Browsing by Author "Suriyawansa, K"

Now showing 1 - 18 of 18

Embargo
Automatic Question Extractor and Answer Detector in a Recorded Webinar
(IEEE, 2022-08-18) Dissanayake, C; Kodagoda, N; Suriyawansa, K
Online learning becomes the primary method of education due to the novel coronavirus (COVID 19). This research paper describes the automatic extraction of domain-related questions in a lecture video, identifies the answers given by the lecturer for both voice-based questions and chat questions. The paper also presents a method to identify whether a lecturer gave a valid answer for the chat-based questions in the later section of the video. Additionally, this paper describes the approach to identify the most accurate solutions from the custom search engine-based responses.
Embargo
A Bilingual Audio Based Online Shopping Mobile Application for Visually Impaired and the Elderly People
(IEEE, 2021-12-07) Kangeswaran, V; Vasandarai, D; Eliyas, C; Munsil, M. M. M; Kodagoda, N; Suriyawansa, K
Despite the widespread success of online shopping, it is not available to all consumer types. In this sense, visually impaired and elderly users, in particular, frequently face daunting barriers. Due to the inaccessibility and difficulty of current online shopping mobile applications, millions of visually impaired and elderly people are unable to benefit from the convenience provided by online shopping. Developing ideas that inspire people is really essential for visually impaired and elderly people to engage in social life. Generic product explanations, unhelpful images, and visually appealing user experiences are provided to average eyes in online shopping, and they are incompatible with visually impaired people, even with visually impaired assistive devices. Due to visual barriers and inaccessible user experiences, the visually impaired are struggling to do online shopping independently. During this COVID-19 pandemic situation, online shopping is one of the better ways to meet everyone's needs and wants. Ordinary individuals can meet their needs and desires, but the visually impaired and elderly people who live alone find it difficult to manage their daily life. Therefore, we have come up with a solution for this by having an online shopping mobile application. Our objective with this application is to assist visually impaired and elderly individuals in meeting their underlying needs and to help them in this pandemic situation. This paper presents an online shopping mobile application for visually impaired and elderly people that allows them to shop online in a variety of convenient ways.
Embargo
Digital Platform to Empower the Self-Employment in Sri Lanka
(IEEE, 2021-12-01) Wickramasinghe, H. C. P; Thebuwana, T. D; Wijesinghe, G. K. H. S; Dissanayake, U. N; Kodagoda, N; Suriyawansa, K
Unemployment is a huge problem around the world because a lack of job opportunities. People are unable to find the job opportunities according to their preferences and qualifications. As a solution for this, many countries are attempting to empower self-employment. Most of current world problems have been solved using modern technologies. Therefore, the development of self-employment also can be achieved through modern technology. The objective of our proposed platform, HIRELANCER, is empowering self-employment using modern technologies. HIRELANCER is bringing the consumers, service providers, and suppliers into the same platform. HIRELANCER will consist of innovative features that go beyond comparatively to other platforms such as an advanced mechanism to find best suitable service providers/suppliers for the service, handling the virtual front-desk, cost estimation for the services prior to contacting a service provider, and advanced facility to find a suitable career path for the people who are seeking career guidance. This research paper discusses how the innovative features of HIRELANCER will be beneficial for consumers, service providers, and suppliers and ultimately achieve our main objective, which is empowering self-employment in Sri Lanka.
Embargo
EDUZONE – A Educational Video Summarizer and Digital Human Assistant for Effective Learning
(IEEE, 2022-12-26) Wangchen, T; Tharindi, P.N; De Silva, K. C. C. C; Sandeepa, W. D. T; Kodagoda, N; Suriyawansa, K
The availability of technology and the expansive nature of the internet have created a surge in the demand for online learning. Despite so many advantages, there are some existing drawbacks related to online learning. The lengthy recorded video lectures of different subjects and modules in a static manner, are extremely tedious for the learner to understand the contents available. And lack of assistance for academic-related problems of students is also stated as a major issue that comes with online education. EDUZONE provides a reliable solution to mitigate and overcome these challenges. This tool is educational assistance that generates a summarized version of the video lectures which depicts the overall idea of the whole video with the capability of a lecture notes generator along with a digital human which helps to clarify students’ problems and build an efficient conversational flow. The summarized video content can be used by the learners for revisions and as a quick reference before any examinations. In addition to generating short and precise content, EDUZONE also indexes any specific topics to make it easier to find content and generate class notes, highlighting all the important content. Overall EDUZONE can be considered a time-efficient educational assistant which helps students with their studies.
