Search

Knowledge extraction is meant by acquiring relevant information from the unstructured document in natural language and representing them in a structured form. Enormous information in various domains, including agriculture, is available in the natural language from several resources. The knowledge needs to be represented in a structured format to understand and process by a machine for automating various applications. This paper reviews different computational approaches like rule-based and learning-based methods and explores the various techniques, features, tools, datasets, and evaluation metrics adopted for knowledge extraction from the most relevant literature. [ABSTRACT FROM AUTHOR]

A computational fatigue study of the propagation of delamination in a composite wing rib has been conducted. A typical Boeing 747 rib having a circular hole with a semi-elliptical delamination was taken as the rib of interest; gust loads experienced during the cruise phase of flight were identified as the source of fatigue. A square section surrounding the circular hole comprising of laminated carbon–epoxy prepreg was isolated from the rib for computational analysis. The lack of analytical solutions for such a problem encouraged the use of the general-purpose finite element software ABAQUS. The delamination mechanism was simulated using the energy-based virtual crack closure technique in tandem with the Paris–Erdogan equation. The delamination propagation with respect to aircraft flight hours was obtained for the aircraft rib, with Mode III tearing dominating the delamination process. A parametric analysis was further conducted for various ply orientations where delamination modes were compared via a frame-based analysis. Significant differences in delamination propagation were observed, and better performing orientations for the given conditions were identified. [ABSTRACT FROM AUTHOR]

The practice of using ontologies in medicine is mainly focussed on the representation and re-organization of medical terminologies. Physicians developed their own specialized languages and lexicons to help them store and communicate general medical knowledge and patient-related information efficiently. Such terminologies, optimized for human processing, are characterized by a substantial amount of implicit knowledge. Medical information systems, on the other hand, need to be able to communicate complex and detailed medical concepts unambiguously. This is noticeably a complex task and requires a intense analysis of the composition and concepts of medical terminologies. But it can be accomplished by fabricating medical domain ontologies for demonstrating medical terminology systems. Moreover, there are limited ontologies available in the domain of pulmonary diseases and as such tropical diseases like swine-flu(H1N1) are yet unexplored. Swine-flu is rapidly spreading disease and the information for it available from books, newspaper articles and internet which is unmanageable and unorganized. Therefore, in this paper, we propose to develop a medical ontology based information system for Swine-flu. We have implemented this system using Protégé 4.1 Beta Software and then hosted it onto Apache Tomcat Server. The deployed version can be viewed in XML and RDF formats and DL query can be used where user can get answers to their queries when questioned. Finally, to evaluate the performance functional testing with Fact++ Reasoner is used with ontology browser. [ABSTRACT FROM AUTHOR]