Entity

Time filter

Source Type


Sivakumar P.,Manakula Vinayagar Institute of Technology | Durai Swamy K.,k-Technology
European Journal of Scientific Research | Year: 2011

Generally, due to unbalanced load allocation, congestion results in mobile adhoc networks. By keeping dynamic metrics such as network load, will result in load balanced routing thus avoiding congestion. The resources allocated for real-time traffic result in wastage of resources, if there is no such traffic is available for a particular period. In this paper, we propose a new distributed load based routing algorithm intended for a variety of traffic classes to establish the best routing paths. The proposed algorithm calculates the cost metric on the basis of the load on the links. The dynamic traffic can be classified as multimedia and normal traffic. Multimedia traffic is considered as high priority and normal traffic as low priority. The routing of high priority traffic is performed over the lightly loaded links, in such a manner that the links with lighter loads are chosen instead of links with heavier-loads. In addition, the resources can be shared between the high priority traffic's path and low priority traffic. In the absence of multimedia traffic, the lightly loaded path can be utilized by normal traffic. © EuroJournals Publishing, Inc. 2011.


Gopal U.N.,Manakula Vinayagar Institute of Technology
2012 International Conference on Radar, Communication and Computing, ICRCC 2012 | Year: 2012

Artificial Intelligence and web when amalgamated, it may produce miracle in terms of semantic web. E-learning works efficiently only when E-Content preparation is need based, searchable through semantic similarity between keywords. This paper describes a e-content/e-book preparation from existing available contents on a selected topic/topics, based on a semantic similarity between particular keywords. Accurately measuring semantic similarity between two words remains a challenging task. We propose an empirical method to estimate semantic similarity using page counts and text snippets. © 2012 IEEE.


Sandya M.,Manakula Vinayagar Institute of Technology
AICERA 2012 - Annual International Conference on Emerging Research Areas: Innovative Practices and Future Trends | Year: 2012

Practice of engineering has undergone numerous reformations in the recent years of globalization. The first and foremost question that arises in our mind regarding engineering is whether the engineering education system is capable of providing competent engineers. It is the first issue to be addressed in engineering. In the current generation of globalization there is a need to modify the engineering education system. This paper addresses the competencies required from an engineer, ways to enhance the competency and provides an insight into the trends in an engineering education system. © 2012 IEEE.


Seetharaman K.,Annamalai University | Palanivel N.,Manakula Vinayagar Institute of Technology
International Journal of Image and Data Fusion | Year: 2013

A statistical approach, based on full range Gaussian Markov random field model, is proposed for texture analysis such as texture characterization, unique representation, description, and classification. The parameters of the model are estimated based on the Bayesian approach. The estimated parameters are utilized to compute autocorrelation coefficients. The computed autocorrelation coefficients fall in between -1 and +1. The coefficients are converted into decimal numbers using a simple transformation. Based on the decimal numbers, two texture descriptors are proposed: (i) texnum, the local descriptor; (ii) texspectrum, the global descriptor. The decimal numbers are proposed to represent the textures present in a small image region. These numbers uniquely represent the texture primitives. The textured image under analysis is represented globally by observing the frequency of occurrences of the texnums called texspectrum. The textures are identified and are distinguished from untextured regions with edges. The classification analyses such as supervised and unsupervised are performed on the local descriptors. © 2013 Copyright Taylor and Francis Group, LLC.


Saraswathi D.,Manakula Vinayagar Institute of Technology | Srinivasan E.,Pondicherry Engineering College
International Journal of Biomedical Engineering and Technology | Year: 2014

This paper presents a new improved classification technique using Fully Complex-Valued Relaxation Networks (FCRN) based ensemble technique for classifying mammogram images. The system is developed based on three stages of breast cancer, namely normal, benign and malignant defined by the MIAS database. Features like binary object features, RST invariant features, histogram features, texture features and spectral features are extracted from the MIAS database. Extracted features are then given to the proposed FCRN-based ensemble classifier. FCRN networks are ensembled together for improving the classification rate. Receiver Operating Characteristic (ROC) analysis is used for evaluating the system. The results illustrate the superior classification performance of the ensembled FCRN. The resultant ensembled FCRN approximates the desired output more accurately with a lower computational effort. © 2014 Inderscience Enterprises Ltd.

Discover hidden collaborations