge gathered to provide services such as recommendations to the Learner, track the progress of the Learner as well as provide useful statistics of lecture materials to the Content Providers.
Open Access
An Automated Monitoring and Alert System for a Typical Server Room
(Academia.edu, 2014-06-13) Jayakody, J. A. D. C. A; Wijesundara, M
In this paper presents, the design and implementation of an Automated Monitoring and Alert System for Typical Server Room. This project is based on a microcontroller by Dallas Semiconductor known as TINI (Tiny Internet Interface) DS80C400. The system can send SMS messages, send out emails, etc to alert to appropriate personnel to maintain a high availability of services.
Open Access
Design of a Framework for Professional Development Programs for Teachers in the Use of Interactive Touch Screen
(researchgate.net, 2021-12) Perera, K. G. S. K; Wijesundara, M; Siriwardhena, I
Interactive Touch Screens (ITSs) are distributed in selected schools in Sri Lanka. Although, in these schools, selected teachers are trained on the use of the ITS, comprehensive training on the instructional strategies of ITS is yet to be provided. The objective of the study was to design and develop a framework for professional development programme (PDP) for teachers on the use of ITS. The sample of 31 teachers of an educational zone in the Colombo district was selected to test the methodology. Instruments for quantitative data collection were six scales and to collect qualitative data open-ended questions were used. Design Based Research (DBR) approach was made to evaluate the new methodology. DBR approach is characterized by analysis of the problem domain, design of the solution (intervention), iterative cycles of testing and refining the solution and finally reflecting on the whole process to arrive at design principles and inventing the solution. Intervention of this study was in terms of two professional development programmes on the integration of ITS in instruction. The results of the first intervention are presented in this paper. Analysis of data formed the feedback to design the revised PDP. The results of the study are the feedback to the proposed revisions to the next PDP. The feedback was to increase the time allocation of the PDP, provide more hands-on experience, demonstrate ITS-based instructional strategies related to different subject areas and conduct separate PDPs for non-ICT teachers.
Embargo
Design of a kinetic energy harvester for elephant mounted wireless sensor nodes of jumbonet
(IEEE, 2016-12-04) Wijesundara, M; Tapparello, C; Gamage, A; Gokulan, Y; Gittelson, L; Howard, T; Heinzelman, W
In areas where the habitats of elephants and humans are rapidly encroaching on each other, real-time monitoring of the elephants' locations has the potential to drastically improve the co-existence of elephants and humans, resulting in reduced deaths in both groups. However, as tagging (using GPS collars) elephants to obtain such location information is difficult and costly, it is important to ensure very long lifetimes of the tags, which can only be achieved using energy harvesting. In this paper, we present a kinetic energy harvester that uses magnetic levitation and ferro fluid bearings to generate energy from an elephant's movements. In order to determine the feasibility of using this kinetic energy harvester for powering the tags on elephants, we obtained real acceleration data collected from an Asian elephant over a 10 day period, and this data was then used to tune the system to maximize the harvested energy. Using experimentally validated analytical and simulation models, and the actual elephant acceleration data, we find that our prototype can generate 88.91J of energy per day. This energy is not only sufficient to power the tags to acquire and transmit locations 24 times a day to a distance of 114Km (line of sight), but provides a surplus of at least 35.40J, which can be used to increase the frequency of position updates or to support alternative communication options such as GPRS. Therefore, this shows the viability of long-term tracking of elephants.
Embargo
Design of a kinetic energy harvester for elephant mounted wireless sensor nodes of jumbonet
(IEEE, 2016-12-04) Wijesundara, M; Tapparello, C; Gamage, A; Gokulan, Y; Gittelson, L; Howard, T; Heinzelman, W
In areas where the habitats of elephants and humans are rapidly encroaching on each other, real-time monitoring of the elephants' locations has the potential to drastically improve the co-existence of elephants and humans, resulting in reduced deaths in both groups. However, as tagging (using GPS collars) elephants to obtain such location information is difficult and costly, it is important to ensure very long lifetimes of the tags, which can only be achieved using energy harvesting. In this paper, we present a kinetic energy harvester that uses magnetic levitation and ferro fluid bearings to generate energy from an elephant's movements. In order to determine the feasibility of using this kinetic energy harvester for powering the tags on elephants, we obtained real acceleration data collected from an Asian elephant over a 10 day period, and this data was then used to tune the system to maximize the harvested energy. Using experimentally validated analytical and simulation models, and the actual elephant acceleration data, we find that our prototype can generate 88.91J of energy per day. This energy is not only sufficient to power the tags to acquire and transmit locations 24 times a day to a distance of 114Km (line of sight), but provides a surplus of at least 35.40J, which can be used to increase the frequency of position updates or to support alternative communication options such as GPRS. Therefore, this shows the viability of long-term tracking of elephants.
