Browsing by Author "Meedeniya, D"

Now showing 1 - 20 of 83

item: Conference-Abstract
An Adapter Architecture for heterogeneous data processing in bioinformatics pipelines
Lenadora, D; Wickramarachchi, A; Meedeniya, D; Mallawaarachchi, V; Perera, L
Bioinformatics is a growing field focused on both the domains of computer science and biology. A range of bioinformatics data processing tools exists at present, which takes inputs and produces outputs in varying formats depending on the algorithms and processes being used. The undesirable situation where such processes would produce outputs that may not allow the pipelining of other processes, calls for a generic bioinformatics data format converter. Though such converters currently exist, most of them are limited to text conversions and provide limited functionality. In addition, such functions have the potential capability of supporting parallelism to increase the overall throughput. A solution that can provide the said conversion functions as well as utility functions, while processing with a high throughput via parallelism is proposed through this paper. A utility function of this system requires storing bioinformatics data locally. In addition to facilitating this, an average compression rate of 26% achieved in data storage. Evaluation of the system using a set of 7,000,000 gene data showed the maximum time consumption for retrieval as 400ms.
item: Conference-Full-text
Adapting general purpose platform-as-a- service for customized product deployment
(Department of Computer Science and Engineering, University of Moratuwa., 2014-09) Senanayake, DA; Perera, I; Meedeniya, D; Perera, S
The web services industry has evolved to a point where a lot of services are provided for free or a free tier of services is offered, most of the times. An attempt of trying to exploit this situation is to try and implement a game server based on completely free and open-source technologies or at least not exceeding the free tiers of commercial technologies.
item: Conference-Full-text
Application based extension for windows network monitor widget
(Department of Computer Science and Engineering, University of Moratuwa., 2014-09) Kumarasinghe, CU; Perera, I; Meedeniya, D; Perera, S
This paper was written to give an idea about the windows network monitor extension which was developed in order to improve system security and application accountability of windows processes and to help the user to be aware of how much bandwidth is used by each process.
item: Conference-Full-text
Askfedora ux/ui and functionality overhaul
(Department of Computer Science and Engineering, University of Moratuwa., 2016-12) Welivita, KA; Perera, I; Meedeniya, D
AskFedora is a well known community knowledge base and a support forum, which provides community support for Fedora users. It is powered by Askbot, a Python and DJango based web application. With time, the user interface and user experience of AskFedora had come to a point of having a comprehensive overhaul. This is to have some uniformity with the other Fedora websites and have improved usability features. The AskFedora redesign project was aimed at achieving the goal of providing better user experience for the users. The project was conducted in three main phases, which were user experience analysis and mock-ups development, coding and integration with Askbot. The designs done are mainly based on user experience research and the styles used follow concepts of responsiveness and cross browser compatibility.
item: Article-Full-text
Automated license plate recognition for resource-constrained environments
(MDPI, 2022) Padmasiri, H; Shashirangana, J; Meedeniya, D; Rana, O; Perera, C
The incorporation of deep-learning techniques in embedded systems has enhanced the capabilities of edge computing to a great extent. However, most of these solutions rely on high-end hardware and often require a high processing capacity, which cannot be achieved with resource-constrained edge computing. This study presents a novel approach and a proof of concept for a hardware-efficient automated license plate recognition system for a constrained environment with limited resources. The proposed solution is purely implemented for low-resource edge devices and performed well for extreme illumination changes such as day and nighttime. The generalisability of the proposed models has been achieved using a novel set of neural networks for different hardware configurations based on the computational capabilities and low cost. The accuracy, energy efficiency, communication, and computational latency of the proposed models are validated using different license plate datasets in the daytime and nighttime and in real time. Meanwhile, the results obtained from the proposed study have shown competitive performance to the state-of-the-art server-grade hardware solutions as well.
