基于生成对抗网络模型的RSS缺失值预测

doi:10.13190/j.jbupt.2019-210

北京邮电大学学报 ›› 2021, Vol. 44 ›› Issue (1): 26-31.doi: 10.13190/j.jbupt.2019-210

基于生成对抗网络模型的RSS缺失值预测

任晓琪, 翁仲铭

天津大学智能与计算学部, 天津 300350

收稿日期:2019-11-09 出版日期:2021-02-28 发布日期:2021-09-30
作者简介:任晓琪(1994-),女,硕士生,renxiaoqi@tju.edu.cn;翁仲铭(1970-),男,副教授.

RSS Missing Value Estimation with Generative Adversarial Networks Model

REN Xiao-qi, OWN Chung-ming

College of Intelligence and Computing, Tianjin University, Tianjin 300350, China

Received:2019-11-09 Online:2021-02-28 Published:2021-09-30

摘要/Abstract

摘要： 无线上网（Wi-Fi）定位是目前室内定位中的主流方法，指纹数据库的构建是Wi-Fi定位系统的关键.然而指纹数据库中的接收信号强度（RSS）指纹值会随室内环境的变化而变化，通常需要不断地重新测量指纹值去更新指纹数据库，这就导致了成本高、耗时长，尤其是在定位区域较大的动态环境中是不切实际的.针对此问题，提出了自适应上下文生成对抗网络模型.该模型只需测量指纹数据库中的部分RSS指纹，即"参考点"，然后通过学习参考点的分布情况，预测特定位置的缺失指纹.仿真实验结果表明，室内定位精确性显著提高，人力成本大大减少.

关键词: 接收信号强度指纹数据库, 生成对抗网络, 室内定位系统

Abstract: Wireless-fidelity(Wi-Fi)positioning is currently the mainstream method in indoor positioning,and the construction of fingerprint database is the key to Wi-Fi positioning system. However,the received signal strength(RSS)value in the fingerprint database will be changed with the variability of the indoor environment,and it is usually need to constantly re-measure the value in the fingerprint database,which leads to high cost and long time,especially in the dynamic environment with large positioning area. To address this problem,the adaptive context generative adversarial networks model is proposed. The model only needs to measure part of RSS fingerprints,and then learn the RSS fingerprints distribution to finally predict the missing fingerprint at a specific location. Simulation shows that the accuracy of indoor positioning is significantly improved,and the labor cost is greatly reduced.

Key words: received signal strength fingerprint database, generative adversarial network, indoor positioning system

中图分类号:

TN932

任晓琪, 翁仲铭. 基于生成对抗网络模型的RSS缺失值预测[J]. 北京邮电大学学报, 2021, 44(1): 26-31.

REN Xiao-qi, OWN Chung-ming. RSS Missing Value Estimation with Generative Adversarial Networks Model[J]. Journal of Beijing University of Posts and Telecommunications, 2021, 44(1): 26-31.

参考文献

[1] Opiela M, Frantiek Galík. Grid-based bayesian filtering methods for pedestrian dead reckoning indoor positioning using smartphones[J]. Sensors, 2020, 20(18):5343-5374.
[2] Yu Feng, Jiang Minghua, Liang Jing, et al. 5G WiFi signal-based indoor localization system using cluster k-nearest neighbor algorithm[J]. International Journal of Distributed Sensor Networks, 2014, 10(12):1-12.
[3] Li Wenjun, Chen Zhenyu, Gao Xingyu, et al. Multimod-el framework for indoor localization under mobile edge computing environment[J]. IEEE Internet of Things Journal, 2019, 6(3):4844-4853.
[4] Liu Hunghung, Liu Chun. Implementation of WiFi signal sampling on an android smartphone for indoor positioning systems[J]. Sensors, 2018, 18(1):1-16.
[5] Pu Yuchi, You Peichun. Indoor positioning system based on BLE location fingerprinting with classification approach[J]. Applied Mathematical Modelling, 2018, 62(10):654-663.
[6] Tolza X, Acco P, Fourniols J Y, et al. Optimal uncalibrated RSS indoor positioning and optimal reference node placement using cramér-rao lower bound[J]. Journal of Sensors, 2019, 2019(11):1-12.
[7] Koweerawong C, Wipusitwarakun K, Kaemarungsi K. Indoor localization improvement via adaptive RSS fingerprinting database[C]//International Conference on Information Networking. Bangkok:IEEE Computer Society, 2013:412-416.
[8] Yiu S, Yang Kai. Gaussian process assisted fingerprinting localization[J]. IEEE Internet of Things Journal, 2017, 3(5):683-690.
[9] Liu Kehan, Meng Zhaopeng, Own Chungming. Gaussian process regression plus method for localization reliability improvement[J]. Sensors, 2016, 16(8):1-17.
[10] Teng Fei, Tao Wenyuan, Own Chungming. Localization reliability improvement using deep Gaussian process regression model[J]. Sensors, 2018, 18(12):1-19.
[11] Renaudin O, Zemen T, Burgess T. Ray-tracing based fingerprinting for indoor localization[C]//International Workshop on Signal Processing Advances in Wireless Communications. Kalamata:IEEE, 2018:1-5.
[12] Wang Jie, Zhang Liang, Wang Changcheng, et al. Device-free human gesture recognition with generative adversarial networks[J]. Internet of Things Journal IEEE, 2020, 7(8):7678-7688.
[13] Pathak D, Krahenbuhl P, Donahue J, et al. Context encoders:feature learning by inpainting[C]//IEEE Conference on Computer Vision and Pattern Recognition. LasVegas:IEEE, 2016:2536-2544.
[14] Hu Jiusong, Liu Hongli, Liu Dawei, et al. Reducing WiFi fingerprint collection based on affinity propagation clustering and WKNN interpolation algorithm[C]//2018 2nd IEEE Advanced Information Management. Xi'an:IEEE, 2018:1-6.

基于生成对抗网络模型的RSS缺失值预测

RSS Missing Value Estimation with Generative Adversarial Networks Model

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	许同乐, 苏元浩, 孟良, 兰孝升, 李云凤. 优化GAN的风电机组齿轮箱故障诊断方法[J]. 北京邮电大学学报, 2023, 46(3): 62-66.
[2]	贾珺, 冯春燕, 夏海轮, 张天魁, 李成钢. 基于样本均衡与特征交互的通信网络故障预测方法[J]. 北京邮电大学学报, 2021, 44(6): 59-66.
[3]	王辰魁, 陈岳林, 蔡晓东. 图像样式风格迁移的行人再识别方法[J]. 北京邮电大学学报, 2021, 44(3): 67-72.
[4]	王蓬辉, 李明正, 李思. 基于数据增强的中文医疗命名实体识别[J]. 北京邮电大学学报, 2020, 43(5): 84-90.
[5]	曹志义, 牛少彰, 张继威. 基于生成对抗网络的遮挡图像修复算法[J]. 北京邮电大学学报, 2018, 41(3): 81-86.