Embargo
Exploiting Multivariate LSTM Models with Multistep Price Forecasting for Agricultural Produce in Sri Lankan Context
(IEEE, 2020-12-10) Navaratnalingam, S; Kodagoda, N; Suriyawansa, K
In Sri Lanka agricultural produces possess a large supply which involves various stakeholders and thus, fluctuation of the agricultural produce prices has a direct impact on the purchasing decisions of the consumer. So, the main purpose of this study is to address the problem faced by the consumer due to poor awareness of price fluctuation which consequently astonish the consumers and hinder them from making better purchasing decisions. The research study is being specially developed in a way to adapt the Sri Lankan agricultural consumer market that is mainly based on Pettah and Dambulla trade centers. As the study we exploited different types of LSTM model with multivariate inputs along with the different combination of multistep models. The result of the study reveals that better performance was obtained for the multivariate CNN LSTM model with encoder decoder multistep model which provided an average RMSE of 19.46 Sri Lankan rupees per kilogram with an average RMSPE of 14.9%. Also, study reveals a correlation between price fluctuation and standard days of the week, where a better prediction was obtained for Monday and Tuesday with an average RMSE of 17.2 and 17.7 Sri Lankan rupees per kilogram respectively with an average RMSPE of 12.2%. Based on the input timestep considered for model, though 14 days and 21 days provided a similar result with minor variation result reveals that 14 days provided a lesser standard deviation of 0.17 than 21 days standard deviation which is 0.98.
Embargo
A Gamified Virtual Learning Environment to Enhance Online Teaching and Learning Experience
(IEEE, 2022-07-18) Tharaka, W.C.M. K; Dilanka, R. M. T; Perera, H.D.D. S; Rathnayake, R.H.C. S; Kodagoda, N; Suriyawansa, K
In-class teaching not only concentrates on lecture content delivery but also on maintaining strong mutuality between lecturer-students and student-student. Online lectures are gaining popularity due to the Covid-19 pandemic. However, the learning-teaching process has become ineffective because existing video conferencing solutions are not intended for academic purposes. This research was conducted to identify the pain points of online education and develop an enhanced software solution. A user survey confirmed that an isolated environment tends to diminish attentiveness during online lectures. Also, it is difficult for teachers to observe the attentiveness of all the students. As a solution, student attentiveness was measured using their facial expressions and collected data shown to lecturers through a virtual student behavioural environment. The physical separation causes students to feel isolated during lectures, which can negatively affect their academic development and social and psychological development. The developed application also provides a virtual group study environment as a feature. According to the results gathered in the user acceptance testing phase, it was found that the attention detection feature helps students keep their attention at a significant level. Further, 9 out of 10 teachers who participated in the testing acknowledged that the simulated student behavioural view could provide a more immersive experience. 71% of students preferred the new collaborative virtual environment, and students further elaborated that the virtual environment was more likely the physical group studies. 72% of students mentioned that the collaborative group study tool helped eliminate isolation during group studies.
Embargo
gCodex: A tool to analyze software repositories over time (visualization)
(IEEE, 2019-12-05) Nuzrath, S; Amarasinghe, N. H; Liyanage, K. T; Suriyawansa, K; Madanayake, D. P; Kodagoda, N
gCodex is a novel tool for analyzing and visualizing the code base in a manner that it allows its users to get an idea of the insights of the codebase. This tool was built to analyze code bases and it supports any language. In addition, it provides a visualization of the file structure, rate of change of complexity and defects rate. In order to improve the quality of the software and the controllability of the project, it is necessary to control the complexity of the software by measuring the associated aspects and visualize those in a descriptive and attractive dashboard. Using the existing tools, it is not possible to visualize the rate of change of code complexity with the time. This tool uses Cyclomatic complexity, line of code and Halstead complexity metric and their impact on the software quality, and visualize those in a descriptive dashboard which provides analytics that describes and summarize past trends.