Embargo
Design of a Low-Frequency Linear Motion Testbed for Electromagnetic Kinetic Energy Harvesters in JumboNet
(IEEE, 2017-09-14) Wijesundara, M; Gamage, A; Gokulan, Y; Tapparello, C
Kinetic energy harvesting on animals is an emerging technology that could facilitate real-time monitoring of wild elephants. Real-time monitoring is a proven solution to the Human-Elephant Conflict, a problem that has spread across Asia and Africa. However, when designing electromagnetic harvesters, it is essential to accurately model the voltage produced due to electromagnetic effects. In this paper, we present the design, development and the complete simulation of a simple and low-cost linear motion testbed that estimates the generation of an electromagnetic harvester. We integrated the dynamic non-linear flux linkage across the coil with an analytical model that accurately estimated the motion of the moving magnet. The experimental measurements from the testbed were better than 80% in agreement with the simulation results within the frequency range of 1Hz to 2Hz.
Embargo
Eduscope. Mobile-Mobile Application for Teaching and Learning
(IEEE, 2018-12-06) Fernando, K. H. M; Gunasekara, I. S; Krishani, J. V. G. A; Dilshani, A. G. C; Wijesundara, M
Smart Phones and Tablets are very common devices among people at Present. They have many additional features i.e. camera, internet, GPS etc than the basic phone has. Smart devices make easier the work of social, business and academic life of people. M-Learning is used to make easier works of academic life. M-Learning describes the Teaching and Learning using mobile devices. Eduscope.Mobile represents the M-Learning by providing virtual classroom. It will cover the whole classroom scenario. The lecturer can do their lectures from anywhere as well as students can learn the lectures from anywhere. Eduscope.Mobile is a cross-platform mobile application for M-Learning. It provides Live session facility for both Lecturers and students to connect from anywhere to the lecture at the same time. It creates a virtual classroom for lecturers and students. Lecturers and Students perform any activity in a normal classroom by using this mobile application.
Embargo
Energy Conservation in Animal Tracking
(IEEE, 2018-03-05) Ayatollahi, H; Tapparello, C; Wijesundara, M; Heinzelman, W
Wireless animal tracking represents the process of using battery operated wireless collars or tags to monitor and track animals in the wild. Given that it is particularly difficult to tag some species, communication protocols must be designed to be energy efficient, while still ensuring a high packet delivery ratio and low delay. In this paper, we present an energy efficient cross-layer protocol for an animal tracking application. The proposed protocol, MAC-LEAP, is a MIMO based energy adaptive protocol that reduces the energy consumption of the nodes by dynamically selecting their number of antennas for communication. We evaluate this protocol in an elephant tracking application in three different scenarios; when the nodes have limited energy, when the nodes have unlimited energy; and when the tags can be recharged via energy harvesting. Our results show that MAC-LEAP outperforms traditional protocols in terms of packet delivery ratio, and average packet delay and energy consumption.
Embargo
Gaja-Mithuru: Smart Elephant Monitoring and Tracking System
(IEEE, 2020-11-04) Fernando, P. P. S; Perera, K. Y. L; Dissanayake, P. N; Jayakody, J. A. D. M; Wijekoon, J; Wijesundara, M
In the past few years, a considerable number of villages bordering elephant populated areas of Sri Lanka have been continuously facing the dire effects of the Human-Elephant conflict. With the expanding human settlements in those natural habitats, the sources of food and water for elephants have gradually diminished over time. Therefore, animals are forced to attack crops. The consequent attacks on the villages cause a steady rise in human and elephant casualties. Within such a context, the existing methods of mitigating the human-elephant conflict have proven to be less effective as they often employ intrusive and harmful methods to ward off elephant threats. Thus, this proposal will focus on a monitoring method that is both nonintrusive and nonharmful to both humans and elephants using IoT technologies. To achieve the said objective, a method is proposed mean to detect elephants, monitor their behavior, and identify elephants' future attacks through seismic data related to elephants and GPS data and notify villages in advance. The data were captured using a hardware setup which includes geophones, circuits for amplification and filtering, and GSM modules for data communication. This method achieved a high accuracy in detecting elephant.
Embargo
A Geophone Based Surveillance System Using Neural Networks and IoT
(IEEE, 2020-12-10) Hettigoda, S; Jayaminda, C; Amarathunga, U; Thaha, S; Wijesundara, M; Wijekoon, J
Securing our assets and properties from intruders and thieves has become increasingly challenging as intruders become technology aware. The most common approach to monitor physical assets is CCTV. However, this approach has a number of technical limitations in addition to the cost. The CCTV camera location is visible to the intruder and intruder can also identify possible blind spots in the CCTV coverage area. In this paper, we introduce a novel method to secure physical assets using Geophones, Neural Networks, and IoT Platforms. This can either be used stand alone or to complement existing CCTV systems. In this approach, the system monitors vibrations on ground to detect intruders. We have achieved up to 93.90% overall accuracy for person identification. The system is invisible to intruders and covers a large area with a smaller number of nodes, thereby reducing the cost of ownership.
