dc.contributor.advisor |
Meedeniya D |
|
dc.contributor.advisor |
Perera GIUS |
|
dc.contributor.author |
Athukorala LADP |
|
dc.date.accessioned |
2019 |
|
dc.date.available |
2019 |
|
dc.date.issued |
2019 |
|
dc.identifier.citation |
Athukorala, L.A.D.P. (2019). Context-aware recommendation for data visualization [Master’s theses, University of Moratuwa]. Institutional Repository University of Moratuwa. http://dl.lib.mrt.ac.lk/handle/123/15781 |
|
dc.identifier.uri |
http://dl.lib.mrt.ac.lk/handle/123/15781 |
|
dc.description.abstract |
Today projects with data analysis play a significant role to give us suggestions to our daily problems. While understanding those analysis data user needs to get the meaning and the nature of the data. Data visualization is the best option to observe the data. The human eye can easily analyze those data with the help of visualization. Moreover when visualizing a dataset better to have an understanding of data types and user intention or preferences. Recommendation systems are the best approach to address the above problem. In this ,study we discuss recommendation application which gets the help of machine leaning and mapping algorithm. Context awareness is a help while giving recommendations to chart types. Even though from users perspective suggestions can be changed. Therefore the proposed solution improves with the help of user’s feedbacks. For each test-run system is collecting user feedbacks and use them to improve the training dataset. At the initial stage, there are only a few training data. Users can interact with the system and based on their feedbacks the outcome of the system will get more accurate. Based on user feedbacks recommendation will get more reliable in the long-run. In this study, we are looking at how much accuracy it has in the initial stage and how it varies with the number of test runs in the system. Therefore user interaction plays a significant role to help recommendations. Feedbacks from users help when improving the recommendations. The System recommendations are provided using a combined method of machine learning and rule based components and the evaluation has shown an accuracy over 80%. As this is a trending research area, contribution made through this study can be useful for the industry and the research community. |
en_US |
dc.language.iso |
en |
en_US |
dc.subject |
COMPUTER SCIENCE AND ENGINEERING-Dissertations |
en_US |
dc.subject |
HUMAN-CENTERED COMPUTING |
en_US |
dc.subject |
DATA VISUALIZATION |
en_US |
dc.subject |
INFORMATION SYSTEMS-Applications |
en_US |
dc.title |
Context-aware recommendation for data visualization |
en_US |
dc.type |
Thesis-Full-text |
en_US |
dc.identifier.faculty |
Engineering |
en_US |
dc.identifier.degree |
MSc in Computer Science and Engineering by research |
en_US |
dc.identifier.department |
Department of Computer Science & Engineering |
en_US |
dc.date.accept |
2019 |
|
dc.identifier.accno |
TH3961 |
en_US |