基于域自适应的Wi-Fi指纹设备无关室内定位模型

doi:10.11959/j.issn.1000-436x.2022069

摘要/Abstract

摘要：

基于Wi-Fi指纹定位方法在大规模实际应用中存在设备多样性问题，定位精度受到极大影响。提出了一种设备无关的 Wi-Fi 指纹室内定位模型 DeviceTransfer。该模型基于深度学习的域自适应理论，把智能手机的设备类型作为域，通过对抗训练来提取任务相关而设备无关的Wi-Fi数据特征，并把学习到的源域位置信息迁移到目标域上。采用预训练和联合训练来提高模型训练的稳定性并加快收敛。在教学楼和商场2个真实场景中，使用 4 台不同型号的智能手机验证模型的性能。实验结果表明，DeviceTransfer 能够有效提取设备无关的Wi-Fi数据特征。只使用一台手机在参考点采集Wi-Fi指纹，使用其他型号手机在线定位也能获得较高的定位精度，降低了定位成本。

关键词: 设备多样性, Wi-Fi指纹定位, 室内定位, 域自适应, 深度学习

Abstract:

In real-world large-scale deployments of indoor localization, Wi-Fi fingerprinting approaches suffer from device diversity problem which impacts the localization accuracy significantly.A device-independent Wi-Fi fingerprint indoor localization model DeviceTransfer was proposed.Based on the domain adaptation theory of deep learning, the device type of the smartphone was taken as the domain, the task-related and device-independent Wi-Fi data features were extracted through adversarial training, and the learned source domain location information was transferred to the target domain.Pre-training and joint training were employed to improve model training stability and to accelerate convergence.The performance of DeviceTransfer was evaluated using four types of smartphones in two real-world indoor environments: a school building and a shopping mall.The experimental results show that DeviceTransfer effectively extracts device-independent Wi-Fi fingerprint features.Using only one type of phone to collect Wi-Fi fingerprints, online localization using other types still achieves high localization accuracy, thus reducing localization cost significantly.

Key words: device diversity, Wi-Fi fingerprinting localization, indoor localization, domain adaptation, deep learning

中图分类号:

TP393

赵增华, 童跃凡, 崔佳洋. 基于域自适应的Wi-Fi指纹设备无关室内定位模型[J]. 通信学报, 2022, 43(4): 143-153.

Zenghua ZHAO, Yuefan TONG, Jiayang CUI. Device-independent Wi-Fi fingerprinting indoor localization model based on domain adaptation[J]. Journal on Communications, 2022, 43(4): 143-153.

