By Topic

Neural network based precise location identification in a cellular mobile

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Mitra, S. ; Dept. of Comput. Sci. & Tech., Bengal Eng. Coll., Howrah, India ; DasBit, S.

Next generation wireless networks are expected to support broadband multimedia services because of increasing demand for multimedia services. In such network, a mobile user may require multiple channels, and different users may require different numbers of channels. In order for a mobile user to gain access to a wireless network from anywhere in the service areas of the network, it is unavoidable that the coverage areas of two or more base stations overlap with each other. Channel rearrangement is a technique that enables a mobile user in the overlap area to handoff to another base station, such that the released channels can be used by a new call or a handoff call. In one such wireless network, i.e., the cellular network, with the increase in number of users, the demand for different services is growing day by day. For many such services it is required to identify the exact location of a mobile user within a radius of few meters or so. A neural network with its learning and generalization ability may act as a suitable tool to predict the precise location of a user provided it is trained appropriately by varying network conditions such as channel rearrangement, signal strength etc. The present work employs the 'mixture of experts' model based neural network having two experts. We have generated 15000 input patterns for both the experts for training and testing of the system. The scheme has reduced location management cost and is free from all unrealistic assumptions.

Published in:

Personal Wireless Communications, 2005. ICPWC 2005. 2005 IEEE International Conference on

Date of Conference:

23-25 Jan. 2005