Abstract: Early diagnosis of dental caries is essential for maintaining dental health. In this paper, method for diagnosis of dental caries is proposed using Laplacian filter, adaptive thresholding, texture analysis and Support Vector Machine (SVM) classifier. Analysis of the proposed method is compared with Otsu thresholding, watershed segmentation and active contouring method. Adaptive thresholding has comparatively better performance with 96.9% accuracy and 96.1% precision. The results are validated using statistical method, two-way ANOVA, at significant level of 5%, that shows the interaction of proposed method on performance parameter measures are significant. Hence the proposed technique could be used for detection of dental caries in automated computer assisted diagnosis system.
Abstract: In this paper we focus on event extraction from Tamil
news article. This system utilizes a scoring scheme for extracting and
grouping event-specific sentences. Using this scoring scheme eventspecific
clustering is performed for multiple documents. Events are
extracted from each document using a scoring scheme based on
feature score and condition score. Similarly event specific sentences
are clustered from multiple documents using this scoring scheme.
The proposed system builds the Event Template based on user
specified query. The templates are filled with event specific details
like person, location and timeline extracted from the formed clusters.
The proposed system applies these methodologies for Tamil news
articles that have been enconverted into UNL graphs using a Tamil to
UNL-enconverter. The main intention of this work is to generate an
event based template.
Abstract: Aim. We have introduced the notion of order to multinormed spaces and countable union spaces and their duals. The topology of bounded convergence is assigned to the dual spaces. The aim of this paper is to develop the theory of ordered topological linear
spaces La,b, L(w, z), the dual spaces of ordered multinormed spaces
La,b, ordered countable union spaces L(w, z), with the topology of bounded convergence assigned to the dual spaces. We apply Laplace transformation to the ordered linear space of Laplace transformable
generalized functions. We ultimately aim at finding solutions to nonhomogeneous
nth order linear differential equations with constant
coefficients in terms of generalized functions and comparing different
solutions evolved out of different initial conditions.
Method. The above aim is achieved by
• Defining the spaces La,b, L(w, z).
• Assigning an order relation on these spaces by identifying a
positive cone on them and studying the properties of the cone.
• Defining an order relation on the dual spaces La,b, L(w, z) of La,b, L(w, z) and assigning a topology to these dual spaces which makes the order dual and the topological dual the same. • Defining the adjoint of a continuous map on these spaces
and studying its behaviour when the topology of bounded
convergence is assigned to the dual spaces.
• Applying the two-sided Laplace Transformation on the ordered
linear space of generalized functions W and studying some
properties of the transformation which are used in solving
differential equations.
Result. The above techniques are applied to solve non-homogeneous
n-th order linear differential equations with constant coefficients in
terms of generalized functions and to compare different solutions of the differential equation.