Embargo
Innovative use of Collaborative Teaching in Conducting a Large Scale Online Synchronous Fresher’s Programming Course
(IEEE, 2021-04-21) Kodagoda, N; Gamage, A; Suriyawansa, K; Jayasinghe, B; Rupasinghe, S; Ganegoda, D; Jayalath, T; Kurrupu, A
The COVID-19 pandemic has forced educationist to come up with innovative solutions in delivering, engaging synchronous online academic modules. An innovative collaborative teaching approach was utilized in delivering programming concepts for freshers. A team of six academics functioned as a resource panel in delivering synchronous online lecture content. These interactive sessions were led by a moderator inquiring the resource panel on topics related to the content of the lecture. This was done in the same spirit on how a panel discussion would be conducted led by a moderator in a conference. Microsoft Teams Live was used in the delivery of the content to an audience of up to 800 students. Delivering a freshers programming course is known to be challenging in face- to-face delivery. A collaborative programming environment was used to engage students in live coding activities during the lectures. Students had opportunities to interact with the resource panel through quizzes, QA and through coding related activities. These lectures also introduced the innovative use of QR codes to get students engagement through a mobile device for the interactive sessions. Results based on a survey shared among the participated students, confirmed the collaborative teaching approach in conducting webinar was more effective over a traditional webinar that is conducted by one person. Interactive programming environment (Repl.it) allowed the resource personal to give feedback on the programs submitted by the students during synchronous sessions conducted. The best practices used in delivering this course can be easily adopted in delivering highly engaging online lectures for other courses.
Open Access
LEARNING STYLES BASED CHECKLIST FOR INSTRUCTIONAL MATERIAL FEATURES IN E-LEARNING
(researchgate.net, 2020-03) Suriyawansa, K; Kodagoda, N
E-learning is a rapidly growing industry with a large number of users around the globe. The learning process of e-learning mainly depends on different learning techniques of instructional materials provided in the learning environment. Learning materials are the key component of comprehending information in an e-learning environment. Thus, it is vital to develop e-learning learning materials that are beneficial for the target learners. Different learners have different preferences in learning. Several learning style models have proposed over the years to define the different characteristics of different types of learners. This paper describes seven such learning style models and define learner characteristics focused on each of these models. Then the defined characteristics of each learner style in all seven learning style models are tabularized to emphasize the overlaps of learner characteristics focused in different learning style models. As the next step, a list of unique learner characteristics with reference to learning styles was defined using the information in the table with all learner characteristics. This paper also defines features available in e-learning materials. At present, MOOCs (Massive Open Online Course) can be defined as the key pillar of e-learning. Thus, several MOOCs provided by Coursera platform were analyzed to derive features of e-learning materials or elearning environments. The identified unique learner characteristics of learning styles are then mapped with the list of features in learning materials in an e-learning environment. The final result of this research is a checklist which can be used by e-learning content developers to classify how the instructional materials are effective for the target learners. This checklist defines the satisfied learning styles of all seven learning style models by each identified feature of e-learning instructional materials. It can be used as a guideline for e-learning content developers to determine the features that has to be included in the learning materials to provide an effective learning environment for the target learners
Embargo
MOOCRec 2 for Humanities-Learning Style Based MOOC Recommender and Search Engine
(IEEE, 2019-12-05) Fazuludeen, F; Vijayakumaran, G; Mahroof, Z. A; Kodagoda, N; Suriyawansa, K
Introduction of Massive Open Online Courses (MOOC) has a great impact on the e-learning sector. Further, MOOC platforms like Coursera, EdX, and Future Learn have made learning accessible to millions of people for free. Also, availability of such platforms has become a blessing and a burden to people since users cannot find the right courses that suits them due to the availability of similar topic of courses in different platforms. Moreover, MOOCRec Humanities is a curated search platform for these courses. Further, MOOCRec tries to address this problem by considering the learning style of user and matching them with the right courses. Additionally, the courses are mapped using VARK learning model. For the mapping purpose, course video styles and course practical content such as quizzes and reading materials are considered. In addition, users can search individual topics that can be covered in a course.