item: Conference-Full-text
Automated programming assignment grading system
(Department of Computer Science and Engineering, University of Moratuwa., 2017-12) Subashith, SKTD; Perera, I; Meedeniya, D
Today there are many e-learning systems that fulfill the thirst for education. Those e-learning systems have many courses in different fields. There are so many e-classes that teach how to program in many different programming languages. But in most of those e-classes instructors have to spend a lot of time to evaluate assignments submitted by students. If the grading process can be done automatically, it will save lots of time of instructors. There are many systems that use the functionality of evaluating programs automatically. They provide support for hosting online programming competitions, but most of them do not provide platforms for e-classes. Therefore Automated Programming Assignment Grading System (APAGS) is the solution which supports both e-class environment and programming competition environment. The APAGS is a web system which has developed using Symfony framework according to the model, control and view architecture to provide both e-class environment and competition hosting environment. Its main goal is to evaluate the programs and analyse results for both assignments and competitions.
item: Conference-Full-text
Automated vehicle parking occupancy detection in real-time
(IEEE, 2020-07) Padmasiri, H; Madurawe, R; Abeysinghe, C; Meedeniya, D; Weeraddana, C; Edussooriya, CUS; Abeysooriya, RP
Parking occupancy detection systems help to identify the available parking spaces and direct vehicles efficiently to unoccupied lots by reducing time and energy. This paper presents an approach for the design and development of an end-to-end automated vehicle parking occupancy detection system. The novelty of this study lies in the methodology followed for the object detection process using RetinaNet one stage detector and region-based convolutional neural network deep learning technique. The proposed software architecture consists of low coupled components that support scalability and reliability. The developed web-based and mobile-based client applications assist to find parking spaces easily and efficiently. The existing solutions utilize dedicated sensors and depend on manual segmentation of surveillance footage to detect the state of parking spaces. The proposed approach eliminates existing limitations while maintaining reasonable accuracy.
item: Conference-Full-text
An automatic classifier for exam questions with wordnet and cosine similarity
(IEEE, 2016-04) Jayakodi, K; Bandara, M; Meedeniya, D; Jayasekara, AGBP; Bandara, HMND; Amarasinghe, YWR
The learning objectives, learning activities and assessment are very much interrelated. Assessment helps to evaluate students learning achievement. Poorly designed assessments usually fail to examine the achievement of intended learning outcome of a course. There are different taxonomies that have been developed to identify the level of the assessment being practiced such as Bloom’s and SOLO. In this research we have studied the use of WordNet with Cosine similarity algorithm for classifying a given exam question according to Bloom’s taxonomy learning levels. WordNet similarity algorithm depends on the extracted verbs from exam question. Cosine similarity algorithm was based on identification of question patterns of exam question. It consists of tag pattern generation module, grammar generation module, parser generation and cosine similarity checking module. This algorithm was helpful to classify the exam question where verbs were not present in exam questions. Exam questions taken from courses at the Department of Computing and Information Systems at Wayamba University were used as a basis for a performance comparison, with the autonomous system providing classifications that were consistent with those provided by domain experts on approximately 71% of occasions.
item: Conference-Full-text
Automator – location and battery level based profile changer, alarm and sms sender
(Department of Computer Science and Engineering, University of Moratuwa., 2014-09) Kumarasiri, MKDS; Perera, I; Meedeniya, D; Perera, I
This paper discusses the project Automator which is a location and battery level based automatic profile changer, location based alarm and SMS sender. This is a third party software developed for Android operating system. The application takes the location of the device from GPS and changes settings of the device as the user has defined earlier. The main advantage of this software comparing to other similar software in the Android market is the customization in selecting the settings the user wanted to change.
item: Conference-Full-text
Big data visualization
(Department of Computer Science and Engineering, University of Moratuwa., 2016-12) Abeysekara, M; Perera, I; Meedeniya, D
Computer based visualizations have been a popular approach that provides accurate and efficient visualization techniques to the users. There is an increasing growth in geographical data with the development of mobile devices. There is a trend to analyze the human behaviors and patterns with respect to the geographical locations in order to take decisions and predictions. This paper presents a Human Movement Visualizer tool to provide populating flow data between regions of a given map. The tool was designed to use with modern web browsers by implementing the complete functionality of the system using client-side JavaScript language. Also the tool can integrate with other visualization tools by introducing component based architecture to the system. Users of this tool can give a Shapefile as a base map and CSV (Comma Separated Values) based data to visualize the geographical data. The main goal of this tool is to provide visualizations for the transport planning in Sri Lanka.
