TY - JOUR
T1 - AF-DCGAN
T2 - Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems
AU - Li, Qiyue
AU - Qu, Heng
AU - Liu, Zhi
AU - Zhou, Nana
AU - Sun, Wei
AU - Sigg, Stephan
AU - Li, Jie
N1 - Funding Information:
Manuscript received April 20, 2019; revised July 19, 2019 and August 30, 2019; accepted September 29, 2019. Date of publication November 5, 2019; date of current version May 25, 2021. This work was supported in part by National Natural Science Foundation of China, Grant 51877060, in part by ANHUI Province Key Laboratory of Affective Computing & Advanced Intelligent Machine, Grant ACAIM180102, in part by the Fundamental Research Funds for the Central Universities, under Grants JZ2018HGTB0253, JZ2019HGTB0089, and PA2019GDQT0006, and in part by State Grid Science and Technology Project (Research and application of key Technologies for integrated substation intelligent operation and maintenance based on the fusion of heterogeneous network and heterogeneous data). (Corresponding author: Jie Li.) Q. Li, H. Qu, N. Zhou, and W. Sun are with the School of Electrical Engineering and Automation, Hefei University of Technology, Hefei 230009, China (e-mail: liqiyue@mail.ustc.edu.cn; quhengedu@mail.hfut.edu.cn; nnzhou@mail.hfut.edu.cn; wsun@hfut.edu.cn).
Publisher Copyright:
© 2017 IEEE.
PY - 2021/6
Y1 - 2021/6
N2 - With widely deployed WiFi network and the uniqueness feature (fingerprint) of wireless channel information, fingerprinting based WiFi positioning is currently the mainstream indoor positioning method, in which fingerprint database construction is crucial. However, for accuracy, this approach requires enough data to be sampled at many reference points, which consumes excessive efforts and time. In this paper, we collect Channel State Information (CSI) data at reference points by the method of device-free localization, then we convert collected CSI data into amplitude feature maps and extend the fingerprint database using the proposed Amplitude-Feature Deep Convolutional Generative Adversarial Network (AF-DCGAN) model. The use of AF-DCGAN accelerates convergence during the training phase, and substantially increases the diversity of the CSI amplitude feature map. The extended fingerprint database both reduces the human effort involved in fingerprint database construction and the accuracy of an indoor localization system, as demonstrated in the experiments.
AB - With widely deployed WiFi network and the uniqueness feature (fingerprint) of wireless channel information, fingerprinting based WiFi positioning is currently the mainstream indoor positioning method, in which fingerprint database construction is crucial. However, for accuracy, this approach requires enough data to be sampled at many reference points, which consumes excessive efforts and time. In this paper, we collect Channel State Information (CSI) data at reference points by the method of device-free localization, then we convert collected CSI data into amplitude feature maps and extend the fingerprint database using the proposed Amplitude-Feature Deep Convolutional Generative Adversarial Network (AF-DCGAN) model. The use of AF-DCGAN accelerates convergence during the training phase, and substantially increases the diversity of the CSI amplitude feature map. The extended fingerprint database both reduces the human effort involved in fingerprint database construction and the accuracy of an indoor localization system, as demonstrated in the experiments.
KW - amplitude feature
KW - channel state information (CSI)
KW - fingerprint
KW - generative adversarial network
KW - Wi-Fi positioning
UR - http://www.scopus.com/inward/record.url?scp=85107175537&partnerID=8YFLogxK
U2 - 10.1109/TETCI.2019.2948058
DO - 10.1109/TETCI.2019.2948058
M3 - Article
AN - SCOPUS:85107175537
VL - 5
SP - 468
EP - 480
JO - IEEE Transactions on Emerging Topics in Computational Intelligence
JF - IEEE Transactions on Emerging Topics in Computational Intelligence
SN - 2471-285X
IS - 3
M1 - 8891678
ER -