(3.238.7.202) 您好!臺灣時間:2021/03/03 22:47
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果

詳目顯示:::

我願授權國圖
: 
twitterline
研究生:柯舜友
研究生(外文):KO, SHUN-YU
論文名稱:RSSI室內定位系統的設計與實現
論文名稱(外文):The Design and Implementation of RSSI Indoor Positioning Systems
指導教授:吳和庭吳和庭引用關係
指導教授(外文):WU, HO-TING
口試委員:吳和庭柯開維葉丁鴻
口試委員(外文):WU, HO-TINGKE, KAI-WEIYEH, DIG-HORNG
口試日期:2020-07-28
學位類別:碩士
校院名稱:國立臺北科技大學
系所名稱:資訊工程系
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2020
畢業學年度:108
語文別:中文
論文頁數:56
中文關鍵詞:室內定位系統質量彈簧模型(Mass-Spring Model)神經網路(Neural Network)接收訊號強度指標(RSSI)
外文關鍵詞:Indoor Positioning SystemMass-Spring ModelNeural NetworkRSSI
相關次數:
  • 被引用被引用:0
  • 點閱點閱:81
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
室內定位系統不僅是工業4.0轉型的重要一環,諸如醫療中心或博物館等場域,也開始導入室內定位的基礎設備,用來收集人流,熱門區域分布等重要資料,以發展出新的應用。但高精準度的定位往往需要購買昂貴的設備佈署,所以本論文旨在設計一個新的定位演算法,能在精度和設備佈署成本上,取得較佳的平衡。
本論文使用ZigBee, BLE與UWB技術,開發異質網路整合的無線感測定位系統。考慮到傳統RSSI指紋定位演算法在實際佈署需要大量人力與時間,我們輔以UWB系統,簡化地圖指紋資料庫的演算法,可大幅降低建置之時間成本。實驗主軸分成兩個部分,第一部分基於質量彈簧模型之定位演算法,採用移動式錨點的設計與UWB所提供之位置資訊,強化此演算法的定位效率,並優化定位精準度;第二部分利用BLE與UWB的整合,設計新的指紋定位演算法,以路徑的方式建構指紋地圖,並採用單層神經網路來做室內定位與路徑追蹤。兩套演算法皆在大小兩個不同實驗場域進行實測,且在大場域實驗中,質量彈簧模型取得了平均80公分的定位誤差,而神經網路模型取得了平均89公分的定位誤差,皆優於傳統的RSSI定位結果。

The indoor positioning system plays an important part in the era of Industry 4.0. In addition to factories, medical centers and museums have begun to deploy indoor positioning systems to collect important data, such as the pedestrian flow or the distribution of popular areas to develop new applications. However, high-precision positioning systems often require expensive equipment for deployment, so this research work aims to design a new positioning mechanism that can achieve a better balance between accuracy and equipment deployment costs.
In this thesis, we integrate ZigBee, BLE and UWB technology to develop wireless sensor positioning systems for heterogeneous networks. Considering that the traditional RSSI fingerprint positioning algorithm requires lots of manpower and time for deployment, we use the UWB positioning system to facilitate the buildup of the fingerprint database, which can reduce the time cost of database construction significantly. The experiment is divided into two parts. The first part is based on the positioning algorithm of the mass spring model, which uses mobile anchors and the position information provided by UWB to enhance the positioning efficiency of this algorithm and optimize the positioning accuracy; In the second part, we integrate BLE and UWB to design a new fingerprint positioning algorithm through the use of a single-layer neural network for indoor positioning and path tracking system.
Both algorithms are conducted in two different experimental fields. In the experiments with large areas, the mass spring model achieved an average positioning error of 80 cm. On the other hand, the neural network model achieved an average positioning error of 89 cm. These results are superior to those obtained by traditional RSSI positioning methods.

