基於CSI 指紋庫之機器學習演算法做 帶缺陷訓練資料之室內定位

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：24

、訪客IP：3.139.69.151

姓名

許哲齊(Che-Chi Hsu) 查詢紙本館藏

畢業系所

通訊工程學系

論文名稱

基於CSI 指紋庫之機器學習演算法做帶缺陷訓練資料之室內定位
(CSI-Based Fingerprints for Machine Learning Method with Indoor Localization of Incomplete Training Data)

相關論文

★ 利用二元關聯法之簡易指紋辨識	★ 基於數位單脈衝接收機與質點演算法之無人機追蹤效能分析
★ 基於輔助波束對之UAV追蹤方法實現	★ 使用MMSE等化器的Filterbank OFDM系統探討
★ Kalman Filtering應用於可適性載波同步系統之研究	★ 無線區域網路之MIMO-OFDM系統設計與電路實現
★ 包含通道追蹤之IEEE 802.11a接收機設計與電路實現	★ 時變通道下的OFDM傳輸系統設計: 基於IEEE 802.11a標準
★ MIMO-OFDM系統各天線間載波頻率偏差之探討與收發機硬體實現	★ 使用雜散式領航訊號之DVB-T系統通道估測演算法與電路實現
★ 數位地面視訊廣播系統同步模組之設計與電路實現	★ 適用於移動式正交分頻多工通訊系統的改良型時域通道響應追蹤演算法
★ 正交分頻多工系統通道估測基於可適性模型化通道參數估測	★ 以共同項載波頻率偏移補償於正交分頻多重存取系統中減少多重存取干擾之方法
★ 正交分頻多工系統之資料訊號裁剪雜訊消除	★ 適用於正交分頻多工通訊系統的改良型決策反饋之卡爾曼濾波通道估測器

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

室內定位(Indoor Localization) 是早於十餘年前就提出的技術，相較於全球定位系統(Global Positioning System, GPS) 的戶外定位系統(Location-Based Service, LBS)，由於衛星訊號無法穿透建材，故無法使用衛星進行定位。但室內定位的應用仍相當廣泛，且具有一定的商業價值，如醫療看護、倉儲、機場、百貨公司等，加上近年來科技技術的提升，使得室內定位搖身一變成為一個熱門的話題。本篇論文採用Wi-Fi 做為室內定位技術，以通道狀態資訊(Channel State Information, CSI) 作為定位方針，先敘述環境參數與設備，並說明各式演算法，從而討論利用各種演算法來進行基本室內定位的準確度，再延伸討論至若有些位置無法採集或不方便採集到通道資訊時，能以什麼樣的方式來進行克服，進而在資訊存有缺陷的情況下實現室內定位。

摘要(英)

Indoor Localization has been being an attracting technology studied over ten years along with the Location-Based Service of Global Positioning System (GPS). Because satellite signals cannot enter building, it is impossible to use satellite signals for indoor localization. However, the application of indoor localization is still quite extensive, and it has some commercial values certainly, such as medical care, warehousing, airports, departments, etc. In recent years, due to the advancement of the computing technology, the issue of indoor localization become an attractive topic.
This thesis adopts Wi-Fi as the technique of Indoor Localization and channel state information (CSI) as the localization fingerprint. First, we describe the problem formulation and the involved equipment. Second, we introduce some machine learning algorithms that are compared in this paper. Then we discuss the accuracy of indoor localization with different machine learning algorithms. In this paper, considering there is some missed information which cannot be collected or is inconvenient to be collected for machine training, we propose a method that can be used to deal with this kind of situation to achieve effective indoor localization.

關鍵字(中)

★ 通道狀態資訊
★ K-近鄰演算法
★ XGBoost
★ 多層感知器

關鍵字(英)

★ Channel State Information
★ K-Nearest Neighbors
★ Extreme Gradient Boosting
★ Multi-Layer Perception

論文目次

第 1 章序論. . . . . . . . . . . . . . . . . . 1
1.1 前言. . . . . . . . . . . . . . . . . . . 1
1.2 章節架構. . . . . . . . . . . . . . . . . 3
第 2 章室內定位之架構. . . . . . . . . . . . . 4
2.1 室內定位. . . . . . . . . . . . . . . . . 4
2.2 帶缺陷之室內定位. . . . . . . . . . . . . 6
2.3 CSI Tools . . . . . . . . . . . . . . . . 7
第 3 章帶缺陷之室內定位流程說明. . . . . . . . 10
3.1 資料處理與指紋庫. . . . . . . . . . . . . 12
3.1.1 資料收集. . . . . . . . . . . . . . . . 12
3.1.2 資料預處理. . . . . . . . . . . . . . . 13
3.2 產生新的CSI 資料. . . . . . . . . . . . . 16
3.2.1 係數法. . . . . . . . . . . . . . . . . 16
3.2.2 隨機產生. . . . . . . . . . . . . . . . 17
3.3 去除非缺陷CSI 資料以建立虛擬CSI . . . . . 19
3.4 建立指紋庫. . . . . . . . . . . . . . . . 20
3.5 CSI 室內定位模擬的建立. . . . . . . . . . 22
3.6 演算法. . . . . . . . . . . . . . . . . . 24
3.6.1 KNN 演算法. . . . . . . . . . . . . . . 24
3.6.2 XGBoost . . . . . . . . . . . . . . . . 25
3.6.3 多層感知器. . . . . . . . . . . . . . . 28
第 4 章室內定位的結果與分析. . . . . . . . . . 30
4.1 室內環境CSI 資料的量測建立. . . . . . . . 30
4.2 電腦模擬通道結果的研究. . . . . . . . . . 34
4.3 量測結果的研究. . . . . . . . . . . . . . 38
4.3.1 完整量測資料之預先測試結果. . . . . . . 38
4.3.2 針對不完整量測資料的研究結果. . . . . . 41
第 5 章結論. . . . . . . . . . . . . . . . . . 52
參考文獻. . . . . . . . . . . . . . . . . . . 53

