Browsing by Author "Kohomban, U"

Filter results by typing the first few letters
Now showing 1 - 5 of 5
  • Thumbnail Image
    item: Conference-Full-text
    Decisionai: a framework to automate the decision making process
    (Computer Science & Engineering Society c/o Department of Computer Science and Engineering, University of Moratuwa., 2011) Buddhika, KT; Jayamanne, DP; Kohomban, U; Wimalasena, L; WIjegunawardana, PP; Gunasekera, RC; Perera, AS; Weerawardhana, S; Madusanka, A; Dilrukshi, T; Aravinda, H
    accurate decision making is the key to make a business profitable. Decision support systems are used to make the decision making process accurate and easy. Even though there are many business specific decision support systems they cannot be used for general purpose decision making or outside their domain. DecisionAI provides a framework which can be used in any decision making domain with similar decision types. DecisionAI provides a good solution to many decision making problems in the industry allowing detailed analysis of data with the integrated intelligence.
  • Thumbnail Image
    item: Conference-Full-text
    Machine learning approach to recognize subject based sentiment values of reviews
    (IEEE, 2016-04) De Mel, NM; Hettiarachchi, HH; Madusanka, WPD; Malaka, GL; Perera, AS; Kohomban, U; Jayasekara, AGBP; Bandara, HMND; Amarasinghe, YWR
    Due to the increase in the number of people participating online on reviewing travel related entities such as hotels, cities and attractions, there is a rich corpus of textual information available online. However, to make a decision on a certain entity, one has to read many such reviews manually, which is inconvenient. To make sense of the reviews, the essential first step is to understand the semantics that lie therein. This paper discusses a system that uses machine learning based classifiers to label the entities found in text into semantic concepts defined in an ontology. A subject classifier with a precision of 0.785 and a sentiment classifier with a correlation coefficient of 0.9423 was developed providing sufficient accuracy for subject categorization and sentiment evaluation in the proposed system.
  • Thumbnail Image
    item: Conference-Abstract
    Question answering system for the travel domain
    (2017) Kahaduwa, H; Pathirana, D; Liyana Arachchi, P; Dias, V; Ranathunga, S; Kohomban, U
    A Question Answering (QA) system backed by a comprehensive and up-to-date knowledge base would be appropriate for travellers to satisfy their information needs. In this paper, a complete QA system is presented. It has two main phases: question identification (Expected Answer Type (EAT) identification) and searching the knowledge base (KB) to find the answer to the classified question. In QA systems, identification of the EAT of a question imposes some constraints when determining the possible answer. This paper presents the first study on semantic classification of questions into EATs in the travel domain. A new two-level taxonomy for the travel domain is introduced, along with a dataset annotated with the same. A machine learning approach is used for question identification, which gives very promising results even with the use of syntactic and semantic features. A rule-based approach is used for searching the KB to find the answer. An ontology serves as the KB of the QA system which is traversed using a Simple Protocol and RDF Query Language (SPARQL) query generated through the rule-based approach.
  • Thumbnail Image
    item: Conference-Full-text
    Representation of web based graphics and equations for the visually impaired
    (2013) Gunawardhana, CLR; Hasanthika, HHM; Piyasena, TDG; Pathirana, SPDP; Fernando, MSD; Perera, AS; Kohomban, U
    With the extensive growth of technology, it is becoming prominent in making learning more interactive and effective. Due to the use of Internet based resources in the learning process, the visually impaired community faces difficulties. In this research we are focusing on developing an e-Learning solution that can be accessible by both normal and visually impaired users. Accessibility to tactile graphics is an important requirement for visually impaired people. Recurrent expenditure of the printers which support graphic printing such as thermal embossers is beyond the budget for most developing countries which cannot afford such a cost for printing images. Currently most of the books printed using normal text Braille printers ignore images in documents and convert only the textual part. Printing images and equations using normal text Braille printers is a main research area in the project. Mathematical content in a forum and simple images such as maps in a course page need to be made affordable using the normal text Braille printer, as these functionalities are not available in current Braille converters. The authors came up with an effective solution for the above problems and the solution is presented in this paper.
  • Thumbnail Image
    item: Conference-Full-text
    Representation of web based graphies and equations for the visually impaired
    (The Engineering Research Unit, University of Moratuwa, 2013-02) Gunawardhana, CLR; Hasanthika, HMM; Piyasena, TGD; Pathirana, SPDP; Fernando, S; Perera, AS; Kohomban, U; Rodrigo, R
    With the extensive growth of technology’, it is becoming prominent in making learning more interactive and effective Due to the use of Internet based resources in the learning process, the visually impaired communin’faces difficulties In this research we are focusing on developing an e-Learning solution that can be accessible by both normal and visually impaired users. Accessibility to tactile graphics is an important requirement for visually impaired people. Recurrent expenditure of the printers which support graphic printing such as thermal embossers is beyond the budget for most developing countries which cannot afford such a cost for printing images. Currently most of the books printed using normal text Braille printers ignore images in documents and convert only the textual part. Printing images and equations using normal text Braille printers is a main research area in the project. Mathematical content in a forum and simple images such as maps in a course page need to be made affordable using the normal text Braille printer, as these functionalities are not available in current Braille converters. The authors came up with an effective solution for the above problems and the solution is presented in this paper.