摘要 i
ABSTRACT iii
誌 謝 v
目錄 vi
表目錄 vii
圖目錄 viii
第一章 緒論 1
1.1 研究動機 1
1.2 研究目的 1
1.3 論文架構 2
第二章 相關技術與背景 3
2.1室內定位無線通訊技術 3
2.2室內定位方法 4
2.3 質量彈簧模型 10
2.4卡爾曼濾波器 11
2.5 神經網路 13
第三章 室內定位演算法設計與實作 15
3.1 基於質量彈簧模型之室內定位演算法設計與實現 15
3.1.1實驗情境定義 15
3.1.2實驗架構設計 17
3.1.3 質量彈簧模型實作 18
3.2 基於神經網路模型之室內定位演算法設計與實現 22
3.2.1實驗情境定義 22
3.2.2實驗架構設計 24
3.2.3卡爾曼濾波器之RSSI前處理 25
3.2.4 神經網路模型 26
第四章 實驗結果與分析 31
4.1 質量彈簧模型實驗結果與分析 31
4.1.1 小場域實驗結果 31
4.1.2 大場域實驗結果 35
4.2 神經網路模型實驗結果與分析 39
4.2.1實驗情境介紹 39
4.2.2 訓練資料集 40
4.2.3 小場域實驗結果 41
4.2.4大場域實驗結果 46
4.2.5雙模型神經網路設計與實驗結果 51
第五章 結論與未來展望 53
參考文獻 54

