TY - JOUR
T1 - SmartLoc
T2 - Smart Wireless Indoor Localization Empowered by Machine Learning
AU - Li, Lin
AU - Guo, Xiansheng
AU - Ansari, Nirwan
N1 - Funding Information:
This work was supported in part by the National Natural Science Foundation of China under Grant 61371184, Grant 61671137, Grant 61771114, and Grant 61771316, and in part by the Technology Department in Sichuan Province under Grant 2018JY0242 and Grant 2018JY0218.
Funding Information:
Manuscript received January 10, 2019; revised March 26, 2019 and May 24, 2019; accepted June 21, 2019. Date of publication August 30, 2019; date of current version March 31, 2020. This work was supported in part by the National Natural Science Foundation of China under Grant 61371184, Grant 61671137, Grant 61771114, and Grant 61771316, and in part by the Technology Department in Sichuan Province under Grant 2018JY0242 and Grant 2018JY0218. (Corresponding author: Xiansheng Guo.) L. Li and X. Guo are with the Department of Electronic Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China (e-mail:,linli9419@gmail.com; xsguo@uestc.edu.cn).
Publisher Copyright:
© 2019 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - Recently, machine learning (ML) has been widely adopted for fingerprint-based indoor localization because of its potency in delineating relationships between received signal strength (RSS) information and labels accurately. Existing ML-based indoor localization systems are less robust because they only adopt the output with the highest probability. This affects the final location estimate, hence compromising accuracy due to the severity of RSS fluctuations. Since different ML algorithms (MLAs) yield different performances, it is therefore intuitive to fuse predictions from multiple MLAs to improve the positioning performance in the presence of signal fluctuation. In this article, we propose SmartLoc, a smart wireless indoor localization framework to enhance indoor localization. In the offline phase, multiple MLAs are trained by utilizing an offline database. We further apply probability alignment to guarantee the predicted probabilities of each MLA at the same confidence level. In the online phase, given a testing RSS sample of a user at an unknown location, we extract the labels with probabilities greater than a certain threshold from each MLA to construct the space of candidate labels (SCL). The size of SCL can be adaptively determined by using our proposed dynamic size determination algorithm. Based on the SCL, we propose a probabilistic model to intelligently estimate the user's location by evaluating the label credibility simultaneously. A high label credibility indicates that the frequently occurred label is more likely to be true. Experimental results in a real changing environment verify the superiority of SmartLoc, outperforming the best among comparative methods by 10.8% in 75th percentile accuracy.
AB - Recently, machine learning (ML) has been widely adopted for fingerprint-based indoor localization because of its potency in delineating relationships between received signal strength (RSS) information and labels accurately. Existing ML-based indoor localization systems are less robust because they only adopt the output with the highest probability. This affects the final location estimate, hence compromising accuracy due to the severity of RSS fluctuations. Since different ML algorithms (MLAs) yield different performances, it is therefore intuitive to fuse predictions from multiple MLAs to improve the positioning performance in the presence of signal fluctuation. In this article, we propose SmartLoc, a smart wireless indoor localization framework to enhance indoor localization. In the offline phase, multiple MLAs are trained by utilizing an offline database. We further apply probability alignment to guarantee the predicted probabilities of each MLA at the same confidence level. In the online phase, given a testing RSS sample of a user at an unknown location, we extract the labels with probabilities greater than a certain threshold from each MLA to construct the space of candidate labels (SCL). The size of SCL can be adaptively determined by using our proposed dynamic size determination algorithm. Based on the SCL, we propose a probabilistic model to intelligently estimate the user's location by evaluating the label credibility simultaneously. A high label credibility indicates that the frequently occurred label is more likely to be true. Experimental results in a real changing environment verify the superiority of SmartLoc, outperforming the best among comparative methods by 10.8% in 75th percentile accuracy.
KW - Indoor localization
KW - machine learning (ML)
KW - received signal strength (RSS)
KW - smart localization
KW - wireless fingerprinting
UR - http://www.scopus.com/inward/record.url?scp=85082144715&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85082144715&partnerID=8YFLogxK
U2 - 10.1109/TIE.2019.2931261
DO - 10.1109/TIE.2019.2931261
M3 - Article
AN - SCOPUS:85082144715
SN - 0278-0046
VL - 67
SP - 6883
EP - 6893
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
IS - 8
M1 - 8820139
ER -