Embargo
MoocRec: Learning styles-oriented MOOC recommender and search engine
(IEEE, 2019-04-08) Aryal, S; Porawagama, A. S; Hasith, M. G. S; Thoradeniya, S. C; Kodagoda, N; Suriyawansa, K
Massive Open Online Courses (MOOCs) are the new revolution in the field of e-learning, providing a large number of courses in different domains to a wide range of learners. Due to the availability of several MOOC providers (including edX, Coursera, Udacity, FutureLearn), a specific domain has multiple courses spread across these platforms that confuses a learner on selecting the most suitable course for him. It is a tedious manual task for the learner to browse through various courses before he finds the best course that meets his learning requirements and objectives. MoocRec is a unique learning styles-oriented system that recommends the most suitable courses to a learner from different MOOC platforms based on their learning styles and individual needs. The courses are recommended based on the mapping of Felder and Silverman learning styles with the standard video styles used in MOOC videos (including talking head, slide, tutorial/demonstration). MoocRec also allows the learners to search for courses using specific topics to provide an enhanced personalized learning environment. Results show that MoocRec is strongly reliable and can be used for personalized learning.
Embargo
MOOCs Recommender based on User Preference and Video Quality
(IEEE, 2020-12-10) Sankalpa, R; Sankalpani, T; Sandeepani, T; Ransika, N; Kodagoda, N; Suriyawansa, K
MOOCs (Massive Open Online Courses) are a new revolution in the field of e-learning. MOOCs are capable of providing several thousands of learners with access to courses over the internet. MOOCs are produced in many different video production styles and these styles play an important role in helping the consumer stay engaged and interested in the courses. MOOCs provide a large number of courses in different domains to a wide range of learners. It has become difficult and a time-consuming task for a user to find the most suitable courses that suit a learner's personal preferences. This paper describes how to recommend a course based on the preferred video style of the learner and the basic learning style of the learner which determines the learner's preferences on other materials in a course. In the course recommendation process, this paper also describes how to classify the course in order to recommend the most appropriate massive open online courses for users according to their most preferred video production style.
Embargo
MOOCs Recommender Based on User Preference, Learning Styles and Forum Activity
(IEEE, 2019-12-05) Hilmy, S; De Silva, T; Pathirana, S; Kodagoda, N; Suriyawansa, K
With the development of MOOCs (Massive Open Online Courses) as a major source of e-learning materials, the number of MOOCs available today has become dauntingly high. Furthermore, MOOCs are produced in many different video production styles and these styles play an important role in helping the consumer stay engaged and interested in the course throughout. However, due to the sheer number of MOOCs available today, it is becoming increasing difficult to find the MOOCs that suits your personal preferences and the learning style. This paper describes how thousands of MOOCs that belong to different styles are identified efficiently while each consumer's preferences are identified to provide personalized MOOC recommendations. Furthermore, the paper describes how forums can be analyzed to identify how consumers feel about MOOCs that they followed, which is a crucial metric in recommending MOOCs to consumers.
Embargo
Online learning resources finder based on computer programming domain
(IEEE, 2018-12-21) Somadasa, K; Karunadhipathi, M; Wickramasinghe, N; Subasingha, S; Kodagoda, N; Suriyawansa, K
With the huge growth of the internet, the amount of content on the internet also grown. Within that context, there are many irrelevant contents spread within the internet for a given topic. Therefore, it is very hard to find accurate, informative learning resources. Even though there are some search engines available, the job they do is very generic and provide millions of search results. Finding the most important learning content within a large set of search results is an extremely difficult task. The solution proposed in this paper addresses this issue. The learner can search for what is required and the system would filter both text and video content across the internet to provide the most relevant content. This paper describes how a textual resource finder was implemented based on ontologies, Euclidean distance, and the TF-IDF algorithm. The video content analyzer used a deep learning algorithm. The solution was developed for learners in the Computer Programming domain.
