Abstract | ||
---|---|---|
Indoor localization based on Wi-Fi is crucial for many practical applications. However, considered the highly dynamic indoor environment, Wi-Fi indoor localization system cannot maintain the high performance for longtime. To address this challenge, we propose a novel online deep learning approach OSDELM, which guarantees the running time of localization system from two aspects: discriminative feature, and updated model. Specifically, deep learning helps extract discriminative Wi-Fi features, and online learning updates the out-of-date model to fit the new environment. The experiments in real indoor environment show that the proposed OSDELM method can cope with the highly dynamic indoor environment issue and make the localization system work well in online manner. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1145/2800835.2800850 | UbiComp/ISWC Adjunct |
Field | DocType | Citations |
Online learning,Computer vision,Computer science,Localization system,Artificial intelligence,Deep learning,Discriminative model | Conference | 1 |
PageRank | References | Authors |
0.38 | 10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yang Gu | 1 | 56 | 7.54 |
Yiqiang Chen | 2 | 1446 | 109.32 |
Junfa Liu | 3 | 357 | 26.85 |
Xinlong Jiang | 4 | 76 | 10.70 |