Fuzzy logic based compensated Wi-Fi signal strength for indoor positioning
Work in indoor positioning so far broadly relies on either signal propagation models or location fingerprinting. The former approach has inherent modelling complexity as a result of intervening walls and movement in the environment which, impacts the accuracy of such models. The latter approach on t...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English English |
| Published: |
IEEE Computer Society
2014
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/58322/ http://irep.iium.edu.my/58322/ http://irep.iium.edu.my/58322/ http://irep.iium.edu.my/58322/1/58322_Fuzzy%20logic%20based%20compensated%20Wi-Fi%20_complete.pdf http://irep.iium.edu.my/58322/2/58322_Fuzzy%20logic%20based%20compensated%20Wi-Fi%20_scopus.pdf |
| Summary: | Work in indoor positioning so far broadly relies on either signal propagation models or location fingerprinting. The former approach has inherent modelling complexity as a result of intervening walls and movement in the environment which, impacts the accuracy of such models. The latter approach on the other hand, is acclaimed to give better accuracy. However, for it to be used, an added overhead of surveying history data of a calibration of every indoor environment is required. Moreover, if any of the mobile Access Points (APs) included in the surveyed history data is down for any reason, the result of the location fingerprinting approach is impacted. This work proposes an indoor location determination approach that uses Fuzzy Weighted Aggregation of Received Signal Strengths (RSS) of Wi-Fi signals with Compensated Weighted Attenuation Factor (CWAF) in the form of fuzzy weighted signal quality and noise. The results are compared with locations away from APs with actual physical measurement in the environmental location to verify accuracy. The performance of the proposed algorithm shows that if the normalized weighted signal strength is properly compensated with weighted signal quality and noise, the approach offers a more computationally efficient positioning with adequate accuracy for indoor localization. |
|---|