Entity

Time filter

Source Type


Arunpriya C.,PSGR Krishnammal College For Women | Thanamani A.S.,Nallamuthu Gounder Mahalingam College
International Journal of Applied Engineering Research | Year: 2015

Due to more and more tea varieties in the current tea market, rapid and accurate identification of tea varieties is crucial for tea quality control. Tea quality mainly depends on the variety of leaf, growing environment, manufacturing conditions, size of ground tea leaves and infusion preparation. In the past few years, tea cultivar has been assessed by morphological assessment coupled with pattern recognition. This paper uses an efficient machine learning approach called Extreme Learning Machine (ELM) for the classification purpose. The proposed approach consists of four phases which are as preprocessing, feature extraction, feature clustering and classification. Additionally, this work proposes an iterative algorithm for feature clustering and applies it to leaf recognition. Feature clustering is a powerful tool to reduce the dimensionality of the selected feature. For improving the accuracy and performance of tea leaf recognition, ELM is implemented. The classifier is tested with 20 leaves from each variety and compared with k-NN and RBF approach. The proposed ELM classification produces effective results. © Research India Publications. Source


Santhi R.,Nallamuthu Gounder Mahalingam College | Prakash K.A.,Kongu Engineering College
Tamkang Journal of Mathematics | Year: 2011

The purpose of this paper is to introduce and study the concepts of intuitionistic fuzzy semi-generalized continuous mappings and intuitionistic fuzzy semi-generalized irresolute mappings in intuitionistic fuzzy topological space. Source


Ramamoorthy H.V.,Sree Saraswathi Thyagaraja College | Karthikeyani H.,Nallamuthu Gounder Mahalingam College
2014 International Conference on Information Communication and Embedded Systems, ICICES 2014 | Year: 2014

A Mobile Ad Hoc Networks (MANET) is a self-configuring network connected by wireless links and they are a collection of mobile nodes which communicate over radio. There are various routing protocols available for MANETs. Broadly they are classified into three. One is Proactive protocol, each node maintains one/more tables containing routing information to every node in the network. All nodes update these tables so as to maintain a consistent and up-to-date view of the network. Two is Reactive protocols, all up-to-date routes are not maintained at every node. Instead the routes are created as and when required. The route remains valid till the destination is reachable or until the routes no longer needed. Ant colony optimization (ACO) depicts a proactive behavior, is a metaheuristic for solving hard combinatorial optimization problems inspired by the indirect communication of real ants. Multi Agent System (MAS) depicts a reactive behavior, is used to solve problems that are difficult or impossible for an individual agent or a monolithic system to solve. Three is Hybrid Protocols, try to profit the advantages of both reactive and proactive protocols and combine their basic properties into one. They have the potential to provide higher scalability than pure reactive or proactive protocols. In this paper, a hybrid routing scheme that combines the best properties of ACO and MAS is proposed. The proposed hybrid protocol reduces the end-to end delay, minimizes the packet loss and results in maximum packet delivery ratio. © 2014 IEEE. Source


Thilagavathi D.,Nallamuthu Gounder Mahalingam College | Thanamani A.S.,Nallamuthu Gounder Mahalingam College
Research Journal of Applied Sciences, Engineering and Technology | Year: 2015

The development of a huge amount of client's job for equivalent performance on open-resource grid system is the main reason of system failures or delayed process due to grimy hardware, software vulnerability, as well as shared confined policy. In this study we represent highly reliability conditions in grid work scheduling and present a new procedure for scheduling by hybridization of intelligent water drop algorithm and particle swarm optimization technique and compare it with earliest deadline in the basis of first come first served. The IWDPSO algorithm is tested with two datasets namely Numerical Aerodynamic Simulation (NAS) and Parameter Sweep Application (PSA) and the results are tested with performance metrics makespan, slowdown and failure rate and grid utilization. The proposed algorithms results in effective usage of grid computing resources with reduced makespan, slowdown and failure rate. The proposed algorithm is compared with Risky-MinMin (RMM), Preemptive-MinMin (PMM) and Delay Tolerant Space-Time Genetic Algorithm (DTSTGA). © Maxwell Scientific Organization, 2015. Source


Thilagavathi D.,Nallamuthu Gounder Mahalingam College | Thanamani A.S.,Nallamuthu Gounder Mahalingam College
ARPN Journal of Engineering and Applied Sciences | Year: 2015

Grid computing is a network of computer resources where every resources are shared, turning a computer network into a powerful super computers. In which, Grid Scheduling is a non linear multi-objective problem. In this paper, intelligent water drop algorithm is hybridized with Tabu Search algorithm to solve scheduling problem in computational grid. The proposed algorithm named EIWD-TS is a meta-heuristic algorithm based on swarm intelligence. The optimization objective of this research is to find the near optimal solution considering multiple objectives namely makespan, slowdown ratio, failure rate and resource utilization of grid scheduling. The result of the proposed model of this paper is tested with PSA (Parameter Sweep Application) dataset and the results are compared with Risky-MinMin (RMM), Preemptive-MinMin (PMM), Particle Swarm Optimization (PSO) and IWD. Experimental evaluation shows that the EIWD-TS algorithm has good convergence property and better in quality of solution than other algorithms reported in recent literature. © 2006-2015 Asian Research Publishing Network (ARPN). Source

Discover hidden collaborations