item: Conference-Full-text
Blind quiz: android application for visually impaired people to access moodle quizzes
(Department of Computer Science and Engineering, University of Moratuwa., 2015-10) Subasinghe, SP; Pemasiri, A; Bandara, M; Meedeniya, D; Perera, I
Although the Moodle facilitates the Accessibility feature for visually impaired people it is not much user friendly for them. The requirement of third party software is the main limiting factor in the existing solution. But Android provides rich accessibility service for different able people. Therefore the application uses the Android platform to give access to Modular object oriented dynamic learning environment (Moodle). This application provides support to access quiz course material on Moodle. People who are visually impaired cannot access Moodle quizzes due to their disability as normal ones. Necessarily they need an external support from login to finish accessing Moodle. But they can access the mobile devices using Android Accessibility service. Thus the project is aimed to build Android Interface to Moodle quizzes for visually impaired people using Android Accessibility service.
item: Conference-Full-text
Blood bank management system
(Department of Computer Science and Engineering, University of Moratuwa., 2016-12) Thirunavukkarasu, N; Perera, I; Meedeniya, D
“BLOOD” is one of the most essential necessities of our lives. Mostly during accidents or most of the hospitals issues the need for blood is the common problem. In addition to emergency requirements, advances in medicine have increased the need for blood in many ongoing treatments and elective surgeries. This paper presents an android application blood bank management system that enables individuals who want to donate blood to help the needy. It also enables hospitals to send blood request to the donors who were already registered to the system. The system has developed by using java, PHP, and MySQL as a database system to manage and store the data. The Waterfall Methodology, which is the traditional version and the classic approach of a system development life cycle, is used to develop and build the android based blood bank system. The system targets three types of user: the public who wants to donate blood, the hospitals who need blood, and the admin who manage the system. In this application the system has utilized the Google distance API to find the distance between donors that are in favor of donating blood and hospitals. The android application is readily scalable, efficient and adaptable to meet the complex need of blood for the hospitals.
item: Conference-Full-text
Bloodforall – android application for blood donors
(Department of Computer Science and Engineering, University of Moratuwa., 2015-10) Uthayakumar, M; Pemasiri, A; Bandara, M; Meedeniya, D; Perera, I
Day to day there are many blood donations happening all over the world to save many lives. The main problem in blood donation is finding the blood donors within a short period of time during an emergency. Currently there is no proper solution exist for this problem. Although there are some blood donor applications in Android market already, none of them solves this problem completely. Many blood donors are not interested in using those applications due to the privacy issues. This application aims to provide a solution to all the problems in the existing blood donor applications. This paper discusses about the BloodForAll Application.
item: Conference-Full-text
Book portal operations management system
(Department of Computer Science and Engineering, University of Moratuwa., 2017-12) Dangalla, DADJS; Perera, I; Meedeniya, D
This paper discusses a system that provides an admin system and a public website for a book store with multiple branches. The admin system allows multiple user levels of the staff members to log in and perform separate duties within the system and the public website allows customers to view availability of items and purchase items online. The admin system generates monthly and annual reports, manages user notifications, incorporates role based access control, saves user logs and provides an invoice for physical bill issue in addition to controlling the items showcased in the website and managing the online purchase requests. The system is implemented using JSP and MySQL on MVC architecture and guest checkouts are integrated using PayPal.
item: Conference-Full-text
Ceylon bus routes: a bus route guide
(Department of Computer Science and Engineering, University of Moratuwa., 2016-12) Nimalsiri, NI; Perera, I; Meedeniya, D
Mobility is a basic human requirement for traversing between different locations. Public transport bus service fulfills this requirement by operating according to a published timetable along a route calling at agreed bus stops. Despite its progress at a rapid pace, moving commuters are riddled with problems of finding the correct bus route to reach their desired destinations. The use of mobile phone applications is an attractive alternative to guide passengers through correct bus routes. This paper discusses the project, “Ceylon Bus Routes” which is a Microsoft Windows universal application built as a solution for finding bus routes in Sri Lanka. This application is significant because it works offline and it can be run on any Windows based device. The goal of the application is to display the best routes as well as all the routes between two locations requested by the user. The application also uses GPS technology to track user location in case if the user does not know his or her actual location.