图/表 10

图1

图2

图3

图4

图5

表1

图6

图7

图8

图9

参考文献 35

[1]	HE S N , CHAN S H G . Wi-Fi fingerprint-based indoor positioning:recent advances and comparisons[J]. IEEE Communications Surveys＆ Tutorials, 2016,18(1): 466-490.
[2]	王慧强, 高凯旋, 吕宏武 . 高精度室内定位研究评述及未来演进展望[J]. 通信学报, 2021,42(7): 198-210.
	WANG H Q , GAO K X , LYU H W . Survey of high-precision localization and the prospect of future evolution[J]. Journal on Communications, 2021,42(7): 198-210.
[3]	LUI G , GALLAGHER T , LI B H ,et al. Differences in RSSI readings made by different Wi-Fi chipsets:a limitation of WLAN localization[C]// Proceedings of 2011 International Conference on Localization and GNSS (ICL-GNSS). Piscataway:IEEE Press, 2011: 53-57.
[4]	ZHENG V W , PAN S J , YANG Q ,et al. Transferring multi-device localization models using latent multi-task learning[C]// Proceedings of the Twenty-Third AAAI Conference on Artificial Intelligence. California:AAAI Press, 2008: 1427-1432.
[5]	TSUI A W , CHUANG Y H , CHU H H . Unsupervised learning for solving RSS hardware variance problem in Wi-Fi localization[J]. Mobile Networks and Applications, 2009,14(5): 677-691.
[6]	HUANG C C , MANH H N , WANG Y S . An self-adaptive wireless indoor localization system for device diversity[C]// Proceedings of 2016 IEEE International Conference on Consumer Electronics. Piscataway:IEEE Press, 2016: 1-2.
[7]	ZHANG L Y , MA L , XU Y B ,et al. Linear regression algorithm against device diversity for indoor WLAN localization system[C]// Proceedings of 2017 IEEE Global Communications Conference. Piscataway:IEEE Press, 2017: 1-6.
[8]	ZHANG L Y , MENG X L , FANG C . Linear regression algorithm against device diversity for the WLAN indoor localization system[J]. Wireless Communications and Mobile Computing,2021, 2021:5530396.
[9]	ZHAO H , DES-COMBES R T , ZHANG K ,et al. On learning invariant representations for domain adaptation[C]// Proceedings of the 36th International Conference on Machine Learning.[S.l.:s.n.], 2019: 7523-7532.
[10]	YANG S , DESSAI P , VERMA M ,et al. FreeLoc:calibration-free crowdsourced indoor localization[C]// Proceedings of IEEE INFOCOM. Piscataway:IEEE Press, 2013: 2481-2489.
[11]	CAI C W , DENG L , LI S F . CSI-based device-free indoor localization using convolutional neural networks[C]// Proceedings of 2018 IEEE 4th International Conference on Computer and Communications. Piscataway:IEEE Press, 2018: 753-757.
[12]	ASHRAF I , KANG M Y , HUR S ,et al. MINLOC:magnetic field patterns-based indoor localization using convolutional neural networks[J]. IEEE Access, 2020,8: 66213-66227.
[13]	WILSON G , COOK D J . A survey of unsupervised deep domain adaptation[J]. ACM Transactions on Intelligent Systems and Technology, 2020,11(5): 1-46.
[14]	SUN B , FENG J , SAENKO K . Return of frustratingly easy domain adaptation[C]// Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence. California:AAAI Press, 2016: 2058-2065.
[15]	KANG G L , JIANG L , YANG Y ,et al. Contrastive adaptation network for unsupervised domain adaptation[C]// Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2019: 4888-4897.
[16]	GHIFARY M , KLEIJN W B , ZHANG M ,et al. Deep reconstruction-classification networks for unsupervised domain adaptation[C]// Proceedings of the European Conference on Computer Vision. Berlin:Springer, 2016: 597-613.
[17]	BOUSMALIS K , TRIGEORGIS G , SILBERMAN N ,et al. Domain-separation networks[J]. Advances in Neural Information Processing Systems, 2016,29: 343-351.
[18]	MATHUR A , ISOPOUSSU A , KAWSAR F ,et al. FlexAdapt:flexible cycle-consistent adversarial domain adaptation[C]// Proceedings of 2019 18th IEEE International Conference on Machine Learning and Applications. Piscataway:IEEE Press, 2019: 896-901.
[19]	YI Z L , ZHANG H , TAN P ,et al. DualGAN:unsupervised dual learning for image-to-image translation[C]// Proceedings of 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2017: 2868-2876.
[20]	GANIN Y , LEMPITSKY V . Unsupervised domain adaptation by backpropagation[C]// Proceedings of the 32nd International Conference on Machine Learning. Cambridge:JMLR, 2015: 1180-1189.
[21]	ZHANG W C , OUYANG W L , LI W ,et al. Collaborative and adversarial network for unsupervised domain adaptation[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2018: 3801-3809.
[22]	CHEN C H , MIAO Y S , LU C X ,et al. Motion transformer:transferring neural inertial tracking between domains[C]// Proceedings of the AAAI Conference on Artificial Intelligence. NewYork:ACM Press, 2019,33: 8009-8016.
[23]	SOHN K , LEE H , YAN X . Learning structured output representation using deep conditional generative models[J]. Advances in neural information processing systems, 2015,28: 3483-3491.
[24]	MIRZA M , OSINDERO S . Conditional generative adversarial nets[J]. arXiv Preprint,arXiv:1411.1784, 2014.
[25]	GOODFELLOW I J , POUGET-ABADIE J , MIRZA M ,et al. Generative adversarial nets[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems. Cambridge:MIT Press, 2014: 2672-2680.
[26]	ZHU J Y , PARK T , ISOLA P ,et al. Unpaired image-to-image translation using cycle-consistent adversarial networks[C]// Proceedings of 2017 IEEE International Conference on Computer Vision. Piscataway:IEEE Press, 2017: 2242-2251.
[27]	KINGMA D P , BA J . Adam:a method for stochastic optimization[J]. arXiv Preprint,arXiv:1412.6980, 2014.
[28]	PASZKE A , GROSS S , CHINTALA S ,et al. Automatic differentiation in pytorch[C]// Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017). New York:Curran Associates Inc, 2017: 1-4.
[29]	SONG X D , FAN X C , HE X J ,et al. CNNLoc:deep-learning based indoor localization with WiFi fingerprinting[C]// Proceedings of 2019 IEEE SmartWorld,Ubiquitous Intelligence ＆ Computing,Advanced＆ Trusted Computing,Scalable Computing ＆ Communications,Cloud＆ Big Data Computing,Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI). Piscataway:IEEE Press, 2019: 589-595.
[30]	HAN S , ZHAO C , MENG W X ,et al. Cosine similarity based fingerprinting algorithm in WLAN indoor positioning against device diversity[C]// Proceedings of 2015 IEEE International Conference on Communications. Piscataway:IEEE Press, 2015: 2710-2714.
[31]	IOFFE S , SZEGEDY C . Batch normalization:accelerating deep net-work training by reducing internal covariate shift[C]// Proceedings of the 32nd International Conference on Machine Learning. Cambridge:JMLR, 2015: 448-456.
[32]	XU B , WANG N , CHEN T ,et al. Empirical evaluation of rectified activations in convolutional network[J]. arXiv Preprint,arXiv:1505.00853, 2015.
[33]	ZEILER M D , KRISHNAN D , TAYLOR G W ,et al. Deconvolutional networks[C]// Proceedings of 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway:IEEE Press, 2010: 2528-2535.
[34]	MIYATO T , KATAOKA T , KOYAMA M ,et al. Spectral normalization for generative adversarial networks[J]. arXiv Preprint,arXiv:1802.05957, 2018.
[35]	HE K M , ZHANG X Y , REN S Q ,et al. Identity mappings in deep residual networks[C]// Proceedings of the Computer Vision - ECCV 2016. Berlin:Springer, 2016: 630-645.

场景	场景面积/m²	AP/个	参考点/个	测试点/个
教学楼走廊	220	124	97	92
商场一层	7 800	1 028	300	99