Abstract
Within cellular systems prediction has proven to be a potential solution to enhancing the handover procedure to guarantee constant Quality of Service to mobile users. By using historical route information, the future movement of mobile devices is predicted in advance with the aim to reserve resources prior to arrival of the device in a new cell. However, as the traffic patterns of devices in this environment change over time this needs to be taken into consideration when designing a prediction system. This paper presents a Neural Network-based movement prediction system for a cellular environment with a Genetic Algorithm-based retraining scheme using layer-based adaptive mutation to enhance the system performance in the presence of changing traffic patterns.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Reference
Nastac, I.; Matei, R. “Fast retraining of artificial neural networks”; Rough Sets, Fuzzy Sets, Data Mining and Granular Computing, Springer-Verlag in the series of Lecture Notes in Artificial Intelligence; 2003; pp. 458.462; ISBN: 978-3-540-14040-5.
Nastac, I.; Costea, A. “A Retraining Neural Network Technique for Glass Manufacturing Data Forecasting; International Joint Conference on Neural Networks”, 2004; Proceedings 2004; Volume 4; 25–29 July 2004 Page(s): 2753 – 2758.
Nastac, I.; Cristea, P., “ANN Flexible Forecasting for the Adaptive Monitoring of Multi-Tube Reactor”; 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services; 14th International Workshop on Systems, Signals and Image Processing 2007; 27–30 June 2007; Page(s): 193 – 196.
Doulamis, A.D.; Doulamis, N.D.; Kollias, S.D., “An Adaptable Neural-Network Model for Recursive Nonlinear Prediction and Modeling of MPEG Video Sources”; IEEE Transaction on Neural Networks; Volume 14, Issue 1; January 2003 Page(s): 150 – 166.
Ichibuchi, H.; Nakashima, T.; Nii, M., “Learning of Neural Networks with GA-Based Instance Selection”; Joint 9th IFSA World Congress and 20th NAFIPS International Conference, 2001; Volume 4, 25–28 July 2001; Page(s): 2102 – 2107 vol.4.
Ling, S.H.; Lam, H.K.; Leung, F.H.F.; Tam, P.K.S., “A Genetic Algorithm Based Neural-Tuned Neural Network”; IECON ‘03; The 29th Annual Conference of the IEEE – Industrial Electronics Society, 2003; Volume 3, 2–6 Nov. 2003 Page(s): 2423 – 2428 Vol.3.
Zuo, Guoyu; Liu, Wenju; Ruan, Xiaogang, “Genetic Algorithm Based RBF Neural Network for Voice Conversion”; WCICA 2004; Fifth World Congress on Intelligent Control and Automation, 2004; Volume 5, 15–19 June 2004 Page(s): 4215 – 4218 Vol.5.
Zhangang, Yang; Yanbo, Che; Cheng, K.W. Eric, “Genetic Algorithm-Based RBF Neural Network Load Forecasting Model”; IEEE Power Engineering Society General Meeting, 2007; 24–28 June 2007 Page(s): 1 – 6.
Ji, Tao; Pang, Qingle; Liu, Xinyun, “Study of Traffic Flow Forecasting Based on Genetic Neural Network”; Sixth International Conference on Intelligent Systems Design and Applications – ISDA ‘06; Volume 1, Oct. 2006; Page(s): 960 – 965.
Núñez, Edwin; Banks, Edwin Roger; Agarwal, Paul, “High Performance Evolutionary Computing”; HPCMP Users Group Conference 2006, June 2006; Page(s): 354 – 359.
DeJong, K.A. and Spears, W.M. “An Analysis of the Interacting Roles of Population Size and Crossover in Genetic Algorithms,” Proc. First Workshop Parallel Problem Solving from Nature, Springer-Verlag, Berlin, 1990. pp. 38–47
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer Science+Business Media B.V.
About this paper
Cite this paper
Bauer, C., Yu, H., Boffey, B. (2010). Adaptive Genetic Algorithm for Neural Network Retraining. In: Sobh, T., Elleithy, K., Mahmood, A. (eds) Novel Algorithms and Techniques in Telecommunications and Networking. Springer, Dordrecht. https://doi.org/10.1007/978-90-481-3662-9_40
Download citation
DOI: https://doi.org/10.1007/978-90-481-3662-9_40
Published:
Publisher Name: Springer, Dordrecht
Print ISBN: 978-90-481-3661-2
Online ISBN: 978-90-481-3662-9
eBook Packages: EngineeringEngineering (R0)