item: Article-Full-text
Chest X-ray analysis empowered with deep learning: A systematic review
(Elsevier, 2022) Meedeniya, D; Kumarasinghe, H; Kolonne, S; Fernando, C; Díez, IDLT; Marques, G
Chest radiographs are widely used in the medical domain and at present, chest X-radiation particularly plays an important role in the diagnosis of medical conditions such as pneumonia and COVID-19 disease. The recent developments of deep learning techniques led to a promising performance in medical image classification and prediction tasks. With the availability of chest X-ray datasets and emerging trends in data engineering techniques, there is a growth in recent related publications. Recently, there have been only a few survey papers that addressed chest X-ray classification using deep learning techniques. However, they lack the analysis of the trends of recent studies. This systematic review paper explores and provides a comprehensive analysis of the related studies that have used deep learning techniques to analyze chest X-ray images. We present the state-of-the-art deep learning based pneumonia and COVID-19 detection solutions, trends in recent studies, publicly available datasets, guidance to follow a deep learning process, challenges and potential future research directions in this domain. The discoveries and the conclusions of the reviewed work have been organized in a way that researchers and developers working in the same domain can use this work to support them in taking decisions on their research.
item: Conference-Full-text
A clinical decision support system for drug conflict identification
(IEEE, 2018-05) Nilan, Y; Sellahewa, D; Fernando, S; Gamage, L; Meedeniya, D; Chathuranga, D
Adverse drug reactions (ADRs) are common major issue in the health-care system that occur mainly due to the interactions among different medicines prescribed for different diseases. Other than the interactions among different medicines, life habits such as food consumption, alcohol consumption and smoking also affect the occurrence of ADRs. The main goal of this research is the identification of ADRs occur due to the interactions of medicines. The proposed solution identifies conflicts among different medicines and diseases based on rules defined using formal methods and provides alternative treatment paths. This study is supported by a mobile application that can be used by both medical practitioners and public users. The outcome of this research can be used by medical officers as a clinical decision support system to assist the prescription process.
item: Conference-Full-text
Computer vision library for western music sheet notations
(Department of Computer Science and Engineering, University of Moratuwa., 2015-10) Rasnayaka, S; Pemasiri, A; Bandara, M; Meedeniya, D; Perera, I
This paper discusses a computer vision system to detect western music notations from images. The developed library will take in images of western music sheet notation and identify the key features necessary to extract the notes. The images will go through several pre-processing stages and then using straight line detection techniques the staff and notes will be detected. The paper will discuss the algorithms used and developed to achieve this. Finally the paper will present the accuracy measures in the developed system for different types of images.
item: Conference-Full-text
Creating soft input methods for natively unsupported languages in android operating system
(Department of Computer Science and Engineering, University of Moratuwa., 2014-09) Perera, TA; Perera, I; Meedeniya, D; Perera, S
The need for native language support for any hand-held communication device is a must. But Android operating systems do not give much freedom when altering system fonts which require many advanced steps that needs to be carried out by a user. The proposed solution is for developers of applications who use native languages to create their own in-app input methods and rendering.
item: Conference-Full-text
Crowdsourcing based train tracking
(Department of Computer Science and Engineering, University of Moratuwa., 2015-10) Hewage, GHRG; Pemasiri, A; Bandara, M; Meedeniya, D; Perera, I
A considerable fraction from the general population use trains as their means of transportation in Sri Lanka [1]. Even though the railway system fulfils the transportation needs of a lot of people, being one of the cheapest means of travelling, it has its own disadvantages as well, such as the regular delays of trains. Most of the time, the passengers get to know about the delays of trains after they have reached the railway stations. An effort made to reduce the effect this particular issue is discussed through this paper. The proposed solution is a mobile application powered by crowdsourcing, which let the users of the application know where a particular train is at a particular moment. Thus by letting them know whether the train in which they are willing to travel is on schedule or not and arrange other means of transport as necessary.