A new algorithm for improving the tracking and positioning of cell of origin

Bai, Yuntian Brian; Norman, Robert; Zhao, Yiqi; Tang, Shuangxia; Wu, Suqin; Wu, Hong Ren; Retscher, Guenther; Zhang, Kefei

doi:10.1109/iain.2015.7352267

Cited by 5 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Generally speaking, Wi-Fi-based indoor positioning methods are divided into two main categories, namely, geometry-based localization methods and fingerprint-based positioning methods. Geometry-based localization can be performed by angle of arrival (AoA), 7 time of arrival (ToA), 8 cell of origin (CoO), 9 time difference of arrival (TDoA), 10 and symmetrical double sided two way ranging (SDS-TWR). 11 The geometry-based location method requires not only additional hardware infrastructure but also time synchronization.…”

Section: Introductionmentioning

confidence: 99%

Wi‐Fi fingerprint‐based indoor location: Multiple fingerprints and multiple classifiers with two‐layer fusion weights

Liu,

Gao

et al. 2024

Int J Communication

View full text Add to dashboard Cite

SummaryIndoor location based on Wi‐Fi fingerprint has attracted extensive attention recently, since it only requires a mobile device and existing network; it does not require additional infrastructure and hardware. However, localization using only received signal strength fingerprint is susceptible to dynamic environments and device heterogeneity. Localization using signal strength differences fingerprint and hyperbolic location fingerprint which extracted from received signal strength fingerprint is a powerful measure to overcome the device heterogeneity. Existing fusion‐based methods do not fully use of the mutual fusion function of multiple fingerprints, which leads to low positioning accuracy. In order to further improve the positioning accuracy, we propose a multifingerprint multiclassifier and two‐layer fusion weight positioning model. The proposed approach first creates a multiple fingerprints group by gleaning signal strength differences fingerprint and hyperbolic location fingerprint from received signal strength fingerprint. In order to deal with the accuracy decline caused by a single classifier in complex scenes, three typical classifiers, random forest (RF), K‐nearest neighbor (KNN), and support vector machine (SVM), are adopted, and a fusion weight selection algorithm is proposed to improve the localization accuracy by choosing fusion weights intelligently from the two‐layer fusion weights. Experiment results show that the proposed scheme is effective to resolve device heterogeneity, and the position accuracy is improved about 16.9% and 5.8%, respectively, compared with single fingerprint and classifier schemes. The results show that, compared with the single fingerprint scheme, the position accuracy is improved at least 16.9% and 28.4% for the homogeneous and heterogeneous equipments, respectively; as for the proposed multiclassifier fusion method, it achieves at least 5.8% and 8.7% accuracy improvement for the cases with homogeneous and heterogeneous equipments, respectively, compared with other traditional classifiers such as RF, KNN, and SVM.

show abstract