Multi-observers instance-based learning approach for indoor symbolic user location determination using IEEE 802.11 signals

Mantoro, Teddy and Azizan, Ahmad and Khairuzzaman, Salahudin and Ayu, Media Anugerah (2009) Multi-observers instance-based learning approach for indoor symbolic user location determination using IEEE 802.11 signals. In: IEEE Symposium on Industrial Electronics and Applications (ISIEA 2009), 4 - 6 October, 2009, Kuala Lumpur.

PDF (Multi-observers instance-based learning) Restricted to Registered users only Download (882kB) | Request a copy

Abstract

Wi-Fi’s signals strength (SS), and signal quality (SQ) are found to greatly fluctuate in determination of symbolic user location in an indoor environment. This paper explores the influence of several different training data-sets in determining user’s symbolic location. The implementation and experimentation were done using offline instance-based machine learning methods to filter all of the training data-sets. The training data-sets were optimized using "multiple observers" k-Nearest Neighbor approach. Using this method, four different observations were compared, which were 8M observations of SQ and SS , 8M SS observers, 1M SQ and SS and the last was 1M SS observers. Then, a continuing determination of the user location was performed by finding the majority of the nearest ten (k=10) user locations.

Item Type:	Conference or Workshop Item (Full Paper)
Additional Information:	5960/4621 (ISBN: 9781424446810)
Uncontrolled Keywords:	Symbolic user location, location-aware computing, location context awareness
Subjects:	T Technology > T Technology (General)
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Information and Communication Technology > Department of Information System
Depositing User:	Media Ayu
Date Deposited:	27 Sep 2011 10:00
Last Modified:	27 Sep 2011 10:00
URI:	http://irep.iium.edu.my/id/eprint/4621

Actions (login required)

View Item