Wi-Fi fingerprinting based on collaborative confidence level training

Jing, Hao; Pinchin, James; Hill, Chris; Moore, Terry

Abstract

Wi-Fi fingerprinting has been a popular indoor positioning technique with the advantage that infrastructures are readily available in most urban areas. However wireless signals are prone to fluctuation and noise, introducing errors in the final positioning result. This paper proposes a new fingerprint training method where a number of users train collaboratively and a confidence factor is generated for each fingerprint. Fingerprinting is carried out where potential fingerprints are extracted based on the confidence factor. Positioning accuracy improves by 40% when the new fingerprinting method is implemented and maximum error is reduced by 35%.

Citation

Jing, H., Pinchin, J., Hill, C., & Moore, T. (2016). Wi-Fi fingerprinting based on collaborative confidence level training. Pervasive and Mobile Computing, 30, https://doi.org/10.1016/j.pmcj.2015.10.005

• Journal Article Type: Article
• Acceptance Date: Oct 1, 2015
• Online Publication Date: Oct 22, 2015
• Publication Date: Aug 1, 2016
• Deposit Date: May 5, 2016
• Publicly Available Date: May 5, 2016
• Journal: Pervasive and Mobile Computing
• Print ISSN: 1574-1192
• Electronic ISSN: 1574-1192
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 30
• DOI: https://doi.org/10.1016/j.pmcj.2015.10.005
• Keywords: Indoor positioning; Wi-Fi fingerprinting; Collaborative positioning
• Public URL: https://nottingham-repository.worktribe.com/output/797610
• Publisher URL: http://dx.doi.org/10.1016/j.pmcj.2015.10.005
• Contract Date: May 5, 2016