-
摘要: 針對提高Wi-Fi指紋室內定位技術性能，提出了一種基于卷積神經網絡（Convolutional neural networks，CNN）的信道狀態信息（Channel state information，CSI）指紋室內定位方法。在離線階段聯合定位環境參考點的幅度差和相位差信息，利用CNN進行訓練，保存訓練后的CNN網絡模型作為指紋；在線階段，針對不同實驗場景，對測試數據的幅度差信息和相位差信息進行加權處理，引入改進的基于概率的指紋匹配算法，利用待定位點的CSI信息并通過CNN網絡模型預測待定位點的坐標。此外，為增強算法普適性，針對復雜室內場景，提出了雙節點定位方案來提高定位精度。在廊廳和實驗室室內兩種不同定位場景進行了實驗，信息聯合定位算法分別獲得了24.7 cm和48.1 cm的平均定位誤差，驗證了基于CNN的CSI幅度差和相位差聯合定位算法的有效性。Abstract: To improve the performance of Wi-Fi fingerprint indoor positioning technology, a method based on convolutional neural networks (CNNs) for channel state information (CSI) fingerprint indoor positioning is proposed. This method fully exploits the feature extraction capabilities of CNNs, applies the combination of amplitude difference and phase difference information as training data in the offline phase, and uses the trained CNN network model for an online test. In the online phase, for different experimental scenarios, by analyzing the variance of the amplitude information and phase information, the amplitude difference and phase difference information of the test data are weighted to obtain a certain universal weight factor for a better positioning result. At the same time, considering the characteristics of terminal mobility during real-time positioning, the CSI information sampled twice in succession is adopted as test data to increase the diversity of test data. To address the disadvantage of poor positioning performance of traditional probability-based positioning algorithms, an improved probability-based fingerprint matching algorithm is introduced. By passing the CSI information of the point to be located through the CNN network model, it can output the probability average value corresponding to the reference position with the highest probability in all test data packets and weight it with the reference position coordinate to estimate the point to be located. In addition, to enhance the universality of the algorithm, a dual-node positioning scheme is proposed for complex indoor scenes to improve positioning accuracy. Experiments are conducted in two positioning scenarios in a corridor and laboratory, including the amplitude difference positioning performance, the average positioning error of each positioning method, and the performance comparison of positioning algorithms. The information joint positioning algorithm obtains an average positioning error of 24.7 and 48.1 cm, which verifies the effectiveness of the proposed algorithm.
-
圖 3 兩種實驗場景下幅度與相位差的方差。（a）廊廳；（b）實驗室
Figure 3. Variance of the amplitude and phase difference in two experimental scenarios: (a) corridor; (b) laboratory
圖 5 實驗室場景。（a）實景圖；（b）簡化圖
Figure 5. Laboratory: (a) real scenario; (b) simplified scenario
表 1 CNN網絡參數
Table 1. CNN network parameters
Layer Parameter Output shape Input Training data (30，30，3，m) Conv2D 1 Conv 2D，fs=5，s=1 (30，30，16，m) Conv2D 2 Conv 2D，fs=5，s=1 (30，30，16，m) Conv2D 3 Conv 2D，fs=2，s=2 (15，15，32，m) Conv2D 4 Conv 2D，fs=5，s=1 (15，15，32，m) Flatten K=7200 (7200，m) FC 1 K=1024 (1024，m) FC 2 K=512 (512，m) Output K=Nrp (N，m) 
下載: 導出CSV
表 2 廊廳定位誤差和執行時間
Table 2. Corridor positioning error and execution time
Algorithm Mean error/m Standard deviation/m Execution time/s CNNFi combine 0.2473 0.5755 0.3593 CNNFi single 0.7259 1.2447 0.3549 CiFi 1.0845 1.2821 0.4530 DeepFi 0.9939 1.6159 0.1250
下載: 導出CSV
表 3 實驗室定位誤差和執行時間
Table 3. Laboratory positioning error and execution time
Algorithm Mean error/m Standard deviation/m Execution time/s CNNFi combine AP=2 0.4806 0.8566 0.5156 CNNFi combine AP=1 0.7159 0.8564 0.3593 CNNFi single 1.1532 1.2243 0.3437 CiFi 1.3559 1.1390 0.4531 DeepFi 1.4523 1.2082 0.1406
下載: 導出CSV
www.77susu.com<span id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> <span id="fpn9h"><noframes id="fpn9h"> <th id="fpn9h"></th> <strike id="fpn9h"><noframes id="fpn9h"><strike id="fpn9h"></strike> <th id="fpn9h"><noframes id="fpn9h"> <span id="fpn9h"><video id="fpn9h"></video></span> <ruby id="fpn9h"></ruby> <strike id="fpn9h"><noframes id="fpn9h"><span id="fpn9h"></span> -
參考文獻
