A rapid fingerprint positioning method based on deep convolutional neural network for MIMO-OFDM systems

Abstract

The combination of fingerprint positioning and 5G (the 5th Generation Mobile Communication Technology) offers broader application prospects for indoor positioning technology, but also brings challenges in real-time performance. In this paper, we propose a fingerprint positioning method based on a deep convolutional neural network (DCNN) using a classification approach in a single-base station scenario for massive multiple input multiple output-orthogonal frequency division multiplexing (MIMO-OFDM) systems. We introduce an angle-delay domain fingerprint matrix that simplifies the computation process and increases the location differentiation. The cosine distance is chosen as the fingerprint similarity criterion due to its sensitivity to angular differences. First, the DCNN model is used to determine the sub-area to which the mobile terminal belongs, and then the weighted K-nearest neighbor (WKNN) matching algorithm is used to estimate the position within the sub-area. The positioning performance is simulated in a DeepMIMO indoor environment, showing that the classification DCNN method reduces the positioning time by 77.05% compared to the non-classification method, with only a 1.08% increase in average positioning error.

References

[1] Alkhateeb A (2019) Deepmimo: A generic deep learning dataset for millimeter wave and massive mimo applications. arXiv preprint arXiv:190206435. https://doi.org/10.48550/arXiv.1902.06435

[2] Arnold M, Hoydis J, ten Brink S (2019) Novel massive MIMO channel sounding data applied to deep learning-based indoor positioning. In: 12th International ITG Conference on Systems, Communications and Coding (SCC), VDE, pp 1–6, https://doi.org/10.30420/454862021

[3] AroraG, LaguduR. Enhancing customer shopping experience with indoor lbs in retail stores. Telecom Business Review, 2013, 6(1): 9-16

[4] Belmonte-HernándezA, Hernández-PeñalozaG, GutiérrezDM, et al. . SWiBluX: Multi-sensor deep learning fingerprint for precise real-time indoor tracking. IEEE Sens J, 2019, 19(9): 3473-3486

[5] Boora U, Wang X, Mao S (2022) Robust massive MIMO localization using neural ode in adversarial environments. In: 2022 IEEE International Conference on Communications (ICC), IEEE, pp 4866–4871. https://doi.org/10.1109/ICC45855.2022.9838836

[6] ChenH, ZhangY, LiW, et al. . ConFi: Convolutional neural networks based indoor wi-fi localization using channel state information. IEEE Access, 2017, 5: 18066-18074

[7] DangX, SiX, HaoZ, et al. . A novel passive indoor localization method by fusion CSI amplitude and phase information. Sensors, 2019, 19(4): 875

[8] De Bast S, Guevara AP, Pollin S (2020) CSI-based positioning in massive MIMO systems using convolutional neural networks. In: 2020 IEEE 91st vehicular technology conference (VTC), IEEE, pp 1–5. https://doi.org/10.1109/VTC2020-Spring48590.2020.9129126

[9] FanJ, ZhangJ, DouX. Single-site indoor fingerprint localization based on MIMO-CSI. China Communications, 2021, 18(8): 199-208

[10] Gong X, Yu X, Liu X, et al (2022) Machine learning-based fingerprint positioning for massive MIMO systems. IEEE Access 10:89320–89330. https://doi.org/10.1109/ACCESS.2022.3199728

[11] GuoX, AnsariN, LiL, et al. . Indoor localization by fusing a group of fingerprints based on random forests. IEEE Internet Things J, 2018, 5(6): 4686-4698

[12] HuaJ, YinY, WangA, et al. . Geometry-based non-line-of-sight error mitigation and localization in wireless communications. SCIENCE CHINA Inf Sci, 2019, 62(202301): 1-15

[13] KolodziejKW, HjelmJ. Local positioning systems: LBS applications and services, 2017FloridaCRC Press

[14] LawI, LoeH. Generic airport location-based services using an integrated indoor positioning system. Journal of Airport Management, 2020, 14(2): 123-140

