Browsing by Author "Wu, Bing-Jhen"

Now showing 1 - 2 of 2

Cluster-enhanced techniques for pattern-matching localization systems
(2007)
Kuo, Sheng-Po
;
Wu, Bing-Jhen
;
Peng, Wen-Chih
;
Tseng, Yu-Chee
;
資訊工程學系
In location-based services, the response time of location determination is critical, especially for real-time applications. This is especially true for pattern-matching localization methods, which rely on comparing tin object's current signal strength pattern against a pre-established location database of signal strength patterns collected in the training phase. In this work, we propose some cluster-enhanced techniques to speed up the positioning process while avoiding the possible positioning errors caused by this accelerated mechanism. Through grouping training locations with similar signal strength patterns together and characterizing them by a single feature vector, we show how to reduce the associated comparison cost so as to accelerate? the pattern-matching process. To deal with signal fluctuations, several clustering strategies allowing overlaps are proposed. Extensive simulation studies are conducted. Experimental results show that compared to the pattern-matching systems without clustering techniques, a reduction of more than 90% in computation cost can be obtained in average without degrading the positioning accuracy.
GeoAds: A middleware architecture for music service with location-aware advertisement
(2007)
Kuo, Sheng-Po
;
Lin, Shih-Ching
;
Wu, Bing-Jhen
;
Tseng, Yu-Chee
;
Shen, Chung-Chou
This paper presents a middleware architecture to support location-based services (LBSs) based on heterogeneous localization systems. A GEOINFO gateway is implemented to hide the discrepancy of different localization systems from application developers. Hence, application developers can deploy their LBSs easily without considering the underlying localization techniques. To demonstrate the detailed process and advantages of the proposed architecture, we present a location-based service, called GeoAds, which is a streaming music service with geographical advertisement. This novel integration is expected to attract more mobile users' attention.