[1] F. Zafari, A. Gkelias and K. K. Leung, "A Survey of Indoor Localization Systems and Technologies," in IEEE Communications Surveys & Tutorials, vol. 21, no. 3, pp. 2568-2599, thirdquarter 2019, doi: 10.1109/COMST.2019.2911558.
[2] G. R. Aiello, "Challenges for ultra-wideband (UWB) CMOS integration," IEEE Radio Frequency Integrated Circuits (RFIC) Symposium, 2003, Philadelphia, PA, USA, 2003, pp. 497-500, doi: 10.1109/RFIC.2003.1213993.
[3] S. S. Saab and Z. S. Nakad, "A Standalone RFID Indoor Positioning System Using Passive Tags," in IEEE Transactions on Industrial Electronics, vol. 58, no. 5, pp. 1961-1970, May 2011, doi: 10.1109/TIE.2010.2055774.
[4] Bai, Y.B., Wu, S., Wu, H.R., & Zhang, K. (2012). Overview of RFID-Based Indoor Positioning Technology. GSR.
[5] M. E. Rida, F. Liu, Y. Jadi, A. A. A. Algawhari and A. Askourih, "Indoor Location Position Based on Bluetooth Signal Strength," 2015 2nd International Conference on Information Science and Control Engineering, Shanghai, 2015, pp. 769-773, doi: 10.1109/ICI.
[6] C. Yang and H. Shao, "WiFi-based indoor positioning," in IEEE Communications Magazine, vol. 53, no. 3, pp. 150-157, March 2015, doi: 10.1109/MCOM.2015.7060497.
[7] J. Larranaga, L. Muguira, J. Lopez-Garde and J. Vazquez, "An environment adaptive ZigBee-based indoor positioning algorithm," 2010 International Conference on Indoor Positioning and Indoor Navigation, Zurich, 2010, pp. 1-8, doi: 10.1109/IPIN.2010.5647828.
[8] 陳宗逸,2018年版通訊產業關鍵報告.
[9] A. Yassin et al., "Recent Advances in Indoor Localization: A Survey on Theoretical Approaches and Applications," in IEEE Communications Surveys & Tutorials, vol. 19, no. 2, pp. 1327-1346, Secondquarter 2017, doi: 10.1109/COMST.2016.2632427.
[10] J. Xiong and K. Jamieson, "ArrayTrack: A fine-grained indoor location system", Proc. 10th USENIX Symp. Netw. Syst. Design Implement. (NSDI), pp. 71-84, 2013.
[11] Sedlacek, Petr & Masek, Pavel & Slanina, Martin. (2019). An Overview of the IEEE 802.15.4z Standard and its Comparison to the Existing UWB Standards. 10.1109/RADIOELEK.2019.8733537.
[12] B. Verso, “HRP UWB PHY enhancements”, IEEE Standards Association - Documents, [online], 2018, accessed: 25-Feb.-2019, Available from: http://www.ieee802.org/15/pub/TG4z.html.
[13] J. Xu, M. Ma and C. L. Law, "Performance of time-difference-of-arrival ultra wideband indoor localisation," in IET Science, Measurement & Technology, vol. 5, no. 2, pp. 46-53, March 2011, doi: 10.1049/iet-smt.2010.0051.
[14] Li G, Geng E, Ye Z, Xu Y, Lin J, Pang Y. Indoor Positioning Algorithm Based on the Improved RSSI Distance Model. Sensors (Basel). 2018;18(9):2820. Published 2018 Aug 27. doi:10.3390/s18092820.
[15] S. He and S.-H. G. Chan "Wi-Fi fingerprint-based indoor positioning: Recent advances and comparisons" IEEE Commun. Surveys Tuts. vol. 18 no. 1 pp. 466-490 1st Quart. 2016.
[16] A. Howard, M. J. Mataric and G. Sukhatme, "Relaxation on a mesh: a formalism for generalized localization," Proceedings 2001 IEEE/RSJ International Conference on Intelligent Robots and Systems. Expanding the Societal Role of Robotics in the the Next M.
[17] F. Franceschini, M. Galetto, D. Maisano, L. Mastrogiacomo, "A review of localization algorithms for distributed wireless sensor networks in manufacturing," International Journal of Computer Integrated Manufacturing, vol. 22, no.7, pp. 698-716, April 2.
[18] Cui, X., Wang, M., Li, J., Ji, M., Liu, J., Huang, T., & Chen, H. (2019).Data process for indoor positioning based on WiFi fingerprint. Weihai: European Alliance for Innovation (EAI). doi:http://dx.doi.org/10.4108/eai.29-6-2019.2282793.
[19] Greg Welch and Gary Bishop, “An Introduction to the Kalman Filter , Monday, July 24, 2006”.
[20] Y .Kim and H. Bang. ”Introduction to Kalman Filter and Its Applications.” IntechOpen).
[21] LIN, JIN-WEI(2020)。The Wireless Sensor Network Indoor Localization Algorithm using Machine Learning。Master Thesis, Department of Information Engineering, National Taipei University of Technology,Taipei。 From https://hdl.handle.net/11296/rrncpz.
[22] Sithole, G. and Zlatanova, S.: POSITION, LOCATION, PLACE AND AREA: AN INDOOR PERSPECTIVE, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., III-4, 89-96, https://doi.org/10.5194/isprs-annals-III-4-89-2016, 2016...
[23] Nowicki, M.; Wietrzykowski, J. Low-Effort Place Recognition with Wi-Fi Fingerprints Using Deep Learning; Springer International Publishing: Cham, Switzerland, 2016.
[24] Zhong, Zhenghang & Tang, Zhe & Li, Xiangxing & Yuan, Tiancheng & Yang, Yang & Wei, Meng & Zhang, Yuanyuan & Sheng, Renzhi & Grant, Naomi & Ling, Chongfeng & Huan, Xintao & Kim, Kyeong Soo & Lee, Sanghyuk. (2018). XJTLUIndoorLoc: A New Fingerprinting Data.
[25] Alexander, Ivan & Kusuma, Gede. (2019). Predicting Indoor Position Using Bluetooth Low Energy And Machine Learning. International Journal of Scientific & Technology Research. 8. 1661-1667.
[26] W. Yu, J. Choi, Y. Kim, W. Lee and S. Kim, "Self-Organizing Localization With Adaptive Weights for Wireless Sensor Networks," in IEEE Sensors Journal, vol. 18, no. 20, pp. 8484-8492, 15 Oct.15, 2018.
[27] Kingma, D. P., & Ba, J. L. (2015). Adam: a Method for Stochastic Optimization. International Conference on Learning Representations, 1–13..
[28] 李宜倫(2019)。基於質量彈簧模型之無線感測網路定位演算法。國立臺北科技大學資訊工程系碩士論文,台北市。 取自https://hdl.handle.net/11296/c6j75p.
[29] Erdem, Ebubekir & Tuncer, T. & Doğan, Resul. (2018). Localization of a Mobile Device with Sensor Using a Cascade Artificial Neural Network-Based Fingerprint Algorithm. International Journal of Computational Intelligence Systems. 12. 238. 10.2991/ijcis.201.

電子全文 電子全文(網際網路公開日期:20210817)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
系統版面圖檔 系統版面圖檔