Embargo
Using active learning integrated with pedagogical aspects to enhance student’s learning experience in programming and related concepts
(Springer, Cham, 2019-09-25) Imbulpitiya, A; Kodagoda, N; Gamage, A; Suriyawansa, K
Teaching programming concepts and skills to beginners is a challenging and daunting task. As undergraduates, students struggle with understanding the fundamental concepts of programming and learning the syntaxes to build up a solution to an existing problem. The main challenges in delivering an introductory programming module are to get the students actively engaged within and outside the classroom and to increase the level of interest towards programming. Many researchers have tried out using different active learning tools and techniques to engage students in the learning process interactively. Even though lot of different techniques and tools have been introduced with time there is still a reluctancy among the learners and academics to move from the traditional teacher centric learning environment to a more interactive student centric environment. This research is focusing on how active learning integrated with pedagogical aspects can be used in an introductory programming module and the effectiveness of it when compared with a traditional approach.
Embargo
Using Pre-trained Models As Feature Extractor To Classify Video Styles Used In MOOC Videos
(IEEE, 2018-12-21) Aryal, S; Porawagama, A. S; Hasith, M. G. S; Thoradeniya, S. C; Kodagoda, N; Suriyawansa, K
Massive Open Online Courses (MOOCs) have emerged as new learning phenomenon in the field of e-learning. Over recent years, it has attracted a significant number of learners as well as researchers. A wide range of researches is being carried out across multiple aspects of MOOCs. Video lectures are the most fundamental component in a MOOC. There are standard video styles that are normally used across several MOOC platforms, such as, talking head, demonstration, slides, animation etc. This paper presents an Image-Based classification approach of the video styles where a single video is split into multiple image frames, and then each frame is classified into one of the video style-category. Different classifier models built on top of each state-of-the-art deep neural architectures, including VGG16, InceptionV3, and ResNet50 are evaluated and the comparison of results is shown. Furthermore, the paper also discusses a numeric method to calculate the composition level of a single video style in multi-style filed videos based on the classification results.
Embargo
VTutor: A Platform for Improving Searchability and Interactivity of Recorded Lectures
(IEEE, 2019-12-05) Karunaratna, D; Hettiarachchi, I; Fernando, S; Epa, S; Kodagoda, N; Suriyawansa, K
Recorded lectures have gained popularity as a method of delivering lecture content as they give learners a host of distinct advantages such as the ability to follow lectures without time or location constraints and to consume the lectures at their own pace. However, despite such benefits, they have a tendency to be lengthy and tedious to watch. They also prove cumbersome when precise information needs to be extracted from the content. Another drawback is that recorded lecture videos fail to show the connection between the lecture and its support material such as slides and questionnaires. Though many of the existing platforms allow editing lecture videos for more interactivity, the methods employed by these platforms have always been manual, and therefore time intensive. VTutor is a web platform that aims to address these drawbacks by introducing automation into the video enhancement process, eventually combining the lecture material to create an enhanced user experience. Specifically, VTutor allows users to navigate through a lecture video using subtopics, its corresponding slides and code samples. Furthermore, it is equipped with the ability to automatically generate questions by scraping the internet based on provided keywords thus improving the level of engagement that a learner has with the lecture.
Embargo
Zilla: An Animal Based Social Media Platform
(IEEE, 2019-12-05) Kasun, R; Mahesh, L. G. H; Yapa, Y; Suwendra, S. M. S. D; Kodagoda, N; Suriyawansa, K
Pets have been part of human societies from ancient times. The purpose of having a pet might have been changed, the breeds of pets have been evolutionarily changed making them tamed and friendly to have in the modern urbanized society. Pet owners consider their pets as one of their family members and love them immensely. Moreover, pet owners face difficulties when their pet gets sick and there is no emergency veterinary support, or even the owner might be unsure about conditions that affect the pet's life. In this research a social media platform called Zilla devoted to pets is presented. This Pets based social media platform provides pet owners a unique platform to interact with other pet owners.