[1] He S N, Chan S H G. Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons. IEEE Commun Surv Tutorials, 2016, 18(1): 466 doi: 10.1109/COMST.2015.2464084 [2] Kuutti S, Fallah S, Katsaros K, et al. A survey of the state-of-the-art localization techniques and their potentials for autonomous vehicle applications. IEEE Internet Things J, 2018, 5(2): 829 doi: 10.1109/JIOT.2018.2812300 [3] Torres-Sospedra J, Jiménez A, Moreira A, et al. Off-line evaluation of mobile-centric indoor positioning systems: The experiences from the 2017 IPIN competition. Sensors, 2018, 18(2): 487 doi: 10.3390/s18020487 [4] Zhang D Q, Zhao S J, Yang L T, et al. NextMe: localization using cellular traces in Internet of Things. IEEE Trans Ind Inf, 2015, 11(2): 302 doi: 10.1109/TII.2015.2389656 [5] Pak J M, Ahn C K, Shmaliy Y S, et al. Improving reliability of particle filter-based localization in wireless sensor networks via hybrid particle/FIR filtering. IEEE Trans Ind Inf, 2015, 11(5): 1089 doi: 10.1109/TII.2015.2462771 [6] Yassin A, Nasser Y, Awad M, et al. Recent advances in indoor localization: A survey on theoretical approaches and applications. IEEE Commun Surv Tutorials, 2017, 19(2): 1327 doi: 10.1109/COMST.2016.2632427 [7] Faragher R, Harle R. Location fingerprinting with bluetooth low energy beacons. IEEE J Sel Areas Commun, 2015, 33(11): 2418 doi: 10.1109/JSAC.2015.2430281 [8] Meng Y, Xiao X F, Zhao K. An underground localization algorithm and topology optimization based on ultra-wide band. Chin J Eng, 2018, 40(6): 743孟宇, 肖小鳳, 趙坤. 基于UWB的地下定位算法和拓撲優化. 工程科學學報, 2018, 40(6):743 [9] Choi H, Son S, Kim J, et al. RF-Based Indoor Locating System for NLOS Environment // 2010 24th IEEE International Conference on Advanced Information Networking and Applications. Perth, 2010: 628 [10] Wang X D, Wu N, Hu Q Q. Indoor visible light positioning based on multiple illuminated areas cooperation. J Optoelectron Laser, 2017, 28(4): 388王旭東, 吳楠, 胡晴晴. 多照明區域協作的室內可見光定位. 光電子·激光, 2017, 28(4):388 [11] Yang C C, Shao H R. WiFi-based indoor positioning. IEEE Commun Mag, 2015, 53(3): 150 doi: 10.1109/MCOM.2015.7060497 [12] Khalajmehrabadi A, Gatsis N, Akopian D. Modern WLAN fingerprinting indoor positioning methods and deployment challenges. IEEE Commun Surv Tutorials, 2017, 19(3): 1974 doi: 10.1109/COMST.2017.2671454 [13] Feng C, Au W S A, Valaee S, et al. Received-signal-strength-based indoor positioning using compressive sensing. IEEE Trans Mob Comput, 2012, 11(12): 1983 doi: 10.1109/TMC.2011.216 [14] Sohan A A, Ali M, Fairooz F, et al. Indoor Positioning Techniques using RSSI from Wireless Devices // 2019 22nd International Conference on Computer and Information Technology (ICCIT). Dhaka, 2019: 1 [15] Bahl P, Padmanabhan V N. RADAR: An in-building RF-based user location and tracking system // Nineteenth Annual Joint Conference of the IEEE Computer and Communications Societies. Tel Aviv, 2000: 775 [16] Youssef M, Agrawala A. The Horus location determination system. Wirel Networks, 2008, 14(3): 357 doi: 10.1007/s11276-006-0725-7 [17] Hoang M T, Yuen B, Dong X D, et al. Recurrent neural networks for accurate RSSI indoor localization. IEEE Internet Things J, 2019, 6(6): 10639 doi: 10.1109/JIOT.2019.2940368 [18] Wang X Y, Gao L J, Mao S W. CSI phase fingerprinting for indoor localization with a deep learning approach. IEEE Internet Things J, 2016, 3(6): 1113 doi: 10.1109/JIOT.2016.2558659 [19] Halperin D, Hu W J, Sheth A, et al. Predictable 802.11 packet delivery from wireless channel measurements. SIGCOMM Comput Commun Rev, 2010, 40(4): 159 [20] Xie Y X, Li Z J, Li M. Precise power delay profiling with commodity Wi-Fi. IEEE Trans Mob Comput, 2019, 18(6): 1342 doi: 10.1109/TMC.2018.2860991 [21] Wu K S, Xiao J, Yi Y W, et al. CSI-based indoor localization. IEEE Trans Parallel Distributed Syst, 2013, 24(7): 1300 doi: 10.1109/TPDS.2012.214 [22] Wu K S, Xiao J, Yi Y W, et al. FILA: Fine-grained indoor localization // 2012 Proceedings IEEE INFOCOM. Orlando, 2012: 2210 [23] Wang X Y, Gao L J, Mao S W, et al. DeepFi: Deep learning for indoor fingerprinting using channel state information //2015 IEEE Wireless Communications and Networking Conference (WCNC). New Orleans, 2015: 1666 [24] Wang Y, Huang X D, Guo S T. Indoor fingerprint location algorithm based on convolutional neural network. J Software, 2018, 29(Suppl 1): 63王英, 黃旭東, 郭松濤. 基于卷積神經網絡的室內指紋定位算法. 軟件學報, 2018, 29(增刊1): 63 [25] Wang X Y, Wang X Y, Mao S W. CiFi: Deep convolutional neural networks for indoor localization with 5 GHz Wi-Fi // 2017 IEEE International Conference on Communications (ICC). Paris, 2017: 1 [26] Li H, Zeng X, Li Y, et al. Convolutional neural networks based indoor Wi-Fi localization with a novel kind of CSI images. China Communications, 2019, 16(9): 250 doi: 10.23919/JCC.2019.09.019 -
點擊查看大圖
圖(15) / 表(3)
計量
- 文章訪問數: 1217
- HTML全文瀏覽量: 799
- PDF下載量: 146
- 被引次數: 0
