Date of Award
Master of Science in Engineering
Electrical and Computer Engineering
Dr. Ikhlas M. Abdel-Qader
Dr. Azim Houshyar
Dr. Janos L. Grantner
Masters Thesis-Campus Only
Restricted to Campus until
The most economic and affordable IPS are those incorporating existing infrastructure, such as the widely spread Wireless Local Area Network (WLAN). The Received Signal Strength (RSS) fingerprinting-based system is one of the most promising and powerful techniques so far to be used for indoor positioning. However, there are two challenges in using RSS based IPS; the first challenge is the variation of RSS to indoor multipath propagation, and the second is the high number of Access Points (APs) that are deployed in the region of interest. The first issue leads to degradation in the performance of RSS based IPS, while the second makes the computational cost too high and the positioning accuracy not adequate in real time.
WLAN dual bands to create a meaningful clustering structure using K-means and Cmeans clustering approaches, and the Euclidian distance similarity measure for classification. Also, to mitigate the dynamic nature of the RSS values, averaging consecutive values by using the moving average was implemented. . The investigation of using K-means and fuzzy C-means with two AP selection techniques shows that the performance of fuzzy C-means clustering technique is better than that of K-means. The proposed system resulted in a percentile reduction of computational complexity due to the reduced number of AP used while achieving a 0.7m positing accuracy.
Al Glehawi, Haider G., "On WLAN Fingerprint Indoor Positioning Systems Clustering, and Classification for Enhanced Performance" (2018). Master's Theses. 3698.