Embargo
A Geophone Based Surveillance System Using Neural Networks and IoT
(IEEE, 2020-12-10) Hettigoda, S; Jayaminda, C; Amarathunga, U; Thaha, S; Wijesundara, M; Wijekoon, J
Securing our assets and properties from intruders and thieves has become increasingly challenging as intruders become technology aware. The most common approach to monitor physical assets is CCTV. However, this approach has a number of technical limitations in addition to the cost. The CCTV camera location is visible to the intruder and intruder can also identify possible blind spots in the CCTV coverage area. In this paper, we introduce a novel method to secure physical assets using Geophones, Neural Networks, and IoT Platforms. This can either be used stand alone or to complement existing CCTV systems. In this approach, the system monitors vibrations on ground to detect intruders. We have achieved up to 93.90% overall accuracy for person identification. The system is invisible to intruders and covers a large area with a smaller number of nodes, thereby reducing the cost of ownership.
Embargo
Lighthouse-Smart Virtual Learning Platform
(IEEE, 2018-10-02) Abeyrathne, P. K. R. R. I; Sarathchandra, B. R. I. D; Hewavitharana, D. T. R; Perera, L. M. D; Wijesundara, M
This paper presents the design, development and performance evaluation of a new virtual learning platform. The novel features in this platform include real-time transcribing of live lectures conducted in English and the ability to search recorded lectures based on keywords mentioned during the lectures. This is in addition to real-time streaming and archiving of nine channels of information namely; audio, subtitles, video, slide synchronization, code editor, whiteboard, chat, polls and emotion. The system provides a number of novel features to ease the lecturer's workload. These include one touch recording, real-time polling, real-time emotion detection of students, and cloud based lecture editor allowing editing of each of the nine channels. From an operational perspective, the system requires no additional or special hardware other than a laptop, and it uses cloud based streaming and storage, eliminating the need for a dedicated infrastructure.
Open Access
Online education during Covid-19 lockdown-Student experience in the non-state higher education in Sri Lanka
(National Science Foundation, 2020) Wijesundara, M; Peiris, T. S, G; Thanaraj, T; Peiris, C. N
The objective of this paper is to analyze the effectiveness of online education in both teaching and learning, based on data captured from the Moodle LMS, Eduscope Lecture Video Management System and two students’ feedback surveys at the Sri Lanka Institute of Technology (SLIIT) from January to December 2020. Regression analysis and chi-square test were used as data analyses tools. The data were analyzed using simple linear regression and Analysis of LMS data showed that with each user logging into LMS 3 to 4 times a day with a minimum of 10 user actions per login. The study also found that the percentage of ‘satisfactory’ ratings by students for all aspects considered under four criteria, namely lecture delivery, technology, support services and overall satisfaction exceeded 80% irrespective of the faculty and time of the year. However the students’ responses for individual criteria within four aspects were significantly associated (p < 0.05) by the nature of the faculty. More than 75% of students claimed that the online delivery is working well and enabling them to continue with their studies. No significant difference was found with respect to overall satisfaction by the students between the two periods. The inferences of this study can be used effectively to provide better online education environment in higher education organizations in Sri Lanka. and The infrastructure upgrades, including overall bandwidth, new services including Zoom, Webex and MS Teams, staff training on online delivery enabled a quick transition to online delivery. The incorporation of Respondus lockdown browser and Respondus Monitor online proctoring system further enhanced the integrity of online assessments and examinations.
Embargo
A Real-Time Cardiac Arrhythmia Classifier
(IEEE, 2019-10-08) Abayaratne, H; Perera, S; De Silva, E; Atapattu, P; Wijesundara, M
Cardiovascular diseases (CVD) have increased drastically among Non-Communicable diseases, which have peaked over the past recent years. In 2018, around 17.9 million which is an estimated 31% of the people have died worldwide due to CVDs. A novel machine learning algorithm for continuous monitoring, identification and classification of cardiac arrhythmias from Electrocardiogram (ECG) data is presented here. The proposed solution has two stages where the first stage is a rule based cardiac abnormality identification which has an individual 97.55% ± 0.3% of accuracy (Acc) for a dataset of 705,000 and the second stage is a Neural Network (NN) based classification model which is trained and tested to identify 15 different classes recommended by ANSI/AAMI standard [1], and has 97.1% of individual accuracy for MIT-BIH Arrhythmia dataset [2] of 96265 beat samples. The combined real-time cardiac arrhythmia classifier is parallelized with CUDA in order to utilize the GPU and increase the execution speed by 4.86 times.