Browsing by Author "Rajapaksha, S, K"

Now showing 1 - 8 of 8

Embargo
An AI based Chatbot to Self-Learn and Self-Assess Performance in Ordinary Level Chemistry
(IEEE, 2020-12-10) Mahroof, A; Gamage, V; Rajendran, K; Rajkumar, S; Rajapaksha, S, K; Wijendra, D
Education is one of the fast-growing fields in the global perspective. Advancement of technology can be used in this sector to provide an effective and a valuable education system. In general, the students are more attracted to displays rather than the textbooks. In Sri Lanka, there is an inadequacy of resources and teachers cannot provide one on one attention to the students. Sri Lanka is not equipped with any platform to self-learn or self-evaluate their performance using an application either. Fortunately, “Edubot” acts as a solution for the stated research gap by providing a self-learning and self-evaluating AI based chatbot platform for Ordinary Level students in Chemistry domain. The self-learning component will provide the students a classroom environment by providing interactive tutorials. Explanatory responses would be given by Edubot by capturing doubts raised by the students and the self-evaluating component will provide an exam-based environment in which the Edubot auto generates the question and answers. The research finding shows that each component has an accuracy of more than 70 percent and helps to achieve the main goal of increasing the resources available to the ordinary level students in the Chemistry domain. This would then lead to an increase in the pass rate of the chemistry subject in the G.C.E Ordinary Level exam.
Embargo
Early Warning for Pre and Post Flood Risk Management by Using IoT and Machine Learning
(IEEE, 2021-12-09) Ilukkumbure, S. P. M. K. W; Samarasiri, V. Y; Mohamed, M. F; Selvaratnam, V; Rajapaksha, S, K
Flooding has been a very treacherous situation in Sri Lanka. Therefore, developing a structure to forecast risky weather conditions will be a great aid for citizens who are affected from flood disasters. In this study, the authors explore the use of Machine Learning (ML), Deep Learning (DL), Internet of Things (IoT), and crowdsourcing to provide insights into the development of the pre and post flood risk management system as a solution to manage and mitigate potential flood risks. Machine learning and deep learning algorithms are used to predict upcoming flooding situations and rainfall occurrences by using predicted weather information and historical data set of flood and rainfall. Crowdsourcing is used as a novel method for identifying flood threatening areas. Weather information is gathered from citizens and it will help to build a procedure to notify the public and authorities of imminent flood risks. The IoT device tracks the real-time meteorological conditions and monitors continuously. The overall outcome showcases that machine learning models, deep learning algorithms, IoT and crowdsourcing information are equally contributing to predict and forecast risky weather conditions. The integration of the above components with machine learning techniques, together with the availability of historical data set, can forecast flood occurrences and disastrous weather conditions with above 0.70 accuracy in specific areas of Sri Lanka.
Embargo
Geo-enabled FOSS tool supports for immediate flood disaster response planning
(IEEE, 2014-12-22) Ramanayake, K; Vithanage, D; Hettiarachchi, N; Rathnayake, G; Rajapaksha, S, K; Fernando, N
—Flood is a major natural hazard occur recurrently in Sri Lanka. Allocating victims to camps and provide medical facilities are two main activities at the immediate response phase of a flood and use of manual methods delayed this process. This project developed a geoenabled application to support immediate response planning, mainly focusing on allocation victims to IDP camps, provide medical facilities, and supporting access avoiding already blocked roads based on administrative divisions of the affected area. Capacities and facilities in camps and hospitals are matched against the needs of the victims. It identifies the blocked roads, alternative routes to reach resource centers, camps and hospitals and provide navigation guidance. The tool can be used after a flood disaster, assuming basic demographic data and the current flood affected area data are available. The tool is developed as a plug-in for QGIS, a free and open source desktop Geographic Information System software. The tool is verified with sample data related to “Kaluthara” area. It is intended to integrate with InaSAFE disaster response support tool at a later stage.
