Time filter

Source Type

United States

Elin Manju Preethi F.,SASTRA
International Journal of Applied Engineering Research

Imperialist Competitive Algorithm is a heuristic optimization method developed by Atashpaz Gargari and Caro Lucas in 2007. It’s a socio- political evolution based algorithm.Various efforts were made to solve constrained problems and discrete optimization. Here we have discussed the various advantage and limitations of ICA. © Research India Publications. Source

Aarthi J.,SASTRA | Niruban Projoth T.,Vel Technology University
International Journal of Applied Engineering Research

In this paper reviewed, the weight optimization of truss structure under displacement and stress constraints using Particle Swarm Optimization (PSO). It is a heuristic global optimization method which is inspired by social habits of fish schooling and bird flocks. PSO combines self-experience of individual and social experience of global population. In this technique the cross sectional area used as a design variable and which is continuously valued after few iteration to get optimal position. © Research India Publications. Source

Shanmuga Prathipa J.,SASTRA
International Journal of Soft Computing

High dimensional data is extra complicated in image based retrieval so the content-based visual information retrieval is used to solve the image retrieval in large database. In proceeding the image is given in the search content it does not retrieves the related images the new format shape similarity measurement and PSNR value is used to access the prominent content in large dataset effectively. © Medwell Journals, 2012. Source

Narasimhan K.,SASTRA | Vijayarekha K.,SASTRA
Journal of Theoretical and Applied Information Technology

This paper proposes a new method for the detection of glaucoma using fundus image which mainly affects the optic disc by increasing the cup size is proposed. The ratio of the optic cup to disc (CDR) in retinal fundus images is one of the primary physiological parameter for the diagnosis of glaucoma. The Kmeans clustering technique is recursively applied to extract the optic disc and optic cup region and an elliptical fitting technique is applied to find the CDR values. The blood vessels in the optic disc region are detected by using local entropy thresholding approach. The ratio of area of blood vessels in the inferiorsuperior side to area of blood vessels in the nasal-temporal side (ISNT) is combined with the CDR for the classification of fundus image as normal or glaucoma by using K-Nearest neighbor, Support Vector Machine and Bayes classifier. A batch of 36 retinal images obtained from the Aravind Eye Hospital, Madurai, Tamilnadu, India is used to assess the performance of the proposed system and a classification rate of 95% is achieved. © 2005-2011 JATIT & LLS. All rights reserved. Source

Discover hidden collaborations