Faculty of Computing

Permanent URI for this communityhttps://rda.sliit.lk/handle/123456789/4202

Browse

Filters

2016 - 201912020 - 20221

Advanced Search

Filter by

Settings

Subject: search.filters.subject.Decision Tree

Search Results

Now showing 1 - 2 of 2
  • Thumbnail Image
    PublicationEmbargo
    A Mobile Gamified Application to Improve Mathematics Skills of Students from Age 9 to 11 Years
    (Institute of Electrical and Electronics Engineers, 2022-09-16) Karunasekara, K.K.R; Olinka, P.L.T; Kodithuwakku, K.T.D; Jayashan, B.V.P; Kahandawaarachchi, C; Attanayaka, B
    The revolutionary change in technology has directly involved with e-learning systems. Mathematics is recognized as essential yet difficult for most of students. The main problem is considered as existing solutions were not provided a better solution for knowledge level enhancement of mathematics by detecting the exact knowledge levels of students. Current applications have offered permission to select students' knowledge levels by themselves or initiated from the initial level which has led to wrong identification of mathematics knowledge. As a solution for these problems gamified mobile application is provided by introducing a knowledge level detection with a whole syllabus coverage question classification and answer classification by using a Logistic Regression extra trees classifier. The knowledge improvement is performed from the exact knowledge level detected and positive emotions of students. Convolutional neural network is utilized for emotional recognition. Further mental health is improved via a Chabot as an educational encouragement and gamified application is developed based on psychology and preference around ten years by adhering to the best practices of Human-Computer Interaction. The proposed solution is considered as a multi-valued and cost-effective solution which will improve the mathematics knowledge level and good mental wellbeing of students with an appealing gamification environment.
  • Thumbnail Image
    PublicationOpen Access
    A comparative study of data mining algorithms in the prediction of auto insurance claims
    (European International Journal of Science and Technology, 2016) Weerasinghe, K. P. M. L. P; Wijegunasekara, M. C
    Insurance claims are a significant and costly problem for insurance companies. The prediction of auto insurance claims has been a challenging research problem for many auto insurance companies. Identifying the risk factors which are affected for the high number of claims and denying them may lead to increased corporate profitability and keep insurance premiums at a below rate. The key objective of conducting this study is to examine the data mining techniques in developing a predictive model in support of auto insurance claim prediction and a comparative study of them. The research was carried out by using Artificial Neural Network (ANN), Decision Tree (DT) and Multinomial Logistic Regression (MLR) to develop the prediction model. The results indicated that the ANN is the best predictor with 61.71% overall classifier accuracy. Decision tree came out to be the second with 57.05% accuracy and the logistic regression model indicated 52.39% accuracy. Parameters of optimal NN model gives 6 input neurons and 7 minimum hidden neurons with 0.15 learning rate. The comparative study of multiple prediction models provided us with an insight into the relative prediction ability of different data mining methods. The comparison of the results of the decision tree and neural network models showed an interesting pattern. Policies that are misclassified by one model are correctly classified by the other. This might be an indication that the combination of the models could result in a better classification performance.