Embargo
iRetina: An Intelligent Mobile Application for the Visually Impaired in an Indoor Environment
(IEEE, 2021-12-09) Labeeshan, A; Satharasinghe, S. A. R. L. P; Dhananjana, A. M; Rupasinghe, T. D; Rajapaksha, S, K; Haddela, P. S
The Visually Impaired face a lot of problems while they carry out their day-to-day activities. Even though there are various ways that technologies have been used together to come up with a solution, there is still no proper, efficient, user-friendly, low-cost solution crafted just for them. Mobile Phones these days are beyond smartness, and they could be used to achieve so many things now compared to before. In this application, the camera of the mobile phone acts as the eyes for the Visually Impaired. The main purpose of this system is to intelligently navigate the visually impaired. This research covers some components namely, intelligent environmental identification by using the YOLOv4 object detection algorithm, calculation of distance by using the Inertial Measurement Unit (IMU) sensors, focusing, guiding and detecting the expiry date of packaged products, identifying and enhancing objects in a low-light environment. The communication between the system and the Visually Impaired will be a verbal voice communication through the microphones and the speakers of the mobile phone. The results presented show that the proposed application successfully achieves its goals by providing the required functionality.
Embargo
Methodology for coping with uncertain information contained in natural language instructions in a robotic system
(IEEE, 2020-12-10) Bandara, H. M. Y. L. W; Wijesekera, D. S; Bandara Herath, H. M. T. D; Kodagoda, D. L; Rajapaksha, S, K
Intelligent service robots are currently being developed to provide services and assistance in different sectors including domestic and household context. Typically, the service tasks of a domestic service robot involve direct interaction with humans. Humans typically express their ideas through voice communication. However, communication through natural language is imprecise because it tends to contain uncertain and unknown information. Therefore, understanding uncertain terms contained in natural language is a crucial capability that an intelligent service robot should possess. Hence, this project which is named as IntelBot is aimed at developing a methodology to cope with uncertain and unknown words contained in a natural language command given to a domestic service robot. In brief, the proposed system can interpret uncertain commands related to speed such as “go very fast” and the uncertain commands related to time such as “go later”. Additionally, if the robot is instructed to identify an object which is regarded to be unknown, as an example “cup” it can interpret and identify that particular object. And for the entire system, a user-friendly interface is developed for the easy control of the robot and the demonstration of the functionalities.
Embargo
Parade in the virtual dressing room
(IEEE, 2018-08-08) Priyadharsun, S; Lakshigan, S; Baheerathan, S. S; Rajasooriyar, S; Rajapaksha, S, K; Harshanath, S. M. B
Fashion has always been in the forefront especially with the youngsters. The interest in fashion can vary according to the country, region, culture, age, seasons, climates, places visited, attitude, personal interests etc. Some of them, however, have difficulties finding out about suitable dressing styles for them. Meeting this need is the purpose of this application. On the other hand, social networks are an easy way to interact with the teenagers. In this new age social network site, users create a profile and enter their body measurements to create a virtual model of the particular user. They can also upload their photos to create a complete virtual model which includes face as well. It was necessary to add business value to the application along with the usual entertainment factors. Adding business value to entertainment factors is the main attraction in Fashion Fit to suit a new age of social networking.
Embargo
Student and Lecturer Performance Enhancement System using Artificial Intelligence
(IEEE, 2020-12-03) Seneviratne, I. K; Perera, B. A. S. D; Fernando, R. S. D; Siriwardana, L. K. B; Rajapaksha, S, K
The proposed research work develops a system to enhance the performance of university students and lecturers by providing an excellent statistical insight. Already existing research works have attempted to solve independent classroom challenges that are related to measuring the student attention and marking student attendance but the existing research works have not combined theimportant aspects into one system. Hence, the proposed research wor has been carried out on various main aspects such as attendance register, monitoring student behavior as well as lecturer performance and lecture summarization. The system will incorporate tools and technologies in the different domains of artificial intelligence, machine learning, and natural language processing. After implementing and testing the proposed method it has been concluded that the student activity recognition process has been performed much better than the other emotion and gaze components by providing 94.5% results. The proposed system can determine the lecturer's physical activities and the quality of the lecture content with a reasonable accuracy. The summarized lecture has showed 70% similarity to actual lecture content and student attendance by using Face Recognition was marked with 83% accuracy. This research concludes that the automation of major classroom activities will impact the students and lecturers positively. Also, this system yields valuable results and increases the productivity of higher education institutions in the future.
Embargo
Virtual Furniture Shop
(IEEE, 2018-08-08) Galketiya, M. K; Fredrick, I. N; Katugampala, D. S. U; Adikari, A. A. J. C; Rajapaksha, S, K; Harshanth, S. M. B
This research illustrates an online, plug-in free, mobile supported and platform independent shop management system for a virtual furniture shop. The main aim of the research is to make the Web experience more appealing and affluent by using realistic 3D models. This purpose is achieved by the implementation of a 3D Content Management System (CMS). A virtual furniture shop will be used as an example to demonstrate the 3D content management system. It can also be applied to any other product.