Congestion Controlled WSN using Genetic Algorithm with different Source and Sink Mobility Scenarios

Wireless Sensor Networks are extremely densely populated and have to handle large bursts of data during high activity periods giving rise to congestion which may disrupt normal operation. It usually occurs when most of the data packets follow one route to reach from source to destination. Thus, there is a need of some new approach which could control congestion to meet increasing traffic demand and improved utilization of existing resources. Chance of congestion increases when both source and sink node are mobile. Due to mobility of source or sink, there is a need of determining optimal path every time when source or sink changes its position. So selection of optimal path is necessary in order to mitigate chance of congestion in the network. This paper employs new genetic algorithm based approach to determine an optimal path from source to destination for different scenarios of source or/and sink node mobility. Concept of connection value and localization region has been employed to determine an optimal path each time the data packet is being sent. An optimal path is the path that has minimum number of connections. In order to send the data packet from source to destination, there is requirement of genetic algorithm that automatically controls congestion. Simulations are performed for different scenarios of source or/and sink mobility. Significant improvements have been observed in terms of congestion value for genetic algorithm. Simulations results determine best route with minimum connection value by incorporating genetic algorithm.

Effective Cluster based Routing Algorithm for WMNS using Effective Data Aggregation

Improving Classification Accuracy based on Random Forest Model with Uncorrelated High Performing Trees

Random forest can achieve high classification performance through a classification ensemble with a set of decision trees that grow using randomly selected subspaces of data. The performance of an ensemble learner is highly dependent on the accuracy of each component learner and the diversity among these components. In random forest, randomization would cause occurrence of bad trees and may include correlated trees. This leads to inappropriate and poor ensemble classification decision. In this paper an attempt has been made to improve the performance of the model by including only uncorrelated high performing trees in a random forest. Experimental results have shown that, the random forest can be further enhanced in terms of the classification accuracy. General Terms Random forest, Classification Accuracy, Uncorrelated trees.

A Novel Approach using Dual Active Feature Sample Selection and LTS (Learn to Search)

the bug signatures(context of bug) is difficult, as it involves mining the execution traces of the program. The discriminative graph mining algorithm is used to identify the bug signatures. It requires manual labelling of the input set to estimate the discriminative subgraphs. To reduce the tedious work of manual labelling, this paper presents novel framework to identify bug signatures. The proposed algorithm uses hybrid approach of dual active feature sample selection and LTS(Learn to Search). In the hybrid method, the dual active feature sample selection is used to find the query graph and its corresponding discriminative subgraphs, and LTS method is applied to obtain risk free optimal solution. The performance of the combined approach is measured with the parameters (i)runtime, (ii)recall and (iii)precision. The experiment results shows that this hybrid approach has an improved runtime of 60.10% when only 40% of the input graph set is manually labelled. The recall and precision are also improved by 33.33% when compared with dual active feature sample selection without LTS. KeywordsMining, Discriminative subgraph mining, Bug Signatures

Network Security Analysis in the Enterprise LANS

Local Area Networks (ELANs) have been expanding following an increase in the number of staff which necessitates establishment of new offices. However, reliability and security of services provided by ELANs need to be ensured at all times to meet expectations of users. In this paper, the network security holes existing within the ELANs were investigated. Vulnerabilities and threats were critically examined in one of the ELANs. It was observed that known vulnerabilities were still around within the network. Based on the findings, the paper suggests that all software used in the networking devices need to be updated; unneeded open ports need to be closed; cache servers and security policy need to be implemented. The suggestions will ensure stability of the network during scaling out as the number of staff continues to grow.

Enhanced Genetic Algorithm based Task Scheduling in Cloud Computing

Design Analysis of a Hexaband Slot Loaded Microstrip Patch Antenna using ANN

The designing of an antenna is a critical area for the present wireless communication system. It is important to maintain an agreement amongst gain, bandwidth, return loss and VSWR characteristics of antenna. In this paper an exclusive design concept for the circular patch antenna is introduced. Initially a circular microstrip patch antenna is designed and the performance of this new design is enhanced after applying different types of slotted perturbations in one half of antenna. The antenna performance is transformed from single band to multiband by employing ‘Y’ shape slotted structures. The proposed antenna represents quad band behavior at resonant frequencies 2.44 GHz, 6.48 GHz, 7 GHz and 8.25 GHz with a good value of return loss of -12.29 dB, -16.48 dB, -15 dB and -27.81 dB respectively. This design also represents VSWR between the specified range of 1 to 2 for the said resonant frequencies with an acceptable value of gain in dB. The antenna is designed and simulated with FEM based electromagnetic field solver. The proposed antenna design is suitable for WLAN, Radio astronomy, Passive sensors and Point to Point defense system wireless applications. The proposed antenna is analyzed for proper coaxial feed location using radial basis function neural networks. The results obtained using RBF neural networks are in a good agreement to the simulation results obtained using electromagnetic solver. The feed location provided by the RBF neural networks results in six band behavior.

A Comparative Analysis of Offline Signature Verification using Zernike Moment and Minutiae using Artificial Neural Network Approach

Improvisation to the R*-Tree kNN Join Principles in Distributed Environment

Music Genre Classification using Improved Artificial Neural Network with Fixed Size Momentum