Browsing by Author "Wijendra, D."

Now showing 1 - 2 of 2

Embargo
An AI based Chatbot to Self-Learn and Self-Assess Performance in Ordinary Level Chemistry
(2020 2nd International Conference on Advancements in Computing (ICAC), SLIIT, 2020-12-10) Mahroof, A.; Gamage, V.; Rajendran, K.; Rajkumar, S.; Rajapaksha, S.; 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
Symptomatic Analysis Prediction of Kidney Related Diseases using Machine Learning
(2021 3rd International Conference on Advancements in Computing (ICAC), SLIIT, 2021-12-09) Lansakara, D.; Gunasekera, T.; Niroshana, C.; Weerasinghe, I.; Bandara, P.; Wijendra, D.
Sri Lanka has been witnessing an increase in kidney disease issues for a while. Elderly kidney patients, kidney transplant patients who passed the risk level after the surgery are not treated in the emergency clinic. These patients are handed over to their families to take care of them. In any case, it is impossible to tackle a portion of the issues that emerge regarding the patient at home. It is hoped to enter patient’s data from home every day and to develop a system that can use that entered data to predict whether a patient is in an essential circumstance or not. Additionally, individuals in high-hazard regions cannot know whether they are in danger of creating kidney disappointments or not and individuals in danger of creating kidney sickness because of Diabetes Mellitus. Thus, we desire to emphasize the framework to improve answers for this issue. The research focuses on developing a system that includes early kidney disease prediction models involving machine learning classification algorithms by considering the relevant variables. In predictive analysis, six machine learning methods are used: Support Vector Machine (SVM with kernels), Random Forest (RF), Decision Tree, Logistic Regression, and Multilayer Perceptron. These classification algorithms' performance is evaluated using statistical measures such as sensitivity (recall), precision, accuracy, and F-score. In categorizing, accuracy determines which examples are accurate. The experimental results reveal that Support Vector Machine outperforms other classification algorithms in terms of accuracy.