參考文獻

[1] S. Yang and B. Wang, “Residual based weighted least square algorithm for bluetooth/uwb indoor localization system,” in 2017 36th Chinese Control Conference (CCC), 2017, pp. 5959–5963.
[2] T. Arai, T. Yoshizawa, T. Aoki, K. Zempo, and Y. Okada, “Evaluation of indoor positioning system based on attachable infrared beacons in metal shelf environment,” in 2019 IEEE International Conference on Consumer Electronics (ICCE), 2019, pp. 1–4.
[3] F. Manzoor, Y. Huang, and K. Menzel, “Passive rfid-based indoor positioning system, an algorithmic approach,” in 2010 IEEE International Conference on RFID-Technology and Applications, 2010, pp. 112–117.
[4] J. Y. Zhu, J. Xu, A. X. Zheng, J. He, C. Wu, and V. O. K. Li, “Wifi fingerprinting indoor localization system based on spatio-temporal (s-t) metrics,” in 2014 International Conference on Indoor Positioning and Indoor Navigation (IPIN), 2014, pp. 611–614.
[5] J. Fu, Y. Fu, and D. Xu, “Application of an adaptive ukf in uwb indoor positioning,” in 2019 Chinese Automation Congress (CAC), 2019, pp. 544–549.
[6] T.-H. Lee, S. Weng, and J. Sanford, “Indoor radio triangulation using only rssi data,” in 2020 IEEE International Symposium on Antennas and Propagation and North American Radio Science Meeting, 2020, pp. 1097–1098.
[7] C. Wang, R. Huang, M. Gu, and G. Xiao, “Rssi-based indoor location with circularly polarized antennas and ludm algorithm for wireless sensor network,” in 2017 Sixth Asia-Pacific Conference on Antennas and Propagation (APCAP), 2017, pp. 1–3.
[8] M. Zheng, S. Li, L. Deng, M. Qu, C. Zhang, and C. Cai, “Csi-based indoor high-precision localization system,” in 2018 Asia-Pacific Microwave Conference (APMC), 2018, pp. 357–359.
[9] C. Cai, L. Deng, and S. Li, “Csi-based device-free indoor localization using convolutional neural networks,” in 2018 IEEE 4th International Conference on Computer and Communications (ICCC), 2018, pp. 753–757.
[10] K. Wu, J. Xiao, Y. Yi, D. Chen, X. Luo, and L. M. Ni, “Csi-based indoor localization,” IEEE Transactions on Parallel and Distributed Systems, vol. 24, no. 7, pp. 1300–1309, 2013.
[11] X. Wang, L. Gao, S. Mao, and S. Pandey, “Deepfi: Deep learning for indoor fingerprinting using channel state information,” in 2015 IEEE Wireless Communications and Networking Conference (WCNC), 2015, pp. 1666–1671.
[12] D. Wu, D. Zhu, Y. Liu, and L. Ma, “Joint rss and csi based access point authentication scheme in wifi networks via xgboost,” in 2019 18th IEEE International Conference On Trust, Security And Privacy In Computing And Communications/13th IEEE International Conference On Big Data Science And Engineering (TrustCom/Big- DataSE), 2019, pp. 821–826.
[13] S. M. Samadani, Y. Savaria, and C. Nerguizian, “Indoor localization using channel state information with regression artificial neural networks,” in 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), 2020, pp. 1–4.
[14] Y. Xie, Z. Li, and M. Li, “Precise power delay profiling with commodity wifi,” in Proceedings of the 21st Annual International Conference on Mobile Computing and Networking, ser. MobiCom ’15. New York, NY, USA: ACM, 2015, p. 53–64. [Online]. Available: http://doi.acm.org/10.1145/2789168.2790124
[15] X. Wang, L. Gao, S. Mao, and S. Pandey, “Csi-based fingerprinting for indoor localization: A deep learning approach,” IEEE Transactions on Vehicular Technology, vol. 66, no. 1, pp. 763–776, 2017.
[16] P. Hafezi, D. Wedge, M. Beach, and M. Lawton, “Propagation measurements at 5.2 ghz in commercial and domestic environments,” in Proceedings of 8th International Symposium on Personal, Indoor and Mobile Radio Communications - PIMRC ’97, vol. 2, 1997, pp. 509–513 vol.2.
[17] H. Yigit, “A weighting approach for knn classifier,” in 2013 International Conference on Electronics, Computer and Computation (ICECCO), 2013, pp. 228–231.
[18] T. Chen and C. Guestrin, “Xgboost: A scalable tree boosting system,”CoRR, vol. abs/1603.02754, 2016.

指導教授

張大中(Dah-Chung Chang)

審核日期

2021-10-21

推文