[15] Löffler C, Riechel S, Fischer J, et al (2018) Evaluation criteria for inside-out indoor positioning systems based on machine learning. In: 2018 International Conference on Indoor Positioning and Indoor Navigation (IPIN), IEEE, pp 1–8. https://doi.org/10.1109/IPIN.2018.8533862

[16] ModiY, TeliR, MehtaA, et al. . A comprehensive review on intelligent traffic management using machine learning algorithms. Innovative Infrastructure Solutions, 2022, 7(1): 128

[17] Prakash VC, Nagarajan G (2020) A hybrid RSS-TOA based localization for distributed indoor massive MIMO systems. In: Emerging Trends in Computing and Expert Technology, Springer, pp 1359–1370. https://doi.org/10.1007/978-3-030-32150-5138

[18] RenY, WangX, LiuL, et al. . Fast fingerprint localisation based on product quantisation and convolution neural network in a massive MIMO system. International Journal of Sensor Networks, 2022, 40(1): 67-75

[19] ShinK, McConvilleR, MetatlaO, et al. . Outdoor localization using ble RSSI and accessible pedestrian signals for the visually impaired at intersections. Sensors, 2022, 22(1): 371

[20] ŠoštarićD, MesterG. Drone localization using ultrasonic TDOA and RSS signal: Integration of the inverse method of a particle filter. FME Transactions, 2020, 48(1): 21-30

[21] SunX, WuC, GaoX, et al. . Fingerprint-based localization for massive MIMO-OFDM system with deep convolutional neural networks. IEEE Trans Veh Technol, 2019, 68(11): 10846-10857

[22] Vieira J, Leitinger E, Sarajlic M, et al (2017) Deep convolutional neural networks for massive MIMO fingerprint-based positioning. In: 2017 IEEE 28th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), IEEE, pp 1–6. https://doi.org/10.1109/PIMRC.2017.8292280

[23] WangW, YangB, ZhangW. Deep learning-based radio map for MIMO-OFDM downlink precoding. J Commun Info Net, 2023, 8(3): 203-211

[24] Wang X, Gao L, Mao S (2015) PhaseFi: Phase fingerprinting for indoor localization with a deep learning approach. In: 2015 IEEE Global Communications Conference (GLOBECOM), IEEE, pp 1–6. https://doi.org/10.1109/GLOCOM.2015.7417517

[25] WangX, GaoL, MaoS, et al. . CSI-based fingerprinting for indoor localization: A deep learning approach. IEEE Trans Veh Technol, 2016, 66(1): 763-776

[26] Wang X, Wang X, Mao S (2017) CiFi: Deep convolutional neural networks for indoor localization with 5 ghz Wi-Fi. In: 2017 IEEE International Conference on Communications (ICC), IEEE, pp 1–6. https://doi.org/10.1109/ICC.2017.7997235

[27] WuC, YiX, WangW, et al. . Learning to localize: A 3d CNN approach to user positioning in massive MIMO-OFDM systems. IEEE Trans Wireless Commun, 2021, 20(7): 4556-4570

[28] Xu Y, Chen X, Ma L (2010) LBS based disaster and emergency management. In: 2010 18th International Conference on Geoinformatics, IEEE, pp 1–5. https://doi.org/10.1109/GEOINFORMATICS.2010.5567872

[29] Zhang L, Ding E, Zhao Z, et al (2017) A novel fingerprinting using channel state information with MIMO–OFDM. Cluster Computing 20:3299–3312. https://doi.org/10.1007/s10586-017-1072-4

[30] Zhou J, Deng W, Li L (2019) Study on LBS-based positioning technique of pipeline robot. In: 2019 International Conference on Wireless Communication, Network and Multimedia Engineering (WCNME), Atlantis Press, pp 54–56. https://doi.org/10.2991/wcnme-19.2019.13

[31] ZhuX, QuW, QiuT, et al. . Indoor intelligent fingerprint-based localization: Principles, approaches and challenges. IEEE Communications Surveys & Tutorials, 2020, 22(4): 2634-2657