scholarly journals RMapCS: Radio Map Construction From Crowdsourced Samples for Indoor Localization

IEEE Access ◽  
2018 ◽  
Vol 6 ◽  
pp. 24224-24238 ◽  
Author(s):  
Yanzhen Ye ◽  
Bang Wang
Keyword(s):  
Indoor Localization ◽  
Map Construction ◽  
Radio Map

scholarly journals Joint Indoor Localization and Radio Map Construction with Limited Deployment Load

2015 ◽  
Vol 14 (5) ◽  
pp. 1031-1043 ◽  
Author(s):  
Sameh Sorour ◽  
Yves Lostanlen ◽  
Shahrokh Valaee ◽  
Khaqan Majeed
Keyword(s):  
Indoor Localization ◽  
Map Construction ◽  
Radio Map

scholarly journals Indoor Radio Map Construction Based on Position Adjustment and Equipment Calibration

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2818
Author(s):  
Ruolin Guo ◽  
Danyang Qin ◽  
Min Zhao ◽  
Xinxin Wang
Keyword(s):  
Particle Filtering ◽  
Wireless Local Area Network ◽  
Indoor Localization ◽  
Local Area Network ◽  
Dead Reckoning ◽  
Local Area ◽  
Area Network ◽  
Map Construction ◽  
Indoor Radio ◽  
Radio Map

The crowdsourcing-based wireless local area network (WLAN) indoor localization system has been widely promoted for the effective reduction of the workload from the offline phase data collection while constructing radio maps. Aiming at the problem of the diverse terminal devices and the inaccurate location annotation of the crowdsourced samples, which will result in the construction of the wrong radio map, an effective indoor radio map construction scheme (RMPAEC) is proposed based on position adjustment and equipment calibration. The RMPAEC consists of three main modules: terminal equipment calibration, pedestrian dead reckoning (PDR) estimated position adjustment, and fingerprint amendment. A position adjustment algorithm based on selective particle filtering is used by RMPAEC to reduce the cumulative error in PDR tracking. Moreover, an inter-device calibration algorithm is put forward based on receiver pattern analysis to obtain a device-independent grid fingerprint. The experimental results demonstrate that the proposed solution achieves higher localization accuracy than the peer schemes, and it possesses good effectiveness at the same time.

A novel radio map construction method to reduce collection effort for indoor localization

Measurement ◽  
2016 ◽  
Vol 94 ◽  
pp. 423-431 ◽  
Author(s):  
Chunrong He ◽  
Songtao Guo ◽  
Yan Wu ◽  
Yuanyuan Yang
Keyword(s):  
Indoor Localization ◽  
Construction Method ◽  
Map Construction ◽  
Radio Map

scholarly journals A Fast Radio Map Construction Method Merging Self-Adaptive Local Linear Embedding (LLE) and Graph-Based Label Propagation in WLAN Fingerprint Localization Systems

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 767 ◽  
Author(s):  
Yepeng Ni ◽  
Jianping Chai ◽  
Yan Wang ◽  
Weidong Fang
Keyword(s):  
Label Propagation ◽  
Positioning Accuracy ◽  
Local Linear Embedding ◽  
Map Construction ◽  
Local Linear ◽  
Linear Embedding ◽  
Fingerprint Database ◽  
Radio Map ◽  
Localization Systems ◽  
Self Adaptive

Indoor WLAN fingerprint localization systems have been widely applied due to the simplicity of implementation on various mobile devices, including smartphones. However, collecting received signal strength indication (RSSI) samples for the fingerprint database, named a radio map, is significantly labor-intensive and time-consuming. To solve the problem, this paper proposes a semi-supervised self-adaptive local linear embedding algorithm to build the radio map. First, this method uses the self-adaptive local linear embedding (SLLE) algorithm based on manifold learning to reduce the dimension of the high-dimensional RSSI samples and to extract a neighbor weight matrix. Secondly, a graph-based label propagation (GLP) algorithm is employed to build the radio map by semi-supervised learning from a large number of unlabeled RSSI samples to a few labeled RSSI samples. Finally, we propose a k self-adaptive neighbor weight (kSNW) algorithm, used for radio map construction in this paper, to realize online localization. The results of the experiments conducted in a real indoor environment show that the proposed method reduces the demand for large quantities of labeled samples and achieves good positioning accuracy. With only 25% labeled RSSI samples, our system can obtain positioning accuracy of more than 88%, within 3 m of localization errors.

Sign in / Sign up

Export Citation Format

Share Document