Research Papers - Dept of Software Engineering
Permanent URI for this collectionhttps://rda.sliit.lk/handle/123456789/1022
Browse
48 results
Filters
Advanced Search
Filter by
Settings
Search Results
Publication Embargo Rubber Buddy: A Mobile Application to Empower Rubber Planters of Sri Lanka(IEEE, 2022-12-09) Jayawardena, A; Ganegoda, K; Imbulana, S; Gunapala, G; Kodagoda, N; Jayasinghe, TThis research was conducted to develop a mobile application that provides expert solutions for the common problems faced by rubber planters in Sri Lanka. The application developed consists of four components, namely, identification of pests in immature rubber plantations and rubber nurseries; leaf disease identification; cover crop identification; and weed identification. Images taken using the mobile phone cameras are recognized using machine learning models developed using several convolutional neural network (CNN) architectures such as mobile net version 2 (MobileNet v2), VGG 16, VGG19, and residual networks (ResNet). After the images were recognized, the application will provide expert solutions and management strategies to the rubber planters. As most of the rubber plantations are located in areas with low network coverage, the application was designed to be operated in offline mode using TensorFlow lite technology.Publication Embargo Mobile Medical Assistant System for Laboratory Report Analysis and Medical Drug Identification(IEEE, 2022-12-09) Warnakulasuriya, D; Dewangi, T; Sewwandi, N; Rathnayake, M; Kodagoda, N; Suriyawansha, KIt is quite common for medical drugs and prescriptions to be misidentified by hospitals and after drugs are being dispensed to the patients. Misidentification of medical drugs is more common among elderly and visually impaired patients. In hospital organizations, the leading medical error is adverse drug events. Another most common issue patients face is keeping track of medical lab reports. Our proposed mobile medical assistant system uses image processing to identify drugs with or without packaging, identifying prescription and medical lab reports. Furthermore, the mobile application will identify the trends of medical lab reports and predict next month’s results of the medical lab report of the patient using machine learning.Publication 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, KThe 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.Publication Embargo Automatic Question Extractor and Answer Detector in a Recorded Webinar(IEEE, 2022-08-18) Dissanayake, C; Kodagoda, N; Suriyawansa, KOnline 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.Publication 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, KIn-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.Publication Open Access LEARNING STYLES BASED CHECKLIST FOR INSTRUCTIONAL MATERIAL FEATURES IN E-LEARNING(researchgate.net, 2020-03) Suriyawansa, K; Kodagoda, NE-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 learnersPublication 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, KTeaching 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.Publication Embargo Limitations of an object-oriented metric: Weighted complexity measure(IEEE, 2015-09-23) De Silva, D. I; Kodagoda, N; Kodituwakku, S. R; Pinidiyaarachchi, A. JMany computer science practitioners and software developers believes that the complexity of a program could be controlled more effectively by using object-oriented programming concepts. In addition to controlling complexity, the object-oriented approach allows faster development, reduction in costs, higher quality, easier maintenance, increased scalability, better information structures, and increased adaptability. As such, more and more programs are written using the object-oriented programming approach rather than using the traditional functional approach. This demand has spurred the provision for a number of object-oriented metrics. Out of them, Chidamber and Kemerers' metrics suite is one of the most prominent object-oriented metrics that has been proposed. It has been widely validated and has been accepted as a useful predictor of object-oriented design complexity. But it does not consider the complexities that occur due to factors such as the nesting level and type of control structures, and the size of the program. Thus, Chhillar and Bhasins' introduced the weighted complexity measure to address these issues. It is the only metric which considers the complexities that occur due to inheritance level of statements, nesting level and type of control structures, and the size of the program. However, weighted complexity measure also has some limitations. This paper attempts to draw the readers' attention to those limitations, with the hope that it will be further improved by addressing them.Publication Embargo A Fully Functional Shopping Mall Application--SHOPPING EYE(IEEE, 2014-11-18) Karunarathna, K. M. D. M; Weerasingha, H. M. D. A; Rumy, M. M; Rajapaksha, M. M; De Silva, D. I; Kodagoda, NIn the modern world, shopping has become an essential day to day activity for most of the people. However, their busy life style has lessened the time to do shopping. This has made them to look for quicker and easier ways to do their shopping. Some of the difficulties that people have to go through when they do shopping include having to travel a long distance without knowing the availability of the items, difficulty in finding relevant shops inside a shopping mall, forgetting to buy some items which they intended to buy. In order to overcome the above mentioned problems a fully functional shopping mall application is proposed in this paper. It contains details about all the shops inside a mall, available items, customer wish lists and a map. It consists of a mobile application developed using Android and a Server side module which act as a main database server for connecting with customers and shop owners. Both the modules communicate through web services. In this project wireless communication technique -- Bluetooth is used to identify the vertical and horizontal position of the customer. Augmented reality based technique is used to tag the shops with its promotions, loyalty points etc.Publication Open Access Enhancements to an OO Metric: CB Measure.(Journal of Software, 2018-01-01) De Silva, D. I; Kodituwakku, S. R; Pinidiyaarachchi, A. J; Kodagoda, NDue to the wide usage of the object-oriented paradigm as a development paradigm many researches have proposed metrics to measure the complexity of object-oriented programs. The proposed object-oriented metrics can be divided into two categories based on the main aspect they have considered: metrics based on object-oriented aspects and metrics based on the cognitive aspects. Majority of the metrics which belong to the latter category have relied on a maximum of three complexity factors to derive the complexity of a program. CB measure is one of the few metrics that has considered four or more complexity factors to measure the complexity associated with a software program. However, there exists some other factors that could be considered by the CB measure to make it a more practically applicable measure. Such factors were proposed by the authors in a previous study. This paper demonstrates how those factors can be incorporated to the CB measure. In addition, it validates the practical applicability of the modified CB measure.