Browsing by Author "Mrindoko, Nicholaus Rashid"

Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Improving performance of indoor positioning system using received signal strength (RSS) – based WLAN fingerprinting: a case of College of Information and Communication Technologies (CoICT)
    (University of Dar es Salaam, 2015) Mrindoko, Nicholaus Rashid
    Satellite-based Global Positioning Systems (GPS) and Cellular Networks (CNs) have enabled a variety of location based services. However, GPS and CNs do not work well in indoor environments where walls and excessive multipath objects greatly attenuate satellite and cellular signals. This study has proposed an Indoor Positioning System (IPS) based on widely deployed indoor Wi-Fi systems. The system uses not only the Received Signal Strength (RSS) values measured at the current location but also the previous location information to determine the current location of a mobile user. The study was conducted at the College of Information and Communication Technologies (CoICT) of the University of Dar es Salaam. Study results show that RSS distribution is not usually Gaussian as it is left or right skewed. Each cluster of the RSS measured at reference points (RPs) may represent one location. In such case, a simple Euclidean distance from mean value was used to calculate a user location. This provides a good accuracy performance in a positioning system where errors estimate between trained RSS and sent signal from mobile device is calculated. Although the positioning system has shown a good accuracy performance of (1 m - 5 m), RSS in some of the RPs was found not to be well distributed, so it is better to look for alternative model for the RSS distribution. Mathematical correlation to allow cross platform mobile application for location positioning from a fingerprinting database is another area of study to be considered. The impact of multiple floors is not yet known, and to improve the performance of the system there is a need to find a solution to deal with the effect of the antenna gain during the online phases.