Abstract
Efficient planning and improved quality of service (QoS) in wireless networks call for the use of mobility prediction schemes. Such schemes ensure accurate mobility prediction of wireless users and units which plays a major role in optimized planning and management of the available bandwidth and power resources. In this paper, fully-complex extreme learning machines (CELMs) model and predict the mobility patterns of arbitrary nodes in a mobile ad hoc network (MANET). Unlike their real-valued counterparts, CELMs properly capture the existing interaction/ correlation between the nodes' location coordinates leading to more realistic and accurate prediction. Simulation results using standard mobility models and real-world mobility data clearly show that the proposed complex-valued prediction algorithm outperforms many existing real-valued learning machines in terms of prediction accuracy.
| Original language | English |
|---|---|
| Title of host publication | 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Proceedings |
| Publisher | i6doc.com publication |
| Pages | 607-612 |
| Number of pages | 6 |
| ISBN (Electronic) | 9782874190957 |
| State | Published - 2014 |
| Event | 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Bruges, Belgium Duration: 23 Apr 2014 → 25 Apr 2014 |
Publication series
| Name | 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Proceedings |
|---|
Conference
| Conference | 22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 |
|---|---|
| Country/Territory | Belgium |
| City | Bruges |
| Period | 23/04/14 → 25/04/14 |
Bibliographical note
Funding Information:Research supported by King Fahd University of Petroleum and Minerals.
ASJC Scopus subject areas
- Artificial Intelligence
- Information Systems