A Hidden Genetic Layer Based Neural Network for Mobility Prediction

Abstract

Problem statement: With numerous wireless devices increasingly connecting to the internet, WLAN infrastructure planning becomes very important to maintain desired quality of services. For maintaining desired quality of service it is desirable to know the movement pattern of users. Mobility prediction involves finding the mobile device's next access point as it moves through the wireless network. Hidden Markov models and Bayesian approach have been proposed to predict the next hop. Approach: In this study we propose a new method for feature extraction and propose a novel neural network classifier based on a hidden Genetic Algorithm layer-GA-SOFM Neural Network. We evaluate our hypotheses by using one month syslog data of Dartmouth college mobility traces available online to extract mobility features and use this features to find the classification accuracy of the proposed model. Results and Conclusion: Proposed methodology was implemented and obtained accuracy in mobility prediction was 83.68%. The output obtained is better than Naive Bayesian method by 15.56% and over CART by 11.94%.

Mobility Analysis for Passive Reservations in Vehicular Cellular Networks Based on Dynamic Programming and Roads Compression

“…Two passive reservation techniques are proposed in (Zhang, 2001), exploiting Wiener prediction and time series theory, making in-advance reservations under non-Poisson and/or non-stationary arrival processes, arbitrary distributed call and channel holding time and arbitrary per-call resource demands. In (Velmurugan, 2012) the authors give a contribution in WLAN infrastructure planning, basing their decisions on mobility prediction: they propose a new method for feature extraction with a novel neural network classifier based on a hidden genetic algorithm, reaching an acceptable prediction accuracy. In previous works , a prediction technique based on the Cell Stay Time (CST) evaluation of a mobile user is proposed.…”