Browsing by Author "Pilapitiya, S.U."

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Collaborative Knowledge Centralization Approach via self Propagating Multi Agent Community Development
    (Uva Wellassa University of Srilanka, 2011) Koggalahew, D.N.; Amararachchi, J.L.; Pilapitiya, S.U.; Tharanga, K.G.D.
    Note: See the PDF Version Most researchers in Artificial Intelligence to date, have dealt with developing theories, techniques, and systems to study and understand the behavior and reasoning properties of a single cognitive entity. Al has matured, and its' endeavors were capable of addressing more complex, realistic, and large-scale problems. Such problems are beyond the capabilities of an individual agent. The capacity of an intelligent agent is limited by its knowledge and its computing resources Sycara, 1998). Multi agent systems can be defined as loosely coupled networks of independent entities called agents, which have individual capabilities, knowledge and resources, and which interact to share their knowledge and resources, and to solve problems beyond their individual capabilities (Wikipedia, 2010). The issue of knowledge sharing has been an important topic in multi-agent research. SESEME will address most of the above mentioned limitations in this domain and the final deliverable will be an agent society which is capable of self-learning and training new agents. Agents' communication is one of the defining characteristics of a multi agent system. In traditional linguistic analysis, the communication is taken to have a certain form (syntax), to carry a certain meaning (semantics), and to be influenced by various circumstances of the communication. SESEME can be differentiated from many other past efforts that have been carried on. SESEME addresses the problem of self-learning by agent itself (Capable of taking the knowledge as it is and no human enrolment).Efficient Methodology of Knowledge Representation using ontology and its own experience. Introducing a new methodology of knowledge distribution and train other agents. Instantiate new agents relevant to the domain. The system starts its learning process once it receives a text document (in .doc, pdf and .html formats) or even it receives an URL from the domain expert. First the system identifies the given content by using natural language processing and it ignores the ambiguity, complexity and the conflicts among the read content. The read content will be used to create or update its knowledge over the specified domain. The Centralized Self learning module (CESLM) is been facilitated with some additional features like adoption of existing ontology and domain experts feedbacks. Each sub agent consists of an ontology that represents its basic knowledge retrieved from CESLM and the system facilitates the updating of sub agent's knowledge
  • No Thumbnail Available
    Item
    Intelligent Ontology based Question Answering System for Medical Domain
    (Uva Wellassa University of Srilanka, 2011) Koggalahewa, D.N.; Amararachchi, J.L.; Tharanga, K.G.D.; Pilapitiya, S.U.
    Note: See the PDF Version Irrespective of the domain, the main aim of a Question Answering system is getting a question from the user, comprehending it, searching the answer in an efficient way and presenting the answers to the user. Many methods have been devised for this purpose. This basic idea is using ontology for representing the knowledge and developing the knowledge base. Although the ultimate aim of question answering is finding the exact answer to any question in any context. In today's world of automated content processing, this is inherently a hard task because without a restriction imposed either on the question type or on the user's vocabulary, the question answering process gets a big hit even at the question interpretation phase. The published medical literature and online medical resources are important sources to help physicians make decisions in patient treatment Cimino et al., 2003. Question answering is a rapid-developing technique that automatically analyses thousands of articles to generate a short text, ideally, in less than a few seconds, to answer questions posed by physicians. Such a technique provides a practical alternative that allows physicians to efficiently seek information at point of patient care. Physicians usually have limited time to browse the retrieved information. For example, studies found that physicians spend on average two minutes or less seeking an answer to a question, and that if a search takes longer, it is likely to be abandoned (Radomski, 1986). Although there are a number of annotated medical knowledge databases available for physicians to use, studies found that most of the resources are not frequently used by physicians in large hospitals due to busy work schedule in their lives (Sackett et al., 2000). Physicians often need to consult literature for the latest information in patient care (Siang et al,. 2001). Information retrieval systems (e.g., PubMed) are frequently used by physicians. Another evaluation study showed that it took an average of more than 30 minutes for a healthcare provider to search for answer from the PubMed, which means "information seeking is practical only 'after hours' and not in the clinical setting" (Wikipedia, 2010).
  • No Thumbnail Available
    Item
    Methodology of Knowledge Representation from Natural language
    (Uva Wellassa University of Sri Lanka, 2010) Koggalahewa, D.N.; Athauda, S.P.B.; Pilapitiya, S.U.; Tharanga, K.G.D.; Fonseka, O.A.R.K.
    Information available in different formats cannot be understood by a computer or a machine due to lack of a proper knowledge representation mechanism. It always requires more human effort in feeding the knowledge to the computers or the knowledge base. XML covers the basic level of knowledge representation, but is incapable of utilizing the concepts and semantics in a proper way. Onto_X is an effort made to automate the process of ontology construction from an annotated xml file or database. The annotation process is done by any natural language processing tool (apart from the system). The system requires an xml file as the input and converts it into ontology in owl format. The system is capable of generating the semantics over annotated content with owl components. Xml entities will be automatically mapped into the owl components such as classes, sub classes, instances and relationships. The conversion mechanism is totally automated inside the Onto_X since it assures all the co-relationships over the annotated content. The conversion process identifies the xml properties and assigns semantics with the integration of word-net 2.1 and owl properties over the parsed content. The system uses the protégé libraries for the conversion process. The most special feature in the conversion process is that it uses its own inference, without just mapping xml properties to owl. The system is capable of visualizing the mapped owl ontology and it allows the user to refine the content of the constructed ontology. The final outcome of the system is ontology in owl format, which is mapped from the xml file or a database. The research ensures a better knowledge representation mechanism and it will assure the creation of domain knowledge from the xml file. The expandability is high since it takes information from the base level. Key words: Information, Knowledge, Onto_X, Natural language