During natural disasters like earth quake and floods, various public emergency agencies like fire services, civil defenses have to coordinate at the disaster site without proper infrastructure. To achieve communication at ground zero wireless networks play a very important role. The wireless network provides global services through integrated networks and using multihop communication without infrastructure. To achieve Quality of Service (QoS) Mobility prediction, precise and competent forecast of mobile users trail is of significance for improved network performance. Mobility prediction along with wireless communication protocols helps in resource management in a disaster management scenario. In this paper a mobility prediction mechanism using Neural Network is proposed. A novel training algorithm based on parallel Swarm Intelligence algorithm is proposed. The proposed technique is evaluated on Multi-Layer Perceptron Neural Network (MLPNN) and Jordan Network. Simulation results on large mobility traces show high degree of classification accuracy.
Mobility Prediction, Bee Algorithm (BA), Fish School Search (FSS), Multi-Layer Perceptron Neural Network (MLPNN) and Jordan Network
Share This Article
© The Author(s) 2015. Open Access. This article is distributed under the terms of the Creative Commons Attribution 4.0 International License which permits